{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:46:53Z","timestamp":1782798413426,"version":"3.54.5"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571411","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Memory-Efficient KV Cache Optimization for Large Language Model Inference at the Edge"],"prefix":"10.1109","author":[{"given":"Chi","family":"Zhang","sequence":"first","affiliation":[{"name":"Hefei University of Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haisheng","family":"Tan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotian","family":"Pan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haohua","family":"Du","sequence":"additional","affiliation":[{"name":"Beihang University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Fu","sequence":"additional","affiliation":[{"name":"University of Göttingen,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1506"},{"key":"ref2","article-title":"Efficient streaming language models with attention sinks","volume-title":"ICLR 2024","author":"Xiao"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0722"},{"key":"ref4","article-title":"Quest: Query-aware sparsity for efficient long-context LLM inference","author":"Tang","year":"2024"},{"key":"ref5","article-title":"SparQ Attention: Bandwidth-efficient LLM inference","volume-title":"ICML 2024","author":"Ribar"},{"key":"ref6","article-title":"Post-training sparse attention with double sparsity","author":"Yang","year":"2024"},{"key":"ref7","article-title":"LServe: Efficient long-sequence LLM serving with unified sparse attention","volume-title":"MLSys 2025","author":"Yang"},{"key":"ref8","article-title":"Twilight: Adaptive attention sparsity with hierarchical top-p pruning","author":"Lin","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1147\/sj.52.0078"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/363095.363141"},{"key":"ref11","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate LLM serving","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Zhao"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68279-0_8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipl.2015.09.004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2786.2793"},{"key":"ref15","article-title":"Compressive transformers for long-range sequence modelling","author":"Rae","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref17","article-title":"Yarn: Efficient context window extension of large language models","author":"Peng","year":"2023"},{"key":"ref18","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref19","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref20","article-title":"LLaMA-2-7B-32K","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.112"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.195"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0040"},{"key":"ref24","article-title":"Dynamic memory compression: Retrofitting LLMs for accelerated inference","volume-title":"ICML 2024","author":"Nawrot"},{"key":"ref25","article-title":"Gear: An efficient kv cache compression recipe for near-lossless generative inference of LLM","author":"Kang","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2193"},{"key":"ref27","article-title":"AdaSplash: Adaptive sparse flash attention","volume-title":"ICML 2025","author":"Gon\u00e7alves"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696099"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044447"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044591"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1126"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3447579"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3109"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571411.pdf?arnumber=11571411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:38:46Z","timestamp":1782797926000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571411","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}