{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:45:33Z","timestamp":1782798333931,"version":"3.54.5"},"reference-count":15,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571450","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Enabling Memory-Disaggregated Cloud Infrastructure for LLMs: An Adaptive CXL-based KV Cache Scheduling Approach"],"prefix":"10.1109","author":[{"given":"Ke","family":"Wang","sequence":"first","affiliation":[{"name":"IEIT SYSTEMS Co., Ltd.,Jinan,China,250101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqian","family":"Zhao","sequence":"additional","affiliation":[{"name":"IEIT SYSTEMS Co., Ltd.,Jinan,China,250101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"IEIT SYSTEMS Co., Ltd.,Jinan,China,250101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Gao","sequence":"additional","affiliation":[{"name":"IEIT SYSTEMS Co., Ltd.,Jinan,China,250101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"IEIT SYSTEMS Co., Ltd.,Jinan,China,250101"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"69","article-title":"LegoOS: A disseminated, distributed OS for hardware resource disaggregation","volume-title":"Proc. 13th USENIX Symp. Oper. Syst. Des. Implement. (OSDI)","author":"Shan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2024.3373763"},{"key":"ref4","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Sheng"},{"key":"ref5","article-title":"Compute Express Link 3.0","author":"Sharma","year":"2022","journal-title":"white paper, CXL Consortium"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"ref7","article-title":"SGLang HiCache: Hierarchical KV cache for large language models","volume-title":"GitHub Repository","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507731"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582063"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613167"},{"key":"ref11","first-page":"33","article-title":"NOMAD: Non-exclusive memory tiering via transactional page migration","volume-title":"Proc. 18th USENIX Symp. Oper. Syst. Des. Impl. (OSDI)","author":"Xiang"},{"key":"ref12","first-page":"809","article-title":"Cost-efficient large language model serving for multi-turn conversations with CachedAttention","volume-title":"Proc. 2024 USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Gao"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3749168"},{"key":"ref14","article-title":"KVFlow: Efficient prefix caching for accelerating LLM-based multi-agent workflows","author":"Pan","year":"2025"},{"key":"ref15","article-title":"Improving WWW proxies performance with greedy-dual-size-frequency caching policy","volume-title":"Tech. Rep. HPL-98-69","author":"Cherkasova","year":"1998"}],"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\/11571450.pdf?arnumber=11571450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:24:20Z","timestamp":1782797060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571450\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571450","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}