{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:45:26Z","timestamp":1785912326259,"version":"3.56.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":[[2026,6]]},"DOI":"10.1109\/2575-8411.2026.00033","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:19:09Z","timestamp":1785871149000},"page":"272-282","source":"Crossref","is-referenced-by-count":0,"title":["Efficient KV Cache Migration for Geo-Distributed LLM Inference in Collaborative Edge Computing"],"prefix":"10.1109","author":[{"given":"Mingjin","family":"Zhang","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiannong","family":"Cao","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangchun","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ne","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639187"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3527641"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s42486-025-00227-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SOSE55356.2022.00026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.004.2300479"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM52923.2024.10901542"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2024.3524255"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044734"},{"key":"ref11","article-title":"Collaborative large language model inference via resource-aware parallel speculative decoding","author":"Koh","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Petals: Collaborative inference and fine-tuning of large models","author":"Borzunov","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"12312","DOI":"10.52202\/075280-0540","article-title":"Distributed inference and fine-tuning of large language models over the Internet","volume":"36","author":"Borzunov","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/Blockchain67634.2025.00023"},{"key":"ref15","article-title":"Keep the cost down: A review on methods to optimize llm\u2019s kv-cache consumption","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"173","article-title":"Llumnix: Dynamic scheduling for large language model serving","volume-title":"18th USENIX symposium on operating systems design and implementation (OSDI 24)","author":"Sun","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044533"},{"key":"ref18","first-page":"31094","article-title":"Flexgen: High-throughput generative inference of large language models with a single gpu","volume-title":"International Conference on Machine Learning","author":"Sheng","year":"2023"},{"key":"ref19","first-page":"155","article-title":"{InfiniGen}: Efficient generative inference of large language models with dynamic {KV} cache management","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Lee","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2017.01.002"},{"key":"ref25","volume-title":"Geometric algorithms and combinatorial optimization","volume":"2","author":"Gr\u00f6tschel","year":"2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/800057.808695"},{"key":"ref27","first-page":"122","article-title":"A n52 algorithm for maximum matchings in bipartite graphs","author":"Hopcroft","year":"2012","journal-title":"DBLP"},{"key":"ref28","article-title":"Pointer sentinel mixture models","volume-title":"International Conference on Learning Representations","author":"Merity","year":"2017"},{"key":"ref29","first-page":"193","article-title":"{DistServe}: Disaggregating prefill and decoding for goodput-optimized large language model serving","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.195"},{"key":"ref31","article-title":"Kivi: A tuning-free asymmetric 2bit quantization for kv cache","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Model tells you where to merge: Adaptive kv cache merging for 1lms on long-context tasks","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2279"},{"key":"ref34","first-page":"114","article-title":"Keyformer: Kv cache reduction through key tokens selection for efficient generative inference","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Adnan","year":"2024"},{"key":"ref35","article-title":"Kvlink: Accelerating large language models via efficient kv cache reuse","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","first-page":"325","article-title":"Prompt cache: Modular attention reuse for low-latency inference","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Gim","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.623"},{"key":"ref38","first-page":"135","article-title":"{ServerlessLLM}: {Low-Latency} serverless inference for large language models","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Fu","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3070974"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3225239"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3558984"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3128037"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3506221"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2871842"}],"event":{"name":"2026 IEEE 46th International Conference on Distributed Computing Systems (ICDCS)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2026,6,22]]},"end":{"date-parts":[[2026,6,25]]}},"container-title":["2026 IEEE 46th International Conference on Distributed Computing Systems (ICDCS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11618978\/11618981\/11619197.pdf?arnumber=11619197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:53:19Z","timestamp":1785909199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11619197\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/2575-8411.2026.00033","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}