{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T20:09:19Z","timestamp":1788811759867,"version":"build-2803163510"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"18","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272050"],"award-info":[{"award-number":["62272050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62302048"],"award-info":[{"award-number":["62302048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Guangdong Key Lab of AI and Multi-modal Data Processing, Beijing Normal-Hong Kong Baptist University, Zhuhai","award":["2023-2024 Grants sponsored by Guangdong Provincial Department of Education"],"award-info":[{"award-number":["2023-2024 Grants sponsored by Guangdong Provincial Department of Education"]}]},{"name":"Institute of Artificial Intelligence and Future Networks (BNU-Zhuhai) and Engineering Center of AI and Future Education, Guangdong Provincial Department of Science and Technology, China"},{"name":"Zhuhai Science-Tech Innovation Bureau","award":["2320004002772"],"award-info":[{"award-number":["2320004002772"]}]},{"name":"Interdisciplinary Intelligence SuperComputer Center of Beijing Normal University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/jiot.2026.3718029","type":"journal-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T19:10:59Z","timestamp":1785352259000},"page":"43872-43882","source":"Crossref","is-referenced-by-count":0,"title":["Efficient LLM Coserving at the Edge via Resource-Aware Cooperative Scheduling"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7661-1922","authenticated-orcid":false,"given":"Zhenzheng","family":"Li","sequence":"first","affiliation":[{"name":"Beijing Normal University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9375-4818","authenticated-orcid":false,"given":"Zhiqing","family":"Tang","sequence":"additional","affiliation":[{"name":"Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0994-3297","authenticated-orcid":false,"given":"Jianxiong","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1000-3937","authenticated-orcid":false,"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shenzhen University of Advanced Technology","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676356"},{"key":"ref2","article-title":"LMSYS-chat-1M: A large-scale real-world LLM conversation dataset","author":"Zheng","year":"2023","journal-title":"arXiv:2309.11998"},{"key":"ref3","article-title":"A comprehensive survey on process-oriented automatic text summarization with exploration of LLM-based methods","author":"Zhang","year":"2024","journal-title":"arXiv:2403.02901"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SenSys-ML62579.2024.00007"},{"key":"ref5","article-title":"Health-LLM: Large language models for health prediction via wearable sensor data","author":"Kim","year":"2024","journal-title":"arXiv:2401.06866"},{"key":"ref6","volume-title":"Triton Inference Server: An Optimized Cloud and Edge Inferencing Solution","year":"2023"},{"key":"ref7","volume-title":"Text Generation Inference","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3456549"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00099"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658473"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695964"},{"key":"ref13","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sheng"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"ref15","article-title":"ConServe: Fine-grained GPU harvesting for LLM Online and offline co-serving","author":"Qiao","year":"2024","journal-title":"arXiv:2410.01228"},{"key":"ref16","article-title":"BurstGPT: A real-world workload dataset to optimize LLM serving systems","author":"Wang","year":"2024","journal-title":"arXiv:2401.17644"},{"key":"ref17","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref18","first-page":"34635","article-title":"Time-MoE: Billion-scale time series foundation models with mixture of experts","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Shi"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717481"},{"key":"ref20","first-page":"1","article-title":"QServe: W4A8KV4 quantization and system co-design for efficient LLM serving","volume-title":"Proc. Mach. Learn. Syst. (MLSys)","author":"Lin"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref22","first-page":"521","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Yu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/085713-0502"},{"key":"ref25","article-title":"Towards resource-efficient serverless LLM inference with SLINFER","author":"Xu","year":"2025","journal-title":"arXiv:2507.00507"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HDIS60872.2023.10499636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2026.3656318"},{"key":"ref28","article-title":"Efficient LLM serving on hybrid real-time and best-effort requests","author":"Borui","year":"2025","journal-title":"arXiv:2504.09590"},{"key":"ref29","first-page":"1639","article-title":"Resource multiplexing in tuning and serving large language models","volume-title":"Proc. USENIX Annu. Tech. Conf. (ATC)","author":"He"},{"key":"ref30","article-title":"FlexLLM: Token-level co-serving of LLM inference and finetuning with SLO guarantees","author":"Oliaro","year":"2024","journal-title":"arXiv:2402.18789"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11679112\/11627859.pdf?arnumber=11627859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:14:51Z","timestamp":1788808491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11627859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":30,"journal-issue":{"issue":"18"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3718029","relation":{},"ISSN":["2327-4662"],"issn-type":[{"value":"2327-4662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}