{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:41:41Z","timestamp":1786390901075,"version":"build-2736575974"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","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"}]},{"name":"Guangdong Key Lab of AI and Multi-modal Data Processing"},{"name":"Beijing Normal-Hong Kong Baptist University","award":["2023-2024"],"award-info":[{"award-number":["2023-2024"]}]},{"DOI":"10.13039\/501100010226","name":"Department of Education of Guangdong Province","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100010226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Institute of Artificial Intelligence and Future Networks and Engineering Center of AI and Future Education"},{"DOI":"10.13039\/501100007162","name":"Guangdong Provincial Department of Science and Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007162","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Zhuhai Science-Tech Innovation Bureau","award":["2320004002772"],"award-info":[{"award-number":["2320004002772"]}]},{"name":"Interdisciplinary Intelligence Super Computer Center of Beijing Normal University at Zhuhai"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tmc.2026.3697118","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T19:43:10Z","timestamp":1779824590000},"page":"15221-15233","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Layer-Granularity Unloading for LLMs in Edge Computing"],"prefix":"10.1109","volume":"25","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6268-2559","authenticated-orcid":false,"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\/3605943"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3649506"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3353265"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3386936"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3394689"},{"key":"ref6","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS 19)","author":"Paszke","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","first-page":"613","article-title":"Clipper: A $\\lbrace${Low-Latency$\\rbrace$} online prediction serving system","volume-title":"Proc. 14th USENIX Symp. Netw. Syst. Des. Implementation","author":"Crankshaw","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3338015"},{"key":"ref10","article-title":"Conserve: Harvesting GPUS for low-latency and high-throughput large language model serving","author":"Qiao","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519584"},{"key":"ref12","first-page":"205","article-title":"Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Shahrad","year":"2020"},{"key":"ref13","first-page":"69","article-title":"Help rather than recycle: Alleviating cold startup in serverless computing through $\\lbrace${Inter-Function$\\rbrace$} container sharing","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Li","year":"2022"},{"key":"ref14","article-title":"AWS Lambda","year":"2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658473"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.29"},{"key":"ref17","article-title":"Airllm: Scaling large language models on low-end commodity computers","author":"Li","year":"2023"},{"key":"ref18","article-title":"Accelerate","author":"Gugger","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057029"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796705"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.108752"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3006388"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/100794018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TON.2025.3649068"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00013"},{"key":"ref26","article-title":"S-LoRA: Serving thousands of concurrent LoRA adapters","author":"Sheng","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2024.3427421"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00105"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696099"},{"key":"ref31","article-title":"Perllm: Personalized inference scheduling with edge-cloud collaboration for diverse LLM services","author":"Yang","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"ref33","article-title":"Safetensors","author":"Face","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6566944"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2593069.2593070","article-title":"A cost efficient online algorithm for automotive idling reduction","volume-title":"Proc. 51st Annu. Des. Automat. Conf.","author":"Dong","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2014.2326988"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737413"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2017.04.025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.02.009"},{"key":"ref40","article-title":"Qwen-7B-Chat","author":"Cloud","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref42","article-title":"Fast inference of mixture-of-experts language models with offloading","author":"Eliseev","year":"2023"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11644029\/11535298.pdf?arnumber=11535298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:15:53Z","timestamp":1786389353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11535298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":42,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2026.3697118","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}