{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:33:22Z","timestamp":1778348002203,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Institute for Artificial Intelligence of Things, The Hong Kong Polytechnic University, HK RGC Grant for Theme-Based Research Scheme","award":["T43-513\/23-N"],"award-info":[{"award-number":["T43-513\/23-N"]}]},{"DOI":"10.13039\/501100011646","name":"Hong Kong RGC Collaborative Research Fund","doi-asserted-by":"publisher","award":["C5032-23G"],"award-info":[{"award-number":["C5032-23G"]}],"id":[{"id":"10.13039\/501100011646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,5,15]]},"DOI":"10.1109\/jiot.2024.3524255","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T19:41:51Z","timestamp":1735674111000},"page":"13119-13131","source":"Crossref","is-referenced-by-count":122,"title":["EdgeShard: Efficient LLM Inference via Collaborative Edge Computing"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1653-108X","authenticated-orcid":false,"given":"Mingjin","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}]},{"given":"Xiaoming","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2725-2529","authenticated-orcid":false,"given":"Jiannong","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}]},{"given":"Zeyang","family":"Cui","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4727-4856","authenticated-orcid":false,"given":"Shan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref3","article-title":"PaLM 2 technical report","volume-title":"arXiv:2305.10403","author":"Anil","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2024.3506221"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29860"},{"key":"ref8","article-title":"GPTQ: Accurate post-training quantization for generative pretrained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref9","first-page":"1","article-title":"OPTQ: Accurate quantization for generative pretrained transformers","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Frantar"},{"key":"ref10","article-title":"AWQ: Activation-aware weight quantization for LLM compression and acceleration","author":"Lin","year":"2023","journal-title":"arXiv:2306.00978"},{"key":"ref11","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref12","article-title":"EdgeQAT: Entropy and distribution guided quantizationaware training for the acceleration of lightweight LLMs on the edge","author":"Shen","year":"2024","journal-title":"arXiv:2402.10787"},{"key":"ref13","article-title":"PrivateLoRA for efficient privacy preserving LLM","author":"Wang","year":"2023","journal-title":"arXiv:2311.14030"},{"key":"ref14","article-title":"NetGPT: A native-AI network architecture beyond provisioning personalized generative services","author":"Chen","year":"2023","journal-title":"arXiv:2307.06148"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SOSE55356.2022.00026"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SEC54971.2022.00019"},{"key":"ref17","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","volume":"32","author":"Huang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3325413.3329787"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3058532"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796896"},{"key":"ref23","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref24","first-page":"99","article-title":"Linux advanced routing & traffic control HOWTO","volume":"1","author":"Hubert","year":"2002","journal-title":"Netherlabs BV"},{"key":"ref25","first-page":"1","article-title":"Pointer sentinel mixture models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Merity"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2947893"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2021.3098816"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737614"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858384"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00099"},{"key":"ref32","article-title":"LAMBO: Large AI model empowered edge intelligence","author":"Dong","year":"2023","journal-title":"arXiv:2308.15078"},{"key":"ref33","article-title":"Large language model enhanced multiagent systems for 6G communications","author":"Jiang","year":"2023","journal-title":"arXiv:2312.07850"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300550"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3384013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2021.02.011"},{"key":"ref37","article-title":"Decentralized physical infrastructure network (DePIN): Challenges and opportunities","author":"Lin","year":"2024","journal-title":"arXiv:2406.02239"},{"key":"ref38","article-title":"Petals: Collaborative inference and fine-tuning of large models","author":"Borzunov","year":"2022","journal-title":"arXiv:2209.01188"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3151670"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SEED51797.2021.00025"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/10993477\/10818760.pdf?arnumber=10818760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T18:01:57Z","timestamp":1746813717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10818760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,15]]},"references-count":40,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2024.3524255","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,15]]}}}