{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:03:49Z","timestamp":1781280229304,"version":"3.54.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"State Scholarship Fund of China Scholarship Council","doi-asserted-by":"publisher","award":["202106470020"],"award-info":[{"award-number":["202106470020"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Research Foundation, Singapore, and the Infocomm Media Development Authority under its Future Communications Research and Development Program"},{"name":"Defence Science Organization (DSO) National Laboratories under the Artificial Intelligence (AI) Singapore Program"},{"name":"Singapore Ministry of Education (MOE) Tier 1","award":["RG87\/22"],"award-info":[{"award-number":["RG87\/22"]}]},{"name":"Nanyang Technological University (NTU) Centre for Computational Technologies in Finance"},{"name":"Ministry of Education, Singapore, under its Academic Research Fund Tier 2","award":["MOE-T2EP20221-0017"],"award-info":[{"award-number":["MOE-T2EP20221-0017"]}]},{"name":"Singapore University of Technology and Design (SUTD) Kickstarter Initiative","award":["SKI 20210204"],"award-info":[{"award-number":["SKI 20210204"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/twc.2024.3497923","type":"journal-article","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T19:13:51Z","timestamp":1732130031000},"page":"643-658","source":"Crossref","is-referenced-by-count":48,"title":["Beyond the Cloud: Edge Inference for Generative Large Language Models in Wireless Networks"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2141-431X","authenticated-orcid":false,"given":"Xinyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1414-0621","authenticated-orcid":false,"given":"Jiangtian","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7178-9067","authenticated-orcid":false,"given":"Yudong","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1561-3577","authenticated-orcid":false,"given":"Gaochang","family":"Xie","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4440-941X","authenticated-orcid":false,"given":"Zehui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Information Systems Technology and Design (ISTD) Pillar, Singapore University of Technology and Design, Tampines, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0729-1299","authenticated-orcid":false,"given":"Jiang","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4140-287X","authenticated-orcid":false,"given":"Xuemin","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900292"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594067"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2023.3321538"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3435752"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC57260.2024.10571127"},{"key":"ref6","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref7","article-title":"Unleashing the power of edge-cloud generative AI in mobile networks: A survey of AIGC services","author":"Xu","year":"2023","journal-title":"arXiv:2303.16129"},{"key":"ref8","article-title":"Enabling AI-generated content (AIGC) services in wireless edge networks","author":"Du","year":"2023","journal-title":"arXiv:2301.03220"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.006.2300223"},{"key":"ref10","volume-title":"GPT-4 Architecture, Datasets, Costs and More Leaked","author":"Schreiner","year":"2023"},{"key":"ref11","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","first-page":"17456","article-title":"Confident adaptive language modeling","volume-title":"Proc. NeurIPS","volume":"35","author":"Schuster"},{"key":"ref14","article-title":"High-throughput generative inference of large language models with a single GPU","author":"Sheng","year":"2023","journal-title":"arXiv:2303.06865"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436771"},{"key":"ref16","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"arXiv:2106.08295"},{"key":"ref17","article-title":"A comprehensive study on post-training quantization for large language models","author":"Yao","year":"2023","journal-title":"arXiv:2303.08302"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00049"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3242724"},{"key":"ref20","first-page":"521","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"Proc. OSDI","author":"Yu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/21582440221082130"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"},{"key":"ref23","volume-title":"Samsung Bans ChatGPT, AI Chatbots After Data Leak Blunder","author":"Sea","year":"2023"},{"key":"ref24","volume-title":"ChatGPT Users Report Being Able To See Random People\u2019s Chat Histories","author":"Cole","year":"2023"},{"key":"ref25","volume-title":"ChatGPT4 Now With 50 Messages Every 3 Hours","year":"2023"},{"key":"ref26","volume-title":"Claude 2","year":"2023"},{"key":"ref27","volume-title":"Future of RPG Games-Bannerlord and ChatGPT","year":"2023"},{"key":"ref28","article-title":"LLM.int8(): 8-bit matrix multiplication for transformers at scale","author":"Dettmers","year":"2022","journal-title":"arXiv:2208.07339"},{"key":"ref29","volume-title":"OpenAI Playground","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105693"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3001012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipl.2006.06.003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155418"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3205427"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-6198-6_18"},{"key":"ref37","article-title":"Training and evaluation of a multilingual tokenizer for GPT-SW3","author":"Stollenwerk","year":"2023","journal-title":"arXiv:2304.14780"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3120520"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2018.8690707"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2019.2910590"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3007640"},{"key":"ref42","volume-title":"NVIDIA AI Inference Platform Technical Overview","year":"2023"},{"key":"ref43","volume-title":"BLOOM-3B Model Card","year":"2023"},{"key":"ref44","volume-title":"BLOOM-7B1 Model Card","year":"2023"},{"key":"ref45","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/10836118\/10759588.pdf?arnumber=10759588","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T06:05:06Z","timestamp":1736489106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10759588\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":45,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/twc.2024.3497923","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}