{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:34:42Z","timestamp":1777995282443,"version":"3.51.4"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T00:00:00Z","timestamp":1726444800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T00:00:00Z","timestamp":1726444800000},"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":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014121","name":"Xilinx","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014121","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,16]]},"DOI":"10.1109\/socc62300.2024.10737825","type":"proceedings-article","created":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T18:29:41Z","timestamp":1730831381000},"page":"1-6","source":"Crossref","is-referenced-by-count":9,"title":["Efficient Deployment of Large Language Model across Cloud-Device Systems"],"prefix":"10.1109","author":[{"given":"Fan","family":"Yang","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhao","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohao","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Practitioners\u2019 expectations on code completion","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.03846"},{"key":"ref2","article-title":"Llmempowered chatbots for psychiatrist and patient simulation: application and evaluation","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv:2305.13614"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.54364\/AAIML.2023.1191"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3178211"},{"key":"ref6","article-title":"A survey on efficient inference for large language models","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv:2404.14294"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","article-title":"Llm inference performance engineering: Best practices","author":"Agarwal","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3279579"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467097"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2020.2997008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3042320"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412700"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621342"},{"key":"ref16","article-title":"Perllm: Personalized inference scheduling with edge-cloud collaboration for diverse llm services","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv:2405.14636"},{"key":"ref17","article-title":"Edgeshard: Efficient 1 m inference via collaborative edge computing","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv:2405.14371"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/EMPDP.2019.8671606"},{"key":"ref19","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"}],"event":{"name":"2024 IEEE 37th International System-on-Chip Conference (SOCC)","location":"Dresden, Germany","start":{"date-parts":[[2024,9,16]]},"end":{"date-parts":[[2024,9,19]]}},"container-title":["2024 IEEE 37th International System-on-Chip Conference (SOCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10737725\/10737709\/10737825.pdf?arnumber=10737825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T08:18:51Z","timestamp":1732695531000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10737825\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,16]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/socc62300.2024.10737825","relation":{},"subject":[],"published":{"date-parts":[[2024,9,16]]}}}