{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:00:47Z","timestamp":1784822447368,"version":"3.55.0"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004410","name":"T?rkiye Bilimsel ve Teknolojik Ara?t?rma Kurumu","doi-asserted-by":"publisher","award":["119E353"],"award-info":[{"award-number":["119E353"]}],"id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018177","name":"Telefonaktiebolaget LM Ericsson","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018177","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3592308","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T17:56:37Z","timestamp":1753379797000},"page":"131614-131637","source":"Crossref","is-referenced-by-count":4,"title":["Edge-LLM Inference With Cost-Aware Layer Allocation and Adaptive Scheduling"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8556-5657","authenticated-orcid":false,"given":"Sama","family":"Habibi","sequence":"first","affiliation":[{"name":"Faculty of Engineering and Natural Sciences, Sabancı University, Istanbul, Türkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3454-5610","authenticated-orcid":false,"given":"Ozgur","family":"Ercetin","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Natural Sciences, Sabancı University, Istanbul, Türkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Serving models, fast and slow: Optimizing heterogeneous LLM inferencing workloads at scale","author":"Jaiswal","year":"2025","journal-title":"arXiv:2502.14617"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5772\/intechopen.1005876"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2984887"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096914"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583413"},{"key":"ref6","article-title":"HexGen: Generative inference of large language model over heterogeneous environment","author":"Jiang","year":"2023","journal-title":"arXiv:2311.11514"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCBDA51879.2021.9442523"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.10.028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/VTS-APWCS.2019.8851649"},{"key":"ref10","first-page":"23202","article-title":"On-device inference with transformers: Optimization and scheduling","volume-title":"Proc. NeurIPS","volume":"35","author":"Wang"},{"key":"ref11","article-title":"Robust DNN partitioning and resource allocation under uncertain inference time","author":"Nan","year":"2025","journal-title":"arXiv:2503.21476"},{"key":"ref12","article-title":"Flashattention: Fast and memory-efficient exact attention with IO-awareness","author":"Dao","year":"2022","journal-title":"arXiv:2205.14135"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640383"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3339788"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e29959"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT.2017.8204109"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626493000083"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2008.25"},{"issue":"1","key":"ref21","first-page":"276","article-title":"An efficient technique for scheduling algorithm in real time environment for optimizing the operating system","volume":"2","author":"Arvindhan","year":"2018","journal-title":"Int. J. Comput. Sci. Wireless Secur."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2016EDP7374"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3431379.3460639"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.11591\/eei.v10i5.2812"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1142\/S0217595916500482"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2009.31"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1142\/S012962649500031X"},{"key":"ref28","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019","journal-title":"arXiv:1909.08053"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2017.02.013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2005.184"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11095716.pdf?arnumber=11095716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T18:52:12Z","timestamp":1753901532000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11095716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3592308","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}