{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T20:58:43Z","timestamp":1775768323383,"version":"3.50.1"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:00:00Z","timestamp":1776211200000},"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":["62350710797"],"award-info":[{"award-number":["62350710797"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology Plan Project of Shenzhen through Project","award":["JSGG20220831110002004"],"award-info":[{"award-number":["JSGG20220831110002004"]}]},{"DOI":"10.13039\/501100001809","name":"China Association for Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,4,15]]},"DOI":"10.1109\/jiot.2026.3657494","type":"journal-article","created":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:00:27Z","timestamp":1769202027000},"page":"15717-15732","source":"Crossref","is-referenced-by-count":0,"title":["Coconut: Multilevel Collaborative Deployment for Real-Time Deep Learning Tasks in Heterogeneous Edge GPU Cluster"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6805-2649","authenticated-orcid":false,"given":"Changyao","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenming","family":"Chen","sequence":"additional","affiliation":[{"name":"China Construction Steel Structure Engineering Corporation Ltd., Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6209-6886","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Smart Farm Technologies and Systems, Harbin Institute of Technology, Harbin, Heilongjiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2970550"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2757384.2757397"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AINA.2010.187"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-6186-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/J.ENG.2017.05.015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2017.8038375"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2015.03.008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3391196"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.02.050"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICBAIE49996.2020.00027"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IEEE.EDGE.2017.50"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3027681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3119950"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HotWeb.2015.22"},{"key":"ref17","volume-title":"Cuda Multi-Streams","year":"2015"},{"key":"ref18","volume-title":"Multi-Process Service","year":"2020"},{"key":"ref19","volume-title":"Multi-Instance GPU","year":"2020"},{"key":"ref20","article-title":"A survey of multi-tenant deep learning inference on GPU","author":"Yu","year":"2022","journal-title":"arXiv:2203.09040"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3492886"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00032"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485938"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560551"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3583120.3586955"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037698"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568520"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538948"},{"key":"ref30","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref31","first-page":"167","article-title":"IOS: Inter-operator scheduler for CNN acceleration","volume-title":"Proc. Mach. Learn. Syst.","author":"Ding"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3511543"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref34","first-page":"19974","article-title":"Chasing sparsity in vision transformers: An end-to-end exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref36","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-48424-7_18"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453520"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS59052.2023.00020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3715014.3722076"},{"key":"ref41","first-page":"1","article-title":"Distributing deep neural networks with containerized partitions at the edge","volume-title":"Proc. 2nd USENIX Workshop Hot Topics Edge Comput. (HotEdge)","author":"Zhou"},{"key":"ref42","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","volume":"30","author":"Agustsson","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"2","key":"ref43","first-page":"22","article-title":"Lzw data compression","volume":"3","author":"Dheemanth","year":"2014","journal-title":"Amer. J. Eng. Res."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00038"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.01578"},{"key":"ref48","article-title":"DARTS: Differentiable architecture search","author":"Liu","year":"2018","journal-title":"arXiv:1806.09055"},{"key":"ref49","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Des. Implement. (OSDI)","author":"Abadi","year":"2016"},{"key":"ref50","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3583120.3586953"},{"key":"ref52","volume-title":"Triton Inference Server","year":"2023"},{"key":"ref53","volume-title":"K3s: Lightweight Kubernetes","year":"2023"},{"key":"ref54","volume-title":"Kubernetes","year":"2023"},{"key":"ref55","volume-title":"YOLOv5 By Ultralytics","author":"Jocher","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref58","volume-title":"Nvidia Jetson Nano","year":"2022"},{"key":"ref59","volume-title":"Nvidia Jetson Xavier","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643501"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682900"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref63","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref64","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref65","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref66","article-title":"A brief review of TVM: An automated end-to-end optimizing compiler for deep learning","author":"Malpani","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.29172\/7c2a6982-6d72-4cd8-bba6-2fccb06a7011"},{"key":"ref68","volume-title":"Nvidia Jetson Tx2","year":"2022"},{"key":"ref69","volume-title":"Nvidia A100","year":"2024"},{"key":"ref70","volume-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results","author":"Everingham","year":"2012"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1339-y"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref75","volume-title":"Cuda Programming Guide","year":"2020"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref77","volume-title":"ONNX: Open Neural Network Exchange","author":"Bai","year":"2019"},{"key":"ref78","volume-title":"Nvidia Tensorrt","year":"2022"},{"key":"ref79","volume-title":"Jetson-Stats","author":"Bonghi","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3754448"},{"key":"ref85","article-title":"A survey of resource-efficient LLM and multimodal foundation models","author":"Xu","year":"2024","journal-title":"arXiv:2401.08092"},{"key":"ref86","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Devlin"},{"key":"ref87","first-page":"208","article-title":"Nimble: Efficiently compiling dynamic neural networks for model inference","volume-title":"Proc. Mach. Learn. Syst.","author":"Shen"},{"key":"ref88","first-page":"848","article-title":"Dietcode: Automatic optimization for dynamic tensor programs","volume-title":"Proc. Mach. Learn. Syst.","volume":"4","author":"Zheng"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11477814\/11363182.pdf?arnumber=11363182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:49:54Z","timestamp":1775764194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11363182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,15]]},"references-count":88,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3657494","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,15]]}}}