{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T22:58:29Z","timestamp":1768517909878,"version":"3.49.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"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","award":["62402141"],"award-info":[{"award-number":["62402141"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2025A1515011785,2023A1515110271"],"award-info":[{"award-number":["2025A1515011785,2023A1515110271"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323176","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["HyDLR: Load-Aware Dynamic Rescheduling for Deep Learning Hybrid Deployment"],"prefix":"10.1109","author":[{"given":"Desheng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology,Shenzhen,China"}]},{"given":"Xiao","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science, Harbin Institute of Technology,Harbin,China"}]},{"given":"Shuo","family":"Si","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science, Harbin Institute of Technology,Harbin,China"}]},{"given":"Sichao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Cyberspace Science, Harbin Institute of Technology,Harbin,China"}]},{"given":"Weizhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology,Shenzhen,China"}]}],"member":"263","reference":[{"issue":"08","key":"ref1","first-page":"29","article-title":"Strengthening computing power as a foundation: Driving stable progress of data centers","author":"Wu","year":"2024","journal-title":"China Financial Computer"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2015.07.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387517"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2021.3132627"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS60453.2023.00305"},{"key":"ref7","first-page":"787","article-title":"SHEPHERD: Serving DNNs in the wild","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Zhang","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS60453.2023.00367"},{"key":"ref9","first-page":"539","article-title":"Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Han","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796670"},{"key":"ref11","first-page":"19","article-title":"A case for task sampling based learning for cluster job scheduling","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Jajoo","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3075625"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2018.2794344"},{"key":"ref14","volume-title":"Evolution of baidu\u2019s large-scale strategic mixed scheduling system","author":"Zhang","year":"2019"},{"key":"ref15","volume-title":"The evolution of large-scale co-location technology at alibaba","author":"Xin","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421285"},{"key":"ref17","first-page":"397","article-title":"INFaaS: Automated model-less inference serving","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Romero","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655833"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00049"},{"key":"ref20","first-page":"559","article-title":"Alpa: Automating inter- and intra-operator parallelism for distributed deep learning","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zheng","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-024-01340-8"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1145\/3458817.3476223","article-title":"Characterization and prediction of deep learning workloads in large-scale gpu datacenters","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, ser. SC \u201921","author":"Hu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587445"},{"key":"ref24","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Qiao","year":"2021"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323176.pdf?arnumber=11323176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:11:02Z","timestamp":1768461062000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323176","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}