{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T22:28:36Z","timestamp":1782944916863,"version":"3.54.5"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100004316","name":"IBM","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004316","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/ccgrid64434.2025.00066","type":"proceedings-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T17:36:08Z","timestamp":1751304968000},"page":"53-62","source":"Crossref","is-referenced-by-count":3,"title":["Energy Efficient Scheduling of AI\/ML Workloads on Multi Instance Gpus with Dynamic Repartitioning"],"prefix":"10.1109","author":[{"given":"Ellie","family":"Lipe","sequence":"first","affiliation":[{"name":"Columbia University,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neel","family":"Karia","sequence":"additional","affiliation":[{"name":"Columbia University,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Connor","family":"Espenshade","sequence":"additional","affiliation":[{"name":"Columbia University,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clifford","family":"Stein","sequence":"additional","affiliation":[{"name":"Columbia University,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asser","family":"Tantawi","sequence":"additional","affiliation":[{"name":"IBM TJ Watson Research Center,Yorktown Heights,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Tardieu","sequence":"additional","affiliation":[{"name":"IBM TJ Watson Research Center,Yorktown Heights,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"AI is pushing the world toward an energy crisis. forbes.","author":"Cohen","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605600"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1239\/jap\/1308662637"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/math8101803"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2004.06.011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530510"},{"key":"ref7","volume-title":"Serving dnn models with multi-instance gpus: A case of the reconfigurable machine scheduling problem","author":"Tan","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.151"},{"key":"ref10","first-page":"119","article-title":"Zeus: Understanding and optimizing GPU energy consumption of DNN training","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"You"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1007\/s10845-021-01847-3","article-title":"Reinforcement learning applications to machine scheduling problems: a comprehensive literature review","volume":"34","author":"Behice","year":"2023","journal-title":"Journal of Intelligent Manufacturing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER52292.2023.00023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN52240.2021.9522309"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00069"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655830"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563510"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00124"},{"key":"ref19","article-title":"Serving DNN models with multi-instance GPUs: A case of the reconfigurable machine scheduling problem","author":"Tan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2012.10.002"},{"key":"ref21","volume-title":"Deep reinforcement learning: An overview","author":"Li","year":"2018"},{"key":"ref22","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in Large-Scale heterogeneous GPU clusters","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Weng"}],"event":{"name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","location":"Troms\u00f8, Norway","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,22]]}},"container-title":["2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11044421\/11044790\/11044810.pdf?arnumber=11044810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T06:02:31Z","timestamp":1751349751000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11044810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ccgrid64434.2025.00066","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}