{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T05:17:08Z","timestamp":1737004628479,"version":"3.33.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"DOI":"10.1109\/ictc62082.2024.10827238","type":"proceedings-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:40:10Z","timestamp":1736883610000},"page":"295-300","source":"Crossref","is-referenced-by-count":0,"title":["Latency-Aware GPU Scheduling for DL Inference Tasks with Internal Resource Partitioning Strategy"],"prefix":"10.1109","author":[{"given":"Taewoo","family":"Kim","sequence":"first","affiliation":[{"name":"School of Electrical Engineering KAIST,Deajeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changha","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering KAIST,Deajeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chan-Hyun","family":"Youn","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering KAIST,Deajeon,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017370"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359658"},{"key":"ref8","first-page":"613","article-title":"Clipper: A Low-Latency online prediction serving system","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Crankshaw","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"key":"ref10","first-page":"443","article-title":"Serving {DNNs} like clockwork: Performance predictability from the bottom up","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Gujarati","year":"2020"},{"key":"ref11","article-title":"Salus: Fine-grained gpu sharing primitives for deep learning applications","author":"Yu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"199","article-title":"Serving heterogeneous machine learning models on {Multi-GPU} servers with {Spatio-Temporal} sharing","volume-title":"2022 USENIX Annual Technical Con-ference (USENIX ATC 22)","author":"Choi","year":"2022"},{"volume-title":"NVIDIA multi-process service","key":"ref13"},{"volume-title":"NVIDIA multi-instance gpu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref16","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"}],"event":{"name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2024,10,16]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 15th International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10826571\/10826594\/10827238.pdf?arnumber=10827238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T07:04:11Z","timestamp":1736924651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10827238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/ictc62082.2024.10827238","relation":{},"subject":[],"published":{"date-parts":[[2024,10,16]]}}}