{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:44:15Z","timestamp":1775745855342,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"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":[[2024,6,19]]},"DOI":"10.1109\/iwqos61813.2024.10682900","type":"proceedings-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T17:41:00Z","timestamp":1727372460000},"page":"1-10","source":"Crossref","is-referenced-by-count":3,"title":["COS: Cross-Processor Operator Scheduling for Multi-Tenant Deep Learning Inference"],"prefix":"10.1109","author":[{"given":"Changyao","family":"Lin","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cuda multi-streams","year":"2015"},{"key":"ref2","article-title":"Multi-instance gpu","year":"2020"},{"key":"ref3","article-title":"Multi-process service","year":"2020"},{"key":"ref4","article-title":"A survey of multi-tenant deep learning inference on gpu","author":"Yu","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568520"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00038"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485938"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538948"},{"key":"ref10","first-page":"167","article-title":"Ios: Inter-operator scheduler for cnn acceleration","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Ding"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643501"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3583120.3586953"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3492886"},{"key":"ref14","article-title":"Cuda c\/c++ streams and concurrency","year":"2012"},{"key":"ref15","first-page":"578","article-title":"{TVM} : An automated {End-to-End} optimizing compiler for deep learning","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen"},{"key":"ref16","article-title":"Darts: Differentiable architecture search","author":"Liu","year":"2018"},{"key":"ref17","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Tensorflow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1602.07360"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref23","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref24","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Cuda programming guide","year":"2020"},{"key":"ref26","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1339-y"}],"event":{"name":"2024 IEEE\/ACM 32nd International Symposium on Quality of Service (IWQoS)","location":"Guangzhou, China","start":{"date-parts":[[2024,6,19]]},"end":{"date-parts":[[2024,6,21]]}},"container-title":["2024 IEEE\/ACM 32nd International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10682818\/10682608\/10682900.pdf?arnumber=10682900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T04:40:17Z","timestamp":1727412017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10682900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,19]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iwqos61813.2024.10682900","relation":{},"subject":[],"published":{"date-parts":[[2024,6,19]]}}}