{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:23:20Z","timestamp":1783787000046,"version":"3.55.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Hong Kong RGC GRF","doi-asserted-by":"publisher","award":["HKBU 12200418"],"award-info":[{"award-number":["HKBU 12200418"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Green Commun. Netw."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/tgcn.2022.3171680","type":"journal-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T19:45:32Z","timestamp":1651779932000},"page":"1649-1659","source":"Crossref","is-referenced-by-count":5,"title":["Energy-Efficient Online Scheduling of Transformer Inference Services on GPU Servers"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7680-1419","authenticated-orcid":false,"given":"Yuxin","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2986-967X","authenticated-orcid":false,"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9745-4372","authenticated-orcid":false,"given":"Xiaowen","family":"Chu","sequence":"additional","affiliation":[{"name":"Data Science and Analytics Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref2","volume-title":"Google\u2019s neural machine translation system","author":"Wu","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref4","volume-title":"Attending to mathematical language with transformers","author":"Wangperawong","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref9","volume-title":"Huggingface benchmark","year":"2019"},{"key":"ref10","first-page":"446","article-title":"MLPerfinference benchmark","volume-title":"Proc. ACM\/IEEE 47th Int. Symp. Comput. Archit. (ISCA)","author":"Reddi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-15"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3077839.3077858"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441578"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3307772.3328315"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3004623"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2016.10.001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3077839.3077855"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057205"},{"key":"ref19","volume-title":"NVIDIA multi-process service","year":"2019"},{"key":"ref20","volume-title":"NVIDIA multi-instance GPU","year":"2021"},{"key":"ref21","volume-title":"Efficient 8-bit quantization of transformer neural machine language translation model","author":"Bhandare","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190541"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iThings-GreenCom-CPSCom-SmartData-Cybermatics50389.2020.00067"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1058129.1058148"},{"key":"ref25","volume-title":"NVIDIA tesla V100 GPU architecture","year":"2018"},{"key":"ref26","volume-title":"Programming tensor cores in CUDA 9","year":"2017"},{"key":"ref27","volume-title":"Understanding searches better","author":"Nayak","year":"2019"},{"key":"ref28","volume-title":"Bing delivers its largest improvement in search experience","author":"Zhu","year":"2020"},{"key":"ref29","volume-title":"Google document translation service","year":"2019"},{"key":"ref30","volume-title":"AWS translation","year":"2020"},{"key":"ref31","volume-title":"Faster transformer: Highly optimized transformer-based encoder and decoder component","author":"Corporations","year":"2019"},{"key":"ref32","volume-title":"TensorRT 7 for inference","author":"Corporations","year":"2019"},{"key":"ref33","volume-title":"NVIDIA management library","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015466"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS51385.2021.00025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref38","article-title":"Distilling the knowledge in a neural network","volume-title":"arxiv.abs\/1503.02531","author":"Hinton","year":"2015"}],"container-title":["IEEE Transactions on Green Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7511293\/9863718\/09769760.pdf?arnumber=9769760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:33:02Z","timestamp":1705962782000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9769760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":38,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tgcn.2022.3171680","relation":{},"ISSN":["2473-2400"],"issn-type":[{"value":"2473-2400","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}