{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T07:05:58Z","timestamp":1780988758775,"version":"3.54.1"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"State Grid Corporation of China, Science and Technology","award":["5700-202358842A-4-3-WL"],"award-info":[{"award-number":["5700-202358842A-4-3-WL"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcc.2026.3685862","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:05:40Z","timestamp":1776715540000},"page":"1202-1216","source":"Crossref","is-referenced-by-count":0,"title":["HASE: Hardware-Aware Scheduling for Inference Tasks in Heterogeneous GPU Clusters"],"prefix":"10.1109","volume":"14","author":[{"given":"Yanqi","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3592-0328","authenticated-orcid":false,"given":"Congfeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunpeng","family":"Wu","sequence":"additional","affiliation":[{"name":"China Electric Power Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"China Electric Power Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghe","family":"Ye","sequence":"additional","affiliation":[{"name":"China Electric Power Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longchuan","family":"Yan","sequence":"additional","affiliation":[{"name":"State Grid Information Telecommunication Branch, State Grid, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianing","family":"Niu","sequence":"additional","affiliation":[{"name":"State Grid Information Telecommunication Branch, State Grid, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junming","family":"Liu","sequence":"additional","affiliation":[{"name":"Supercomputing Center and IT Center, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingjia","family":"Lao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref3","article-title":"Production-grade container orchestration","year":"2024"},{"key":"ref4","article-title":"Openshift container platform documentation","year":"2024"},{"key":"ref5","first-page":"295","article-title":"Mesos: A platform for fine-grained resource sharing in the data center","volume-title":"Proc. 8th USENIX Symp. Netw. Syst. Des. Implementation","author":"Hindman"},{"key":"ref6","article-title":"Apache hadoop YARN","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380362"},{"key":"ref8","first-page":"947","article-title":"Analysis of large-scale multi-tenant GPU clusters for DNN training workloads","volume-title":"Proc. 2019 USENIX Annu. Tech. Conf.","author":"Jeon"},{"key":"ref9","article-title":"Schedule GPUs","year":"2020"},{"key":"ref10","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Symp. Netw. Syst. Des. Implementation","author":"Gu"},{"key":"ref11","article-title":"NVIDIA A100 tensor core GPU architecture","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icse-seip58684.2023.00039"},{"key":"ref13","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters","volume-title":"Proc. 19th USENIX Symp. Netw. Syst. Des. Implementation","author":"Weng"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2020.3034500"},{"key":"ref15","article-title":"NVIDIA H100 tensor core GPU architecture","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624663"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575705"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467882"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-020-00636-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/en16073187"},{"key":"ref21","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Xiao"},{"key":"ref22","article-title":"Multi-process service","year":"2025"},{"key":"ref23","article-title":"Prometheus overview","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3529113.3529124"},{"key":"ref25","article-title":"DynaServe: Unified and elastic tandem-style execution for dynamic disaggregated LLM serving","author":"Ruan","year":"2025"},{"key":"ref26","article-title":"NVIDIA triton inference server","year":"2026"},{"key":"ref27","article-title":"cuDNN: Efficient primitives for deep learning","author":"Chetlur","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2024.3373763"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.29172\/7c2a6982-6d72-4cd8-bba6-2fccb06a7011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref32","first-page":"3149","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Ke"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6245519\/11554470\/11488572.pdf?arnumber=11488572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T06:21:49Z","timestamp":1780986109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11488572\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":31,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2026.3685862","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"value":"2168-7161","type":"electronic"},{"value":"2372-0018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}