{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:07:21Z","timestamp":1784135241154,"version":"3.55.0"},"reference-count":38,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/ccgrid64434.2025.00052","type":"proceedings-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T17:36:08Z","timestamp":1751304968000},"page":"363-372","source":"Crossref","is-referenced-by-count":1,"title":["rInfer: A Generic and High-Performance Framework for Remote Inference with Heterogeneous Accelerators"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Jin","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiquan","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijing","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yin","family":"Du","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiexiong","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhai","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingchang","family":"Qin","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kanghua","family":"Fang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhi","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"543","article-title":"A survey on deep learning for recommendation systems","volume":"35","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref6","first-page":"123","article-title":"Exploring the limits of transfer learning for neural machine translation","volume":"11","author":"Tang","year":"2023","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref7","first-page":"1244912460","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/978-3-030-71593-9_13","article-title":"Criket-An Open-Source Virtualization Layer for CUDA Applications","volume-title":"Euro-Par 2020: Parallel Processing Workshops","volume":"12480","author":"Eiling"},{"key":"ref10","first-page":"20","article-title":"Sla-driven ml inference framework for clouds with heterogeneous accelerators","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Cho"},{"key":"ref11","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"},{"key":"ref12","volume-title":"Nvidia a10","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6474"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HIPINEB.2016.8"},{"key":"ref18","first-page":"995","article-title":"Beware of fragmentation: Scheduling GPU-Sharing workloads with fragmentation gradient descent","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Weng"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587445"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00077"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS.2010.5547126"},{"key":"ref22","volume-title":"Pytorch serve","year":"2020"},{"key":"ref23","article-title":"Tensorflow-serving: Flexible, high-performance ml serving","author":"Olston","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","volume-title":"Pytorch serve configuration guide","year":"2024"},{"key":"ref25","volume-title":"Tensorflow serving rest api","year":"2024"},{"key":"ref26","volume-title":"NVIDIA Developer"},{"key":"ref27","volume-title":"Torch 7: A scientific computing framework for luajit","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2011.112"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339609"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom2018.2018.00049"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS59830.2024.10575103"},{"key":"ref32","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS 2019)"},{"issue":"6","key":"ref33","first-page":"1243","article-title":"The tensorflow and pytorch frameworks for machine learning applications: A comparative review","volume":"35","author":"Zhang","year":"2020","journal-title":"Journal of Computer Science and Technology"},{"key":"ref34","first-page":"35","article-title":"Optimizing pytorch for edge computing","volume-title":"Proceedings of the 2021 IEEE International Conference on Edge Computing (EDGE)","author":"Liu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15277-1_37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SC.Companion.2012.146"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6474"},{"key":"ref38","first-page":"112","article-title":"cl opencl-supporting distributed heterogeneous computing in hpc clusters","volume-title":"European Conference on Parallel Processing","author":"Alves"}],"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\/11044806.pdf?arnumber=11044806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T05:33:37Z","timestamp":1751348017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11044806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ccgrid64434.2025.00052","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}