{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:49:45Z","timestamp":1765039785045,"version":"3.28.0"},"reference-count":31,"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"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006952","name":"Louisiana Board of Regents","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006952","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,19]]},"DOI":"10.1109\/iwqos61813.2024.10682915","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":10,"title":["HarmonyBatch: Batching multi-SLO DNN Inference with Heterogeneous Serverless Functions"],"prefix":"10.1109","author":[{"given":"Jiabin","family":"Chen","sequence":"first","affiliation":[{"name":"East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing"}]},{"given":"Fei","family":"Xu","sequence":"additional","affiliation":[{"name":"East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing"}]},{"given":"Yikun","family":"Gu","sequence":"additional","affiliation":[{"name":"East China Normal University,Shanghai Key Laboratory of Multidimensional Information Processing"}]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Louisiana at Lafayette"}]},{"given":"Fangming","family":"Liu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory"}]},{"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472501"},{"key":"ref2","first-page":"1877","article-title":"Language Models Are Few-shot Learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"ServerlessLLM: Locality-Enhanced Serverless Inference for Large Language Models","year":"2024","author":"Fu","key":"ref3"},{"year":"2023","key":"ref4","article-title":"Function Compute"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605638"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507732"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3232715"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624664"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507709"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3609510.3609816"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14778\/3547305.3547313"},{"article-title":"AWS Lambda Power Tuning","year":"2023","author":"Casalboni","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155363"},{"key":"ref15","first-page":"205","article-title":"Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Provider","volume-title":"Proc. of USENIX ATC","author":"Shahrad"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624783"},{"article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","year":"2014","author":"Simonyan","key":"ref17"},{"key":"ref18","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proc. of NAACL-HLT","author":"Devlin"},{"year":"2023","key":"ref19","article-title":"Install and Use cGPU on a Docker Container"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624645"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/IWQoS61813.2024.10682915","article-title":"HarmonyBatch: Batching multi-SLO DNN Inference with Heterogeneous Serverless Functions","author":"Chen","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/1968633"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref24","first-page":"10 078","article-title":"Videomae: Masked Au-toencoders Are Data-efficient Learners for Self-supervised Video Pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"8","key":"ref25","first-page":"1","article-title":"Language Models are Unsupervised Multitask Learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref26","first-page":"473","article-title":"Tetris: Memory-efficient Serverless Inference through Tensor Sharing","volume-title":"Proc. of USENIX ATC","author":"Li"},{"key":"ref27","first-page":"1049","article-title":"MArk: Exploiting Cloud Services for Cost-Effective, SLO-Aware Machine Learning Inference Serving","volume-title":"Proc. of USENIX ATC","author":"Zhang"},{"key":"ref28","first-page":"521","article-title":"Orca: A Distributed Serving System for Transformer-Based Generative Models","volume-title":"Proc. of USENIX OSDI","author":"Yu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3464298.3493398"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575721"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E.2019.00-10"}],"event":{"name":"2024 IEEE\/ACM 32nd International Symposium on Quality of Service (IWQoS)","start":{"date-parts":[[2024,6,19]]},"location":"Guangzhou, China","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\/10682915.pdf?arnumber=10682915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T04:40:41Z","timestamp":1727412041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10682915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,19]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iwqos61813.2024.10682915","relation":{},"subject":[],"published":{"date-parts":[[2024,6,19]]}}}