{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:08:26Z","timestamp":1780704506821,"version":"3.54.1"},"reference-count":48,"publisher":"Tsinghua University Press","issue":"6","funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0116800"],"award-info":[{"award-number":["2022ZD0116800"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR20221150015"],"award-info":[{"award-number":["ZR20221150015"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Big Data Min. Anal."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.26599\/bdma.2025.9020025","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:39:39Z","timestamp":1757957979000},"page":"1307-1323","source":"Crossref","is-referenced-by-count":5,"title":["Dynamic Batch Processing with FlexiDecode Scheduler for Efficient LLM Inference in IIoT"],"prefix":"10.26599","volume":"8","author":[{"given":"Xiaocong","family":"Jia","sequence":"first","affiliation":[{"name":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security of Ministry of Education,Jinan,China,250000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruce","family":"Gu","sequence":"additional","affiliation":[{"name":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security of Ministry of Education,Jinan,China,250000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjun","family":"Chen","sequence":"additional","affiliation":[{"name":"Swinburne University of Technology,Department of Computing Technologies,Melbourne,Australia,3000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longxiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security of Ministry of Education,Jinan,China,250000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiguang","family":"Pang","sequence":"additional","affiliation":[{"name":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security of Ministry of Education,Jinan,China,250000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangtong","family":"Lv","sequence":"additional","affiliation":[{"name":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security of Ministry of Education,Jinan,China,250000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youyang","family":"Qu","sequence":"additional","affiliation":[{"name":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security of Ministry of Education,Jinan,China,250000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Cui","sequence":"additional","affiliation":[{"name":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security of Ministry of Education,Jinan,China,250000"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref2","first-page":"5547","article-title":"GLaM: Efficient scaling of language models with mixture-of-experts","volume-title":"Proc. 39th Int. Conf. Machine Learning","author":"Du"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29810"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/fi15060192"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/112405.112427"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3406095"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278729"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref10","first-page":"941","article-title":"The flan collection: Designing data and methods for effective instruction tuning","volume-title":"Proc. 40th Int. Conf. Machine Learning","author":"Longpre"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.seta.2021.101267"},{"key":"ref14","first-page":"1516","article-title":"Visual instruction tuning","volume-title":"Proc. 37th Int. Conf. Neural Information Processing Systems","author":"Liu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT61001.2024.10724909"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0279743"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CSR61664.2024.10679444"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650513"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CoST60524.2023.00066"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.12.003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/AITest62860.2024.00014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2022.9020046"},{"key":"ref26","first-page":"2338","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. 37th Int. Conf. Neural Information Processing Systems","author":"Rafailov"},{"key":"ref27","first-page":"521","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"Proc. 16th USENIX Symp. Operating Systems Design and Implementation","author":"Yu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref29","first-page":"117","article-title":"Taming throughput-latency tradeoff in LLM inference with sarathi-serve","volume-title":"Proc. 18th USENIX Symp. Operating Systems Design and Implementation","author":"Agrawal"},{"key":"ref30","volume-title":"NVIDIA Dynamo Platform","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-51399-2_3"},{"key":"ref32","first-page":"611","article-title":"Pretzel: Opening the black box of machine learning prediction serving systems","volume-title":"Proc. 13th USENIX Symp. Operating Systems Design and Implementation","author":"Lee"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359658"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2021.103066"},{"key":"ref36","article-title":"Inference without interference: Disaggregate LLM inference for mixed downstream workloads","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655823"},{"key":"ref39","first-page":"791","article-title":"S3: Increasing GPU utilization during generative inference for higher throughput","volume-title":"Proc. 37th Int. Conf. Neural Information Processing Systems","author":"Jin"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1186\/s42774-021-00077-8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00623-1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2612669.2612675"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.accinf.2024.100715"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682949"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref46","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-2097"},{"key":"ref48","article-title":"OpenChat: Advancing open-source language models with mixed-quality data","volume-title":"Proc. 12th Int. Conf. Learning Representations","author":"Wang","year":"2023"}],"container-title":["Big Data Mining and Analytics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8254253\/11164402\/11164457.pdf?arnumber=11164457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:36:15Z","timestamp":1758044175000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11164457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":48,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.26599\/bdma.2025.9020025","relation":{},"ISSN":["2096-0654","2097-406X"],"issn-type":[{"value":"2096-0654","type":"print"},{"value":"2097-406X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}