首页|期刊导航|Big Data Mining and Analytics|Dynamic Batch Processing with FlexiDecode Scheduler for Efficient LLM Inference in IIoT

Dynamic Batch Processing with FlexiDecode Scheduler for Efficient LLM Inference in IIoT

Xiaocong Jia Bruce Gu Jinjun Chen Longxiang Gao Weiguang Pang Guangtong Lv Youyang Qu Lei Cui

Big Data Mining and Analytics2025，Vol.8Issue(6)：P.1307-1323,17.

Big Data Mining and Analytics2025，Vol.8Issue(6)：P.1307-1323,17.DOI:10.26599/BDMA.2025.9020025

Dynamic Batch Processing with FlexiDecode Scheduler for Efficient LLM Inference in IIoT

Xiaocong Jia ¹Bruce Gu ¹Jinjun Chen ²Longxiang Gao ¹Weiguang Pang ¹Guangtong Lv ¹Youyang Qu ¹Lei Cui¹

作者信息

1. Key Laboratory of Computing Power Network and Information Security of Ministry of Education,Shandong Computer Science Center(National Supercomputer Center in Jinan),Qilu University of Technology(Shandong Academy of Sciences),Jinan 250000,China Shandong Provincial Key Laboratory of Computer Power Internet and Service Computing,Shandong Fundamental Research Center for Computer Science,Jinan 250000,China
2. Department of Computing Technologies,Swinburne University of Technology,Melbourne 3000,Australia
折叠

摘要

关键词

virtual Large Language Model(vLLM)inference/batch scheduling/dynamic decoding batches/calculating utilization

分类

信息技术与安全科学

引用本文复制引用

Xiaocong Jia,Bruce Gu,Jinjun Chen,Longxiang Gao,Weiguang Pang,Guangtong Lv,Youyang Qu,Lei Cui..Dynamic Batch Processing with FlexiDecode Scheduler for Efficient LLM Inference in IIoT[J].Big Data Mining and Analytics,2025,8(6):P.1307-1323,17.

基金项目

supported by the National Science and Technology Major Project(No.2022ZD0116800) （No.2022ZD0116800）

the NSFC International Young Scientists Fund(No.62350410478) （No.62350410478）

the Taishan Scholars Program(Nos.TSQNZ20230621 and TSQN202211214) （Nos.TSQNZ20230621 and TSQN202211214）

the Shandong Excellent Young Scientists Fund(Overseas)(No.2023HWYQ-113) （Overseas）

the Shandong Provincial Natural Science Foundation(No.ZR20221150015). （No.ZR20221150015）

Big Data Mining and Analytics

OACSCD

ISSN：2096-0654

访问量0

下载量0

段落导航