{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:52Z","timestamp":1740169372681,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["232102240089","242102241064"],"award-info":[{"award-number":["232102240089","242102241064"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3483250","type":"journal-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:32:26Z","timestamp":1729272746000},"page":"160441-160449","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing LoRA Model Serving Capacity via Adaptive Operator Scheduling for Multi-Tenancy on GPU"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3525-5647","authenticated-orcid":false,"given":"Lingnan","family":"Xia","sequence":"first","affiliation":[{"name":"Henan High-Speed Railway Operation and Maintenance Engineering Research Center, Zhengzhou Railway Vocational and Technical College, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7746-4639","authenticated-orcid":false,"given":"Hua","family":"Ma","sequence":"additional","affiliation":[{"name":"Henan High-Speed Railway Operation and Maintenance Engineering Research Center, Zhengzhou Railway Vocational and Technical College, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Punica: Multi-tenant LoRA serving","volume-title":"Proc. Mach. Learn. Syst. Conf.","volume":"6","author":"Chen"},{"key":"ref2","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"ref4","article-title":"ProTuner: Tuning programs with Monte Carlo tree search","author":"Haj-Ali","year":"2020","journal-title":"arXiv:2005.13685"},{"key":"ref5","first-page":"521","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Yu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"ref7","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dao"},{"key":"ref8","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sheng"},{"key":"ref9","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Leviathan"},{"key":"ref10","article-title":"SpecInfer: Accelerating generative large language model serving with tree-based speculative inference and verification","author":"Miao","year":"2023","journal-title":"arXiv:2305.09781"},{"volume-title":"Medusa","year":"2023","author":"Cai","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925952"},{"issue":"4","key":"ref14","first-page":"1","article-title":"Differentiable programming for image processing and deep learning in halide","volume":"37","author":"Li","year":"2018","journal-title":"ACM Trans. Graph."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322967"},{"key":"ref16","first-page":"3389","article-title":"Learning to optimize tensor programs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref17","article-title":"Ansor: Generating high-performance tensor programs for deep learning","author":"Zheng","year":"2020","journal-title":"arXiv:2006.06762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2490301.2451150"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SC.1998.10004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.681704"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377928"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2019.00049"},{"key":"ref24","first-page":"70","article-title":"AutoPhase: Juggling HLS phase orderings in random forests with deep reinforcement learning","volume-title":"Proc. 3rd Conf. Mach. Learn. Syst. (ML-Sys)","author":"Haj-Ali"},{"key":"ref25","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref26","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process., Syst. Demonstrations","author":"Wolf"},{"volume-title":"PEFT: State-of-the-Art Parameter-Efficient Fine-Tuning Methods","year":"2022","author":"Mangrulkar","key":"ref27"},{"volume-title":"Fastertransformer","year":"2021","author":"Hsueh","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10721583.pdf?arnumber=10721583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T01:01:38Z","timestamp":1732669298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10721583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3483250","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}