{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:44:56Z","timestamp":1785912296476,"version":"3.56.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSFC","award":["62372184,62572195"],"award-info":[{"award-number":["62372184,62572195"]}]},{"name":"Science and Technology Commission of Shanghai Municipality","award":["22DZ2229004"],"award-info":[{"award-number":["22DZ2229004"]}]},{"name":"NSF","award":["OIA-2327452"],"award-info":[{"award-number":["OIA-2327452"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/2575-8411.2026.00142","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:09:23Z","timestamp":1785870563000},"page":"1465-1475","source":"Crossref","is-referenced-by-count":0,"title":["Cappuccino: Cost-Efficient Heterogeneous Lora Fine-Tuning Via Replica-Level Orchestration"],"prefix":"10.1109","author":[{"given":"Lingxuan","family":"Weng","sequence":"first","affiliation":[{"name":"East China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Xu","sequence":"additional","affiliation":[{"name":"East China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Wu","sequence":"additional","affiliation":[{"name":"East China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"East China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Louisiana at Lafayette."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. of NeurIPS","author":"Brown","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2377"},{"key":"ref3","article-title":"LLaMA: Open and Efficient Foundation Language Models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Qwen Technical Report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1549"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02727"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386351"},{"key":"ref8","article-title":"Parameter-Efficient Fine-Tuning for Foundation Models","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"issue":"2","key":"ref9","first-page":"3","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"Proc. of ICLR","volume":"1","author":"Hu","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.14778\/3725688.3725718"},{"key":"ref14","article-title":"PLoRA: Efficient LoRA Hyperparameter Tuning for Large Models","author":"Yan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3767295.3769331"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref17","article-title":"Training Verifiers to Solve Math Word Problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00027"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","volume-title":"Combinatorial optimization: algorithms and complexity","author":"Papadimitriou","year":"1998"},{"key":"ref21","article-title":"Approximation Algorithms for the Incremental Knapsack Problem via Disjunctive Programming","author":"Bienstock","year":"2013","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"103","article-title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","volume-title":"Proc. of NeurIPS","volume":"32","author":"Huang","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800010110"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37456-2_14"},{"key":"ref25","article-title":"Efficient Sequence Packing without Cross-contamination: Accelerating Large Language Models without Impacting Performance","author":"Krell","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"SLoRA: Scalable Serving of Thousands of LoRA Adapters","volume-title":"Proc. of MLSys","author":"Sheng","year":"2024"},{"key":"ref27","article-title":"Punica: Multi-Tenant LoRA Serving","volume-title":"Proc. of MLSys","author":"Chen","year":"2024"},{"key":"ref28","first-page":"911","article-title":"dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving","volume-title":"Proc. of USENIX OSDI","author":"Wu","year":"2024"},{"key":"ref29","first-page":"1533","article-title":"MuxTune: Efficient Multi-Task LLM Fine-Tuning in Multi-Tenant Datacenters via Spatial-Temporal Backbone Multiplexing","volume-title":"Proc. of USENIX NSDI","author":"Xue","year":"2026"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.14778\/3742728.3742752"},{"key":"ref31","first-page":"1","article-title":"Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning","volume-title":"Proc. of USENIX OSDI","author":"Qiao","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044693"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3731569.3764839"},{"key":"ref35","first-page":"847","article-title":"Cuckoo: Deadline-Aware Job Packing on Heterogeneous GPUs for DL Model Training","volume-title":"Proc. of ACM SoCC","author":"Zhang","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717483"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651359"},{"key":"ref38","article-title":"Zero Bubble (Almost) Pipeline Parallelism","volume-title":"Proc. of ICLR","author":"Qi","year":"2024"},{"key":"ref39","first-page":"785","article-title":"WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training","volume-title":"Proc. of USENIX OSDI","author":"Wang","year":"2025"}],"event":{"name":"2026 IEEE 46th International Conference on Distributed Computing Systems (ICDCS)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2026,6,22]]},"end":{"date-parts":[[2026,6,25]]}},"container-title":["2026 IEEE 46th International Conference on Distributed Computing Systems (ICDCS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11618978\/11618981\/11619040.pdf?arnumber=11619040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:51:02Z","timestamp":1785909062000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11619040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/2575-8411.2026.00142","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}