{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T16:36:00Z","timestamp":1786725360798,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032352507","type":"print"},{"value":"9783032352514","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T00:00:00Z","timestamp":1786752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T00:00:00Z","timestamp":1786752000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-35251-4_18","type":"book-chapter","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T16:02:33Z","timestamp":1786723353000},"page":"255-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Moirai: Dependency-Impact-Based Communication Scheduling for\u00a0Multi-job Distributed Deep Learning Cluster"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2363-3490","authenticated-orcid":false,"given":"Jingbin","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9305-9439","authenticated-orcid":false,"given":"Ting","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7314-2307","authenticated-orcid":false,"given":"Jinglei","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5526-4984","authenticated-orcid":false,"given":"Qinghua","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3290-4767","authenticated-orcid":false,"given":"Hongtao","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,15]]},"reference":[{"key":"18_CR1","unstructured":"Bi, X., et al.: Deepseek LLM: scaling open-source language models with longtermism. arXiv preprint arXiv:2401.02954 (2024)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Cao, J., et al.: Crux: GPU-efficient communication scheduling for deep learning training. In: Proceedings of the ACM SIGCOMM 2024 Conference, pp. 1\u201315 (2024)","DOI":"10.1145\/3651890.3672239"},{"key":"18_CR3","unstructured":"Dai, D., et al.: Deepseekmoe: towards ultimate expert specialization in mixture-ofexperts language models. arXiv preprint arXiv:2401.06066 (2024)"},{"issue":"5","key":"18_CR4","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/MM.2021.3091475","volume":"41","author":"J Dong","year":"2021","unstructured":"Dong, J., et al.: ACCL: architecting highly scalable distributed training systems with highly efficient collective communication library. IEEE Micro 41(5), 85\u201392 (2021)","journal-title":"IEEE Micro"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Gao, W., et al.: Autosched: an adaptive self-configured framework for scheduling deep learning training workloads. In: Proceedings of the 38th ACM International Conference on Supercomputing, pp. 473\u2013484 (2024)","DOI":"10.1145\/3650200.3656598"},{"key":"18_CR6","unstructured":"Gu, J., et\u00a0al.: Tiresias: A $$\\{$$GPU$$\\}$$ cluster manager for distributed deep learning. In: 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19), pp. 485\u2013500 (2019)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Han, X., et\u00a0al.: VCLOS: network contention aware scheduling for distributed machine learning tasks in multi-tenant GPU clusters. Comput. Netw. 111285 (2025)","DOI":"10.1016\/j.comnet.2025.111285"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR9","unstructured":"Hu, Q., et al.: Characterization of large language model development in the datacenter. In: 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24), pp. 709\u2013729 (2024)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Jayaram Subramanya, S., et al.: Sia: Heterogeneity-aware, goodput-optimized mlcluster scheduling. In: Proceedings of the 29th Symposium on Operating Systems Principles, pp. 642\u2013657 (2023)","DOI":"10.1145\/3600006.3613175"},{"key":"18_CR11","unstructured":"Jeon, M., et al.: Analysis of Large-ScaleMulti-TenantGPU clusters for DNN training workloads. In: 2019 USENIX Annual Technical Conference (USENIX ATC 19), pp. 947\u2013960 (2019)"},{"key":"18_CR12","unstructured":"Liu, H.: NAP: A Network-Aware Priority Framework for Distributed Machine Learning Training. Master\u2019s thesis, New York University Tandon School of Engineering (2025)"},{"key":"18_CR13","unstructured":"Liu, Y., et al.: Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et al.: Efficient large-scale language model training on GPU clusters using Megatron-LM. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315 (2021)","DOI":"10.1145\/3458817.3476209"},{"key":"18_CR15","unstructured":"Naumov, M., et al.: Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 (2019)"},{"issue":"8","key":"18_CR16","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"18_CR17","unstructured":"Rajasekaran, S., Ghobadi, M., Akella, A.: $$\\{$$CASSINI$$\\}$$:$$\\{$$Network-Aware$$\\}$$ job scheduling in machine learning clusters. In: 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24), pp. 1403\u20131420 (2024)"},{"key":"18_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2024.101211","volume":"26","author":"T Tsokov","year":"2024","unstructured":"Tsokov, T., Kostadinov, H.: Dynamic network-aware container allocation in cloud\/fog computing with mobile nodes. Internet of Things 26, 101211 (2024)","journal-title":"Internet of Things"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: Spindle: Efficient distributed training of multi-task large models via wavefront scheduling. In: Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, pp. 1139\u20131155 (2025)","DOI":"10.1145\/3676641.3715992"},{"key":"18_CR20","unstructured":"Weng, Q., et\u00a0al.: $$\\{$$MLaaS$$\\}$$ in the wild: Workload analysis and scheduling in $$\\{$$Large-Scale$$\\}$$ heterogeneous $$\\{$$GPU$$\\}$$ clusters. In: 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22), pp. 945\u2013960 (2022)"},{"key":"18_CR21","unstructured":"Zagoruyko, S., et al.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2026: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-35251-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T16:02:38Z","timestamp":1786723358000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-35251-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,15]]},"ISBN":["9783032352507","9783032352514"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-35251-4_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,15]]},"assertion":[{"value":"15 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pisa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2026.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}