{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:27:59Z","timestamp":1786476479691,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Beijing NSF","award":["L2607022"],"award-info":[{"award-number":["L2607022"]}]},{"name":"the National Natural Science Foundation of China","award":["62472404"],"award-info":[{"award-number":["62472404"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3829136","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"1095-1108","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GeoOrchestra: Orchestrating Heterogeneous Geo-Distributed Training with Network-Aware Scheduling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9305-9439","authenticated-orcid":false,"given":"Ting","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5526-4984","authenticated-orcid":false,"given":"Qinghua","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"Purple Mountain Laboratories, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2098-1799","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Purple Mountain Laboratories, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8386-014X","authenticated-orcid":false,"given":"Yuan","family":"Sun","sequence":"additional","affiliation":[{"name":"Purple Mountain Laboratories, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2363-3490","authenticated-orcid":false,"given":"Jingbin","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7314-2307","authenticated-orcid":false,"given":"Jinglei","family":"Pei","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0069-5105","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Purple Mountain Laboratories, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5506-5958","authenticated-orcid":false,"given":"Heng","family":"Pan","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9959-1124","authenticated-orcid":false,"given":"Zhenyu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"},{"name":"Purple Mountain Laboratories, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2212-7955","authenticated-orcid":false,"given":"Yunjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Purple Mountain Laboratories, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519584"},{"key":"e_1_3_2_1_2_1","volume-title":"Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)."},{"key":"e_1_3_2_1_3_1","volume-title":"MAST: Global Scheduling of ML Training across Geo-Distributed Datacenters at Hyperscale.","author":"Choudhury Arnab","year":"2024","unstructured":"Arnab Choudhury, Abha Jain, Shenghao Lin, Delia David, Siavash Soleimanifard, Michael Chen, Abhishek Yadav, Ritesh Tijoriwala, Denis Samoylov, and Chunqiang Tang. 2024. MAST: Global Scheduling of ML Training across Geo-Distributed Datacenters at Hyperscale. (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3772356.3772387"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Haotian Dong Jingyan Jiang Rongwei Lu Jiajun Luo Jiajun Song Bowen Li Ying Shen and Zhi Wang. 2025. Beyond A Single AI Cluster: A Survey of Decentralized LLM Training. arXiv:2503.11023 [cs] 10.48550\/arXiv.2503.11023","DOI":"10.48550\/arXiv.2503.11023"},{"key":"e_1_3_2_1_6_1","volume-title":"Diloco: Distributed low-communication training of language models. arXiv preprint arXiv:2311.08105","author":"Douillard Arthur","year":"2023","unstructured":"Arthur Douillard, Qixuan Feng, Andrei A Rusu, Rachita Chhaparia, Yani Donchev, Adhiguna Kuncoro, Marc'Aurelio Ranzato, Arthur Szlam, and Jiajun Shen. 2023. Diloco: Distributed low-communication training of language models. arXiv preprint arXiv:2311.08105 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00043"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. PMLR, 1676\u20131684","author":"Gao Yuanxiang","year":"2018","unstructured":"Yuanxiang Gao, Li Chen, and Baochun Li. 2018. Spotlight: Optimizing device placement for training deep neural networks. In International Conference on Machine Learning. PMLR, 1676\u20131684."},{"key":"e_1_3_2_1_10_1","volume-title":"DISTMM: Accelerating Distributed Multimodal Model Training.","author":"Huang Jun","year":"2024","unstructured":"Jun Huang, Zhen Zhang, Shuai Zheng, Yida Wang, and Feng Qin. 2024. DISTMM: Accelerating Distributed Multimodal Model Training. (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Dehao Chen, Hyouk Joong Lee, Jiquan Ngiam, Quoc V Le, Yonghui Wu, and Zhifeng Chen.","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao Chen, Hyouk Joong Lee, Jiquan Ngiam, Quoc V Le, Yonghui Wu, and Zhifeng Chen. 2019. Gpipe: Efficient training of giant neural networks using pipeline parallelism. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_12_1","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume":"1","author":"Jia Zhihao","year":"2019","unstructured":"Zhihao Jia, Matei Zaharia, and Alex Aiken. 2019. Beyond data and model parallelism for deep neural networks. Proceedings of Machine Learning and Systems 1 (2019), 1\u201313.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Machine Learning. PMLR, 16639\u201316653","author":"Kim Taebum","year":"2023","unstructured":"Taebum Kim, Hyoungjoo Kim, Gyeong-In Yu, and Byung-Gon Chun. 2023. BPIPE: memory-balanced pipeline parallelism for training large language models. In International Conference on Machine Learning. PMLR, 16639\u201316653."},{"key":"e_1_3_2_1_14_1","volume-title":"Dynamic tensor rematerialization. arXiv preprint arXiv:2006.09616","author":"Kirisame Marisa","year":"2020","unstructured":"Marisa Kirisame, Steven Lyubomirsky, Altan Haan, Jennifer Brennan, Mike He, Jared Roesch, Tianqi Chen, and Zachary Tatlock. 2020. Dynamic tensor rematerialization. arXiv preprint arXiv:2006.09616 (2020)."},{"key":"e_1_3_2_1_15_1","first-page":"341","article-title":"Reducing activation recomputation in large transformer models","volume":"5","author":"Korthikanti Vijay Anand","year":"2023","unstructured":"Vijay Anand Korthikanti, Jared Casper, Sangkug Lym, Lawrence McAfee, Michael Andersch, Mohammad Shoeybi, and Bryan Catanzaro. 2023. Reducing activation recomputation in large transformer models. Proceedings of Machine Learning and Systems 5 (2023), 341\u2013353.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-DSS-SmartCity-DependSys60770.2023.00104"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3247883"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3406420"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.24859"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672228"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629554"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511981"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607073"},{"key":"e_1_3_2_1_24_1","volume-title":"Ravnest: Decentralized Asynchronous Training on Heterogeneous Devices. arXiv preprint arXiv:2401.01728","author":"Menon Anirudh Rajiv","year":"2024","unstructured":"Anirudh Rajiv Menon, Unnikrishnan Menon, and Kailash Ahirwar. 2024. Ravnest: Decentralized Asynchronous Training on Heterogeneous Devices. arXiv preprint arXiv:2401.01728 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3570690.3570697"},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Learning Representations.","author":"Mirhoseini Azalia","year":"2018","unstructured":"Azalia Mirhoseini, Anna Goldie, Hieu Pham, Benoit Steiner, Quoc V Le, and Jeff Dean. 2018. A hierarchical model for device placement. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR, 2430\u20132439","author":"Mirhoseini Azalia","year":"2017","unstructured":"Azalia Mirhoseini, Hieu Pham, Quoc V Le, Benoit Steiner, Rasmus Larsen, Yuefeng Zhou, Naveen Kumar, Mohammad Norouzi, Samy Bengio, and Jeff Dean. 2017. Device placement optimization with reinforcement learning. In International conference on machine learning. PMLR, 2430\u20132439."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.14458"},{"key":"e_1_3_2_1_30_1","volume-title":"Torrent: Re-Architecting End-to-End Transmission for Cross-Datacenter RDMA Networks. In 2025 IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 1\u20136.","author":"Pan Heng","year":"2025","unstructured":"Heng Pan, Yanjie Li, Zihan Wan, Jiao Zhang, and Tao Huang. 2025. Torrent: Re-Architecting End-to-End Transmission for Cross-Datacenter RDMA Networks. In 2025 IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 1\u20136."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621327"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707272"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Ryabinin Max","year":"2023","unstructured":"Max Ryabinin, Tim Dettmers, Michael Diskin, and Alexander Borzunov. 2023. SWARM parallelism: training large models can be surprisingly communication-efficient. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML'23). JMLR.org, Article 1223, 25 pages."},{"key":"e_1_3_2_1_36_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799 (2018)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737367"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650083"},{"key":"e_1_3_2_1_39_1","volume-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053 (2019)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731569.3764839"},{"key":"e_1_3_2_1_41_1","first-page":"24829","article-title":"Piper: Multidimensional planner for dnn parallelization","volume":"34","author":"Tarnawski Jakub M","year":"2021","unstructured":"Jakub M Tarnawski, Deepak Narayanan, and Amar Phanishayee. 2021. Piper: Multidimensional planner for dnn parallelization. Advances in Neural Information Processing Systems 34 (2021), 24829\u201324840.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","volume-title":"Metis: Fast Automatic Distributed Training on Heterogeneous GPUs.","author":"Um Taegeon","year":"2024","unstructured":"Taegeon Um, Byungsoo Oh, Minyoung Kang, Woo-Yeon Lee, Goeun Kim, Dongseob Kim, Youngtaek Kim, Mohd Muzzammil, and Myeongjae Jeon. 2024. Metis: Fast Automatic Distributed Training on Heterogeneous GPUs. (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TON.2025.3569630"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Yongji Wu Xueshen Liu Shuowei Jin Ceyu Xu Feng Qian Z. Morley Mao Matthew Lentz Danyang Zhuo and Ion Stoica. 2025. HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs. arXiv:2504.03871 [cs] 10.48550\/arXiv.2504.03871","DOI":"10.48550\/arXiv.2504.03871"},{"key":"e_1_3_2_1_45_1","volume-title":"Gspmd: general and scalable parallelization for ml computation graphs. arXiv preprint arXiv:2105.04663","author":"Xu Yuanzhong","year":"2021","unstructured":"Yuanzhong Xu, HyoukJoong Lee, Dehao Chen, Blake A. Hechtman, Yanping Huang, Rahul Joshi, Maxim Krikun, Dmitry Lepikhin, Andy Ly, Marcello Maggioni, Ruoming Pang, Noam Shazeer, Shibo Wang, Tao Wang, Yonghui Wu, and Zhifeng Chen. 2021. Gspmd: general and scalable parallelization for ml computation graphs. arXiv preprint arXiv:2105.04663 (2021)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","unstructured":"Ran Yan Youhe Jiang Xiaonan Nie Fangcheng Fu Bin Cui and Binhang Yuan. 2025. HexiScale: Accommodating Large Language Model Training over Heterogeneous Environment. arXiv:2409.01143 [cs] 10.48550\/arXiv.2409.01143","DOI":"10.48550\/arXiv.2409.01143"},{"key":"e_1_3_2_1_47_1","volume-title":"Tianyi Zhang, Tri Dao, Beidi Chen, Percy Liang, Christopher Re, and Ce Zhang.","author":"Yuan Binhang","year":"2022","unstructured":"Binhang Yuan, Yongjun He, Jared Quincy Davis, Tianyi Zhang, Tri Dao, Beidi Chen, Percy Liang, Christopher Re, and Ce Zhang. 2022. Decentralized Training of Foundation Models in Heterogeneous Environments. (2022)."},{"key":"e_1_3_2_1_48_1","volume-title":"2017 USENIX Annual Technical Conference (USENIX ATC 17)","author":"Zhang Hao","year":"2017","unstructured":"Hao Zhang, Zeyu Zheng, Shizhen Xu, Wei Dai, Qirong Ho, Xiaodan Liang, Zhiting Hu, Jinliang Wei, Pengtao Xie, and Eric P Xing. 2017. Poseidon: An efficient communication architecture for distributed deep learning on {GPU} clusters. In 2017 USENIX Annual Technical Conference (USENIX ATC 17). 181\u2013193."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3405671.3405810"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750472"},{"key":"e_1_3_2_1_51_1","first-page":"162","article-title":"Hetegen: Efficient heterogeneous parallel inference for large language models on resource-constrained devices","volume":"6","author":"Zhao Xuanlei","year":"2024","unstructured":"Xuanlei Zhao, Bin Jia, Haotian Zhou, Ziming Liu, Shenggan Cheng, and Yang You. 2024. Hetegen: Efficient heterogeneous parallel inference for large language models on resource-constrained devices. Proceedings of Machine Learning and Systems 6 (2024), 162\u2013172.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_52_1","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zheng Lianmin","year":"2022","unstructured":"Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric P. Xing, Joseph E. Gonzalez, and Ion Stoica. 2022. Alpa: Automating inter-and {Intra-Operator} parallelism for distributed deep learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 559\u2013578."},{"key":"e_1_3_2_1_53_1","volume-title":"Gdp: Generalized device placement for dataflow graphs. arXiv preprint arXiv:1910.01578","author":"Zhou Yanqi","year":"2019","unstructured":"Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi, Daniel Wong, Peter C. Ma, Qiumin Xu, Ming Zhong, Hanxiao Liu, Anna Goldie, Azalia Mirhoseini, and James Laudon. 2019. Gdp: Generalized device placement for dataflow graphs. arXiv preprint arXiv:1910.01578 (2019)."}],"event":{"name":"SIGCOMM '26: ACM SIGCOMM 2026 Conference","location":"Colorado Convention Center Denver CO USA","acronym":"SIGCOMM '26","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2026 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3789240.3829136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:41:23Z","timestamp":1786473683000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3829136"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":53,"alternative-id":["10.1145\/3789240.3829136","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3829136","relation":{},"subject":[],"published":{"date-parts":[[2026,8,11]]},"assertion":[{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}