{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:41:08Z","timestamp":1786509668844,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3718958.3750467","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:54:11Z","timestamp":1756313651000},"page":"1232-1234","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Coflow Scheduling for LLM Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6503-5309","authenticated-orcid":false,"given":"Xinchen","family":"Wan","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8512-1922","authenticated-orcid":false,"given":"Xinyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0501-5968","authenticated-orcid":false,"given":"Kaiqiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8380-1879","authenticated-orcid":false,"given":"Xudong","family":"Liao","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-7622","authenticated-orcid":false,"given":"Yilun","family":"Jin","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2831-0012","authenticated-orcid":false,"given":"Yijun","family":"Sun","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8779-4768","authenticated-orcid":false,"given":"Zhenghang","family":"Ren","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3238-8500","authenticated-orcid":false,"given":"Han","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-6028","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"https:\/\/github.com\/flexflow\/FlexFlow","author":"Flexflow","year":"2024","unstructured":"Flexflow source code. https:\/\/github.com\/flexflow\/FlexFlow, 2024."},{"key":"e_1_3_2_1_2_1","volume-title":"https:\/\/github.com\/nets-cs-pub-ro\/NDP\/wiki\/NDP-Simulator","year":"2024","unstructured":"htsim packet-level simulator. https:\/\/github.com\/nets-cs-pub-ro\/NDP\/wiki\/NDP-Simulator, 2024."},{"key":"e_1_3_2_1_3_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems, 33:1877\u20131901","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877\u20131901, 2020."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"},{"key":"e_1_3_2_1_5_1","volume-title":"The llama 3 herd of models. arXiv preprint arXiv:2407.21783","author":"Dubey Abhimanyu","year":"2024","unstructured":"Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. The llama 3 herd of models. arXiv preprint arXiv:2407.21783, 2024."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_7_1","volume-title":"et al. Gpipe: Efficient training of giant neural networks using pipeline parallelism. Advances in neural information processing systems, 32","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V Le, Yonghui Wu, et al. Gpipe: Efficient training of giant neural networks using pipeline parallelism. Advances in neural information processing systems, 32, 2019."},{"key":"e_1_3_2_1_8_1","first-page":"479","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Jiang Yimin","year":"2020","unstructured":"Yimin Jiang, Yibo Zhu, Chang Lan, Bairen Yi, Yong Cui, and Chuanxiong Guo. A unified architecture for accelerating distributed {DNN} training in heterogeneous {GPU\/CPU} clusters. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pages 463\u2013479, 2020."},{"key":"e_1_3_2_1_9_1","first-page":"760","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, et al. {MegaScale}: Scaling large language model training to more than 10,000 {GPUs}. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24), pages 745\u2013760, 2024."},{"key":"e_1_3_2_1_10_1","first-page":"959","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Li Jiamin","year":"2023","unstructured":"Jiamin Li, Yimin Jiang, Yibo Zhu, Cong Wang, and Hong Xu. Accelerating distributed {MoE} training and inference with lina. In 2023 USENIX Annual Technical Conference (USENIX ATC 23), pages 945\u2013959, 2023."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604869"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_13_1","volume-title":"Gpt-4 technical report. ArXiv, abs\/2303.08774","author":"AI.","year":"2023","unstructured":"OpenAI. Gpt-4 technical report. ArXiv, abs\/2303.08774, 2023."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_2_1_16_1","first-page":"16","volume-title":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Rajbhandari Samyam","unstructured":"Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and Yuxiong He. Zero: Memory optimizations toward training trillion parameter models. In SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pages 1\u201316. IEEE, 2020."},{"key":"e_1_3_2_1_17_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. Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053, 2019."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589288"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411029.3411037"},{"key":"e_1_3_2_1_20_1","first-page":"1443","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Wang Hao","year":"2024","unstructured":"Hao Wang, Han Tian, Jingrong Chen, Xinchen Wan, Jiacheng Xia, Gaoxiong Zeng, Wei Bai, Junchen Jiang, Yong Wang, and Kai Chen. Towards {Domain-Specific} network transport for distributed {DNN} training. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24), pages 1421\u20131443, 2024."},{"key":"e_1_3_2_1_21_1","first-page":"767","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wang Weiyang","year":"2023","unstructured":"Weiyang Wang, Moein Khazraee, Zhizhen Zhong, Manya Ghobadi, Zhihao Jia, Dheevatsa Mudigere, Ying Zhang, and Anthony Kewitsch. {TopoOpt}: Co-optimizing network topology and parallelization strategy for distributed training jobs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 739\u2013767, 2023."},{"key":"e_1_3_2_1_22_1","volume-title":"Tacc: A full-stack cloud computing infrastructure for machine learning tasks. arXiv preprint arXiv:2110.01556","author":"Xu Kaiqiang","year":"2021","unstructured":"Kaiqiang Xu, Xinchen Wan, Hao Wang, Zhenghang Ren, Xudong Liao, Decang Sun, Chaoliang Zeng, and Kai Chen. Tacc: A full-stack cloud computing infrastructure for machine learning tasks. arXiv preprint arXiv:2110.01556, 2021."},{"key":"e_1_3_2_1_23_1","volume-title":"Qwen2 technical report. arXiv preprint arXiv:2407.10671","author":"Yang An","year":"2024","unstructured":"An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. Qwen2 technical report. arXiv preprint arXiv:2407.10671, 2024."},{"key":"e_1_3_2_1_24_1","first-page":"193","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. Poseidon: An efficient communication architecture for distributed deep learning on {GPU} clusters. In 2017 USENIX Annual Technical Conference (USENIX ATC 17), pages 181\u2013193, 2017."}],"event":{"name":"SIGCOMM '25: ACM SIGCOMM 2025 Conference","location":"S\u00e3o Francisco Convent Coimbra Portugal","acronym":"SIGCOMM '25","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2025 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718958.3750467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:54:53Z","timestamp":1756313693000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718958.3750467"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":24,"alternative-id":["10.1145\/3718958.3750467","10.1145\/3718958"],"URL":"https:\/\/doi.org\/10.1145\/3718958.3750467","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"2025-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}