{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:27:58Z","timestamp":1786476478310,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":42,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3828736","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"1973-1980","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Ampel: Scheduling at the Network Cut in ML Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3864-9270","authenticated-orcid":false,"given":"Valerio","family":"Torsiello","sequence":"first","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9723-4513","authenticated-orcid":false,"given":"Ayush","family":"Mishra","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8842-7612","authenticated-orcid":false,"given":"Sushovan","family":"Das","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0720-5134","authenticated-orcid":false,"given":"Lukas","family":"R\u00f6llin","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2345-473X","authenticated-orcid":false,"given":"Tommaso","family":"Bonato","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1455-4381","authenticated-orcid":false,"given":"Laurent","family":"Vanbever","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. Alps | CSCS. https:\/\/www.cscs.ch\/computers\/alps."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_2_1_3_1","unstructured":"[n. d.]. Ultra Ethernet Consortium. https:\/\/ultraethernet.org\/."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230569"},{"key":"e_1_3_2_1_5_1","unstructured":"Joao Araujo Alex Chow Mark Handley Ryder Lewis Christoph Paasch Jitendra Padhye Michael Papamichael Greg Steinbrecher Amin Tootoonchian Lihua Yuan S Anantharamu Abhishek Dosi Mohit Garg Mahdieh Ghazi Torsten Hoefler Deepal Jayasinghe Jithin Jose Abdul Kabbani Guohan Lu Yang Wang K Doddapaneni Murali Garimella Vipin Jain Yanfang Le H Nagulapalli S Narayanan Rong Pan Rathina Sabesan Raghava Sivaramu Rip Sohan Eric Davis Dragos Dumitrescu Mohan Kalkunte Bhaswar Mitra Guglielmo Morandin Adrian Popa Costin Raiciu Eric Spada John Spillane Niranjan Vaidya Aviv Barnea Idan Burstein Elazar Cohen Yamin Friedman Noam Katz Masoud Moshref Yuval Shpigelman Shahaf Shuler Shy Shyman and Sayantan Sur. [n. d.]. Resilient AI Supercomputer Networking Using MRC and SRv6. ([n. d.])."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759884"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3767295.3769320"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning (ICML'25","volume":"6228","author":"Cai Weilin","year":"2025","unstructured":"Weilin Cai, Juyong Jiang, Le Qin, Junwei Cui, Sunghun Kim, and Jiayi Huang. 2025. Shortcut-Connected Expert Parallelism for Accelerating Mixture of Experts. In Proceedings of the 42nd International Conference on Machine Learning (ICML'25, Vol. 267). JMLR.org, Vancouver, Canada, 6211\u20136228."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750499"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2390231.2390237"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787480"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626315"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3730567.3764494"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"e_1_3_2_1_17_1","volume-title":"HeteCCL: Synthesizing Near-Optimal Collective Communication Schedules for Heterogeneous GPU Clusters. In 23rd USENIX Symposium on Networked Systems Design and Implementation (NSDI 26)","author":"Hei Chenyang","year":"2026","unstructured":"Chenyang Hei, Jiayi Li, Jiamin Cao, Chengxi Gao, Xiuzhu Sha, Tongrui Liu, Dengke Zhang, Ennan Zhai, and Xingwei Wang. 2026. HeteCCL: Synthesizing Near-Optimal Collective Communication Schedules for Heterogeneous GPU Clusters. In 23rd USENIX Symposium on Networked Systems Design and Implementation (NSDI 26). 2533\u20132551."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. Number 10","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. Number 10. Curran Associates Inc., Red Hook, NY, USA, 103\u2013112."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3767295.3769322"},{"key":"e_1_3_2_1_20_1","unstructured":"Yanfang Le Rong Pan Peter Newman Jeremias Blendin Abdul Kabbani Vipin Jain Raghava Sivaramu and Francis Matus. 2024. STrack: A Reliable Multipath Transport for AI\/ML Clusters. https:\/\/arxiv.org\/abs\/2407.15266v2."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3663408.3663409"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750465"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750514"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750539"},{"key":"e_1_3_2_1_26_1","volume-title":"Themis: Fair and Efficient GPU Cluster Scheduling. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Mahajan Kshiteej","year":"2020","unstructured":"Kshiteej Mahajan, Arjun Balasubramanian, Arjun Singhvi, Shivaram Venkataraman, Aditya Akella, Amar Phanishayee, and Shuchi Chawla. 2020. Themis: Fair and Efficient GPU Cluster Scheduling. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 289\u2013304."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750521"},{"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":"10.1145\/3651890.3672265"},{"key":"e_1_3_2_1_30_1","volume-title":"Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R. Ganger, and Eric P. Xing.","author":"Qiao Aurick","year":"2021","unstructured":"Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R. Ganger, and Eric P. Xing. 2021. Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning. In 15th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 21)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868457"},{"key":"e_1_3_2_1_32_1","volume-title":"CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Rajasekaran Sudarsanan","year":"2024","unstructured":"Sudarsanan Rajasekaran, Manya Ghobadi, and Aditya Akella. 2024. CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 1403\u20131420."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696348.3696878"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_35_1","volume-title":"TACCL: Guiding Collective Algorithm Synthesis Using Communication Sketches. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Shah Aashaka","year":"2023","unstructured":"Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, Olli Saarikivi, and Rachee Singh. 2023. TACCL: Guiding Collective Algorithm Synthesis Using Communication Sketches. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 593\u2013612."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759838"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv:1909.08053 [cs] 10.48550\/arXiv.1909.08053","DOI":"10.48550\/arXiv.1909.08053"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377454"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750467"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI63208.2024.00013"},{"key":"e_1_3_2_1_41_1","volume-title":"TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed Training Jobs. In 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. 2023. TopoOpt: Co-optimizing Network Topology and Parallelization Strategy for Distributed Training Jobs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 739\u2013767."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"}],"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\/3789240.3828736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:40:46Z","timestamp":1786473646000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3828736"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":42,"alternative-id":["10.1145\/3789240.3828736","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3828736","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"}}]}}