{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T02:10:53Z","timestamp":1768011053965,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767453","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:13:44Z","timestamp":1762532024000},"page":"886-896","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Scaling LLM Training Using RDMA over Converged Ethernet"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1469-0358","authenticated-orcid":false,"given":"Alex","family":"Batlle Casellas","sequence":"first","affiliation":[{"name":"Qualcomm Europe, Inc., Barcelona, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7168-9050","authenticated-orcid":false,"given":"Adri\u00e1n","family":"P\u00e9rez Di\u00e9guez","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies, Inc., San Diego, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2473-3590","authenticated-orcid":false,"given":"Aleix","family":"Torres-Camps","sequence":"additional","affiliation":[{"name":"Qualcomm Europe, Inc., Barcelona, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9409-5674","authenticated-orcid":false,"given":"Harris","family":"Teague","sequence":"additional","affiliation":[{"name":"Qualcomm Technologies, Inc., San Diego, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9907-3548","authenticated-orcid":false,"given":"Arnau","family":"Padres Masdemont","sequence":"additional","affiliation":[{"name":"Qualcomm Europe, Inc., Barcelona, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4450-609X","authenticated-orcid":false,"given":"Jordi","family":"Ros-Giralt","sequence":"additional","affiliation":[{"name":"Qualcomm Europe, Inc., Barcelona, Spain"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Mohammad Al-Fares Alexander Loukissas and Amin Vahdat. 2008. A scalable commodity data center network architecture. ACM SIGCOMM computer communication review 38 4 (2008) 63\u201374.","DOI":"10.1145\/1402946.1402967"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Greg Buzzard David Jacobson Milon Mackey Scott Marovich and John Wilkes. 1996. An implementation of the Hamlyn sender-managed interface architecture. ACM SIGOPS Operating Systems Review 30 si (1996) 245\u2013259.","DOI":"10.1145\/248155.238784"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"e_1_3_3_2_6_2","unstructured":"Torsten Hoefler Duncan Roweth Keith Underwood Bob Alverson Mark Griswold Vahid Tabatabaee Mohan Kalkunte Surendra Anubolu Siyuan Shen Abdul Kabbani et\u00a0al. 2023. Datacenter ethernet and rdma: Issues at hyperscale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.03337 (2023)."},{"key":"e_1_3_3_2_7_2","unstructured":"Infiniband Trade Association. 2023. Infiniband Architecture Specification Volume 1 Release 1.7."},{"key":"e_1_3_3_2_8_2","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."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"W\u00a0Richard Stevens and Thomas Narten. 1990. UNIX network programming. ACM SIGCOMM Computer Communication Review 20 2 (1990) 8\u20139.","DOI":"10.1145\/378570.378600"},{"key":"e_1_3_3_2_11_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Thorsten Von\u00a0Eicken Anindya Basu Vineet Buch and Werner Vogels. 1995. U-Net: A user-level network interface for parallel and distributed computing. ACM SIGOPS Operating Systems Review 29 5 (1995) 40\u201353.","DOI":"10.1145\/224057.224061"},{"key":"e_1_3_3_2_13_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang Guanhua","year":"2024","unstructured":"Guanhua Wang, Heyang Qin, Sam\u00a0Ade Jacobs, Xiaoxia Wu, Connor Holmes, Zhewei Yao, Samyam Rajbhandari, Olatunji Ruwase, Feng Yan, Lei Yang, et\u00a0al. 2024. ZeRO++: Extremely efficient collective communication for large model training. In The Twelfth International Conference on Learning Representations."}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:29:24Z","timestamp":1767986964000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767453"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":12,"alternative-id":["10.1145\/3731599.3767453","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767453","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}