{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:42:51Z","timestamp":1760056971003,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3748273.3749211","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T16:19:34Z","timestamp":1756829974000},"page":"98-104","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MLSynth: Towards Synthetic ML Traces"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2303-3979","authenticated-orcid":false,"given":"Adel","family":"Sefiane","sequence":"first","affiliation":[{"name":"Imperial College London, London, UK, NVIDIA, Roskilde, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5083-4052","authenticated-orcid":false,"given":"Alireza","family":"Farshin","sequence":"additional","affiliation":[{"name":"NVIDIA, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7034-5284","authenticated-orcid":false,"given":"Marios","family":"Kogias","sequence":"additional","affiliation":[{"name":"Imperial College London, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. Using Chakra execution traces for benchmarking and network performance optimization. https:\/\/engineering.fb.com\/2023\/09\/07\/networking-traffic\/chakra-execution-traces-benchmarking-network-performance-optimization\/"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3672198.3673794"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Aaron Grattafiori et al. 2024. The Llama 3 Herd of Models. https:\/\/doi.org\/10.48550\/arXiv.2407.21783 arXiv:2407.21783 [cs].","DOI":"10.48550\/arXiv.2407.21783"},{"key":"e_1_3_2_1_5_1","unstructured":"Fei Gui Kaihui Gao Li Chen Dan Li Vincent Liu Ran Zhang Hongbing Yang and Dian Xiong. 2025. Accelerating Design Space Exploration for {LLM} Training Systems with Multi-experiment Parallel Simulation. 473--488. https:\/\/www.usenix.org\/conference\/nsdi25\/presentation\/gui"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.00134"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","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:\/\/doi.org\/10.48550\/arXiv.2407.15266 arXiv:2407.15266 [cs].","DOI":"10.48550\/arXiv.2407.15266"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Chenning Li Anton A. Zabreyko Arash Nasr-Esfahany Kevin Zhao Prateesh Goyal Mohammad Alizadeh and Thomas Anderson. 2025. m4: A Learned Flow-level Network Simulator. https:\/\/doi.org\/10.48550\/arXiv.2503.01770 arXiv:2503.01770 [cs].","DOI":"10.48550\/arXiv.2503.01770"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Jinkun Lin Ziheng Jiang Zuquan Song Sida Zhao Menghan Yu Zhanghan Wang Chenyuan Wang Zuocheng Shi Xiang Shi Wei Jia Zherui Liu Shuguang Wang Haibin Lin Xin Liu Aurojit Panda and Jinyang Li. 2025. Understanding Stragglers in Large Model Training Using What-if Analysis. https:\/\/doi.org\/10.48550\/arXiv.2505.05713 arXiv:2505.05713 [cs].","DOI":"10.48550\/arXiv.2505.05713"},{"key":"e_1_3_2_1_10_1","unstructured":"Aixin Liu et al. 2025. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_1_11_1","unstructured":"Rixin Liu Menghao Zhang Zihan Niu Zili Meng and Xiaohe Hu. [n.d.]. Themis: Efficiently Mitigating Congestion-Induced Fairness Disparities in Long-Haul RDMA Networks. ([n.d.])."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.04473"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"OpenAI Josh Achiam et al. 2024. GPT-4 Technical Report. https:\/\/doi.org\/10.48550\/arXiv.2303.08774 arXiv:2303.08774 [cs].","DOI":"10.48550\/arXiv.2303.08774"},{"key":"e_1_3_2_1_14_1","unstructured":"Sudarsanan Rajasekaran Manya Ghobadi and Aditya Akella. 2024. {CASSINI}: {Network-Aware} Job Scheduling in Machine Learning Clusters. 1403--1420. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/rajasekaran"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696348.3696878"},{"key":"e_1_3_2_1_16_1","unstructured":"Noam Shazeer Azalia Mirhoseini Krzysztof Maziarz Andy Davis Quoc Le Geoffrey Hinton and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. arXiv:1701.06538 [cs.LG] https:\/\/arxiv.org\/abs\/1701.06538"},{"key":"e_1_3_2_1_17_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. https:\/\/doi.org\/10.48550\/arXiv.1909.08053 arXiv:1909.08053 [cs].","DOI":"10.48550\/arXiv.1909.08053"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.14516"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI63208.2024.00013"},{"key":"e_1_3_2_1_20_1","unstructured":"Xizheng Wang Qingxu Li Yichi Xu Gang Lu Dan Li Li Chen Heyang Zhou Linkang Zheng Sen Zhang Yikai Zhu Yang Liu Pengcheng Zhang Kun Qian Kunling He Jiaqi Gao Ennan Zhai Dennis Cai and Binzhang Fu. 2025. {SimAI}: Unifying Architecture Design and Performance Tuning for {Large-Scale} Large Language Model Training with Scalability and Precision. 541--558. https:\/\/www.usenix.org\/conference\/nsdi25\/presentation\/wang-xizheng-simai"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00035"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.12588"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787484"}],"event":{"name":"SIGCOMM '25: ACM SIGCOMM 2025 Conference","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"],"location":"Coimbra Portugal","acronym":"SIGCOMM '25"},"container-title":["Proceedings of the 2nd Workshop on Networks for AI Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748273.3749211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T14:10:44Z","timestamp":1760019044000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748273.3749211"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":23,"alternative-id":["10.1145\/3748273.3749211","10.1145\/3748273"],"URL":"https:\/\/doi.org\/10.1145\/3748273.3749211","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-09-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}