{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T04:39:32Z","timestamp":1786509572496,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,4]]},"DOI":"10.1145\/3694715.3695960","type":"proceedings-article","created":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T19:28:18Z","timestamp":1731698898000},"page":"211-228","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3689-9591","authenticated-orcid":false,"given":"Swapnil","family":"Gandhi","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, CA, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0706-5208","authenticated-orcid":false,"given":"Mark","family":"Zhao","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2933-0380","authenticated-orcid":false,"given":"Athinagoras","family":"Skiadopoulos","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3154-7530","authenticated-orcid":false,"given":"Christos","family":"Kozyrakis","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, US"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,15]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2024. PyTorch. https:\/\/pytorch.org\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Meta AI. 2024. Meta Llama 3. https:\/\/ai.meta.com\/blog\/meta-llama-3\/."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519584"},{"key":"e_1_3_2_1_5_1","volume-title":"The 18th IEEE Workshop on Silicon Errors in Logic - System Effects.","author":"Bacon David F.","year":"2022","unstructured":"David F. Bacon. 2022. Detection and Prevention of Silent Data Corruption in an Exabyte-scale Database System. In The 18th IEEE Workshop on Silicon Errors in Logic - System Effects."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Yixin Bao Yanghua Peng Chuan Wu and Zongpeng Li. 2018. Online Job Scheduling in Distributed Machine Learning Clusters. arXiv:1801.00936 [cs.DC]","DOI":"10.1109\/INFOCOM.2018.8486422"},{"key":"e_1_3_2_1_7_1","unstructured":"Romain Beaumont. 2022. Large Scale OpenCLIP: L\/14 H\/14 AND G\/14 Trained on LAION-2B. https:\/\/laion.ai\/blog\/large-openclip\/."},{"key":"e_1_3_2_1_8_1","unstructured":"Stas Bekman. 2022. The Technology Behind BLOOM Training. https:\/\/huggingface.co\/blog\/bloom-megatron-deepspeed."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Rishi Bommasani et al. 2021. On the Opportunities and Risks of Foundation Models. arXiv e-prints Article arXiv:2108.07258 (Aug. 2021) arXiv:2108.07258 pages. arXiv:2108.07258 [cs.LG] 10.48550\/arXiv.2108.07258","DOI":"10.48550\/arXiv.2108.07258"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.14165"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2021.3132413"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1604.00981"},{"key":"e_1_3_2_1_13_1","volume-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Chilimbi Trishul","year":"2014","unstructured":"Trishul Chilimbi, Yutaka Suzue, Johnson Apacible, and Karthik Kalyanaraman. 2014. Project Adam: Building an Efficient and Scalable Deep Learning Training System. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14). USENIX Association, Broomfield, CO, 571--582. https:\/\/www.usenix.org\/conference\/osdi14\/technical-sessions\/presentation\/chilimbi"},{"key":"e_1_3_2_1_14_1","unstructured":"Databricks. 2024. Introducing DBRX: A New State-of-the-Art Open LLM. https:\/\/www.databricks.com\/blog\/introducing-dbrx-new-state-art-open-llm\/."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.08989"},{"key":"e_1_3_2_1_16_1","volume-title":"Weinberger (Eds.)","volume":"25","author":"Dean Jeffrey","year":"2012","unstructured":"Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Marc' aurelio Ranzato, Andrew Senior, Paul Tucker, Ke Yang, Quoc Le, and Andrew Ng. 2012. Large Scale Distributed Deep Networks. In Advances in Neural Information Processing Systems, F. Pereira, C.J. Burges, L. Bottou, and K.Q. Weinberger (Eds.), Vol. 25. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2012\/file\/6aca97005c68f1206823815f66102863-Paper.pdf"},{"key":"e_1_3_2_1_17_1","volume-title":"MapReduce: Simplified Data Processing on Large Clusters. In 6th Symposium on Operating Systems Design & Implementation (OSDI 04)","author":"Dean Jeffrey","year":"2004","unstructured":"Jeffrey Dean and Sanjay Ghemawat. 2004. MapReduce: Simplified Data Processing on Large Clusters. In 6th Symposium on Operating Systems Design & Implementation (OSDI 04). USENIX Association, San Francisco, CA. https:\/\/www.usenix.org\/conference\/osdi-04\/mapreduce-simplified-data-processing-large-clusters"},{"key":"e_1_3_2_1_18_1","unstructured":"DGX 2024. Nvidia DGX Systems. https:\/\/www.nvidia.com\/en-gb\/data-center\/dgx-systems\/."},{"key":"e_1_3_2_1_19_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Eisenman Assaf","year":"2022","unstructured":"Assaf Eisenman, Kiran Kumar Matam, Steven Ingram, Dheevatsa Mudigere, Raghuraman Krishnamoorthi, Krishnakumar Nair, Misha Smelyanskiy, and Murali Annavaram. 2022. Check-N-Run: a Checkpointing System for Training Deep Learning Recommendation Models. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, 929--943. https:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/eisenman"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2101.03961"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.02677"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126937"},{"key":"e_1_3_2_1_23_1","unstructured":"Gurobi. 2024. Gurobi. https:\/\/www.gurobi.com."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.00134"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de Las Casas Lisa Anne Hendricks Johannes Welbl Aidan Clark Tom Hennigan Eric Noland Katie Millican George van den Driessche Bogdan Damoc Aurelia Guy Simon Osindero Karen Simonyan Erich Elsen Jack W. Rae Oriol Vinyals and Laurent Sifre. 2022. Training Compute-Optimal Large Language Models. arXiv e-prints Article arXiv:2203.15556 (March 2022) arXiv:2203.15556 pages. arXiv:2203.15556 [cs.CL] 10.48550\/arXiv.2203.15556","DOI":"10.48550\/arXiv.2203.15556"},{"key":"e_1_3_2_1_27_1","volume-title":"Dehao Chen, HyoukJoong 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, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: efficient training of giant neural networks using pipeline parallelism. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_28_1","volume-title":"Elastic Resource Sharing for Distributed Deep Learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Hwang Changho","year":"2021","unstructured":"Changho Hwang, Taehyun Kim, Sunghyun Kim, Jinwoo Shin, and KyoungSoo Park. 2021. Elastic Resource Sharing for Distributed Deep Learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). USENIX Association, 721--739. https:\/\/www.usenix.org\/conference\/nsdi21\/presentation\/hwang"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613152"},{"key":"e_1_3_2_1_30_1","volume-title":"Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads. In 2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Jeon Myeongjae","year":"2019","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Wencong Xiao, and Fan Yang. 2019. Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). USENIX Association, Renton, WA, 947--960. https:\/\/www.usenix.org\/conference\/atc19\/presentation\/jeon"},{"key":"e_1_3_2_1_31_1","unstructured":"Zhihao Jia Matei Zaharia and Alex Aiken. 2018. Beyond Data and Model Parallelism for Deep Neural Networks. arXiv:1807.05358 [cs.DC]"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488792"},{"key":"e_1_3_2_1_33_1","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, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, and Xin Liu. 2024. MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 745--760. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/jiang-ziheng"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.01433"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2001.08361"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML 23)","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 Proceedings of the 40th International Conference on Machine Learning (ICML 23). JMLR.org, Article 682, 15 pages."},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of Machine Learning and Systems 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)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1404.5997"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.05100"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.16668"},{"key":"e_1_3_2_1_42_1","volume-title":"Scaling Distributed Machine Learning with the Parameter Server. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Li Mu","year":"2014","unstructured":"Mu Li, David G. Andersen, Jun Woo Park, Alexander J. Smola, Amr Ahmed, Vanja Josifovski, James Long, Eugene J. Shekita, and Bor-Yiing Su. 2014. Scaling Distributed Machine Learning with the Parameter Server. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14). USENIX Association, Broomfield, CO, 583--598. https:\/\/www.usenix.org\/conference\/osdi14\/technical-sessions\/presentation\/li_mu"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476145"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.12043"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607073"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.05101"},{"key":"e_1_3_2_1_48_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). USENIX Association, Santa Clara, CA, 289--304. https:\/\/www.usenix.org\/conference\/nsdi20\/presentation\/mahajan"},{"key":"e_1_3_2_1_49_1","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer Sentinel Mixture Models. arXiv:1609.07843 [cs.CL]"},{"key":"e_1_3_2_1_50_1","volume-title":"Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Mohan Jayashree","year":"2021","unstructured":"Jayashree Mohan, Amar Phanishayee, and Vijay Chidambaram. 2021. CheckFreq: Frequent, Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21). USENIX Association, 203--216. https:\/\/www.usenix.org\/conference\/fast21\/presentation\/mohan"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.09518"},{"key":"e_1_3_2_1_54_1","unstructured":"OpenAI. 2022. ChatGPT: Language models for task-oriented dialogue. https:\/\/openai.com\/blog\/chatgpt\/."},{"key":"e_1_3_2_1_55_1","volume-title":"Proceedings of Machine Learning and Systems, I. Dhillon, D. Papailiopoulos, and V. Sze (Eds.)","volume":"2","author":"Or Andrew","year":"2020","unstructured":"Andrew Or, Haoyu Zhang, and Michael Freedman. 2020. Resource Elasticity in Distributed Deep Learning. In Proceedings of Machine Learning and Systems, I. Dhillon, D. Papailiopoulos, and V. Sze (Eds.), Vol. 2. 400--411. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2020\/file\/c443e9d9fc984cda1c5cc447fe2c724d-Paper.pdf"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/971701.50214"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_61_1","volume-title":"ZeRO-Offload: Democratizing Billion-Scale Model Training. In 2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. ZeRO-Offload: Democratizing Billion-Scale Model Training. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). USENIX Association, 551--564. https:\/\/www.usenix.org\/conference\/atc21\/presentation\/ren-jie"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.05799"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1811.02084"},{"key":"e_1_3_2_1_64_1","volume-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. CoRR abs\/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. CoRR abs\/1909.08053 (2019). arXiv:1909.08053 http:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.11990"},{"key":"e_1_3_2_1_66_1","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Tarnawski Jakub M","year":"2021","unstructured":"Jakub M Tarnawski, Deepak Narayanan, and Amar Phanishayee. 2021. Piper: Multidimensional Planner for DNN Parallelization. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 24829--24840. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/d01eeca8b24321cd2fe89dd85b9beb51-Paper.pdf"},{"key":"e_1_3_2_1_67_1","volume-title":"Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Thorpe John","year":"2023","unstructured":"John Thorpe, Pengzhan Zhao, Jonathan Eyolfson, Yifan Qiao, Zhihao Jia, Minjia Zhang, Ravi Netravali, and Guoqing Harry Xu. 2023. Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, Boston, MA, 497--513. https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/thorpe"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","unstructured":"Hugo Touvron et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv e-prints Article arXiv:2307.09288 (July 2023) arXiv:2307.09288 pages. arXiv:2307.09288 [cs.CL] 10.48550\/arXiv.2307.09288","DOI":"10.48550\/arXiv.2307.09288"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.02852"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303953"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359653"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.00193"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_2_1_74_1","volume-title":"MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU Clusters. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Weng Qizhen","year":"2022","unstructured":"Qizhen Weng, Wencong Xiao, Yinghao Yu, Wei Wang, Cheng Wang, Jian He, Yong Li, Liping Zhang, Wei Lin, and Yu Ding. 2022. MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU Clusters. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, 945--960. https:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/weng"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1709.05011"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.01068"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.11277"},{"key":"e_1_3_2_1_78_1","volume-title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 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). USENIX Association, Carlsbad, CA, 559--578. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zheng-lianmin"},{"key":"e_1_3_2_1_79_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Zu Yazhou","year":"2024","unstructured":"Yazhou Zu, Alireza Ghaffarkhah, Hoang-Vu Dang, Brian Towles, Steven Hand, Safeen Huda, Adekunle Bello, Alexander Kolbasov, Arash Rezaei, Dayou Du, Steve Lacy, Hang Wang, Aaron Wisner, Chris Lewis, and Henri Bahini. 2024. Resiliency at Scale: Managing Google's TPUv4 Machine Learning Supercomputer. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). USENIX Association, Santa Clara, CA, 761--774. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/zu"}],"event":{"name":"SOSP '24: ACM SIGOPS 30th Symposium on Operating Systems Principles","location":"Austin TX USA","acronym":"SOSP '24","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","USENIX"]},"container-title":["Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3694715.3695960","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3694715.3695960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:48Z","timestamp":1750291548000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3694715.3695960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":78,"alternative-id":["10.1145\/3694715.3695960","10.1145\/3694715"],"URL":"https:\/\/doi.org\/10.1145\/3694715.3695960","relation":{},"subject":[],"published":{"date-parts":[[2024,11,4]]},"assertion":[{"value":"2024-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}