{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:07:45Z","timestamp":1782968865695,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Alibaba Group","award":["Alibaba Innovative Research (AIR) Program"],"award-info":[{"award-number":["Alibaba Innovative Research (AIR) Program"]}]},{"name":"Hong Kong RGC","award":["HKU 17207621, 17204423 and C7004-22G (CRF)"],"award-info":[{"award-number":["HKU 17207621, 17204423 and C7004-22G (CRF)"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,20]]},"DOI":"10.1145\/3698038.3698548","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:32:43Z","timestamp":1731565963000},"page":"443-459","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["FaPES: Enabling Efficient Elastic Scaling for Serverless Machine Learning Platforms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8260-2181","authenticated-orcid":false,"given":"Xiaoyang","family":"Zhao","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0272-3718","authenticated-orcid":false,"given":"Siran","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1098-0403","authenticated-orcid":false,"given":"Jiamang","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6193-6126","authenticated-orcid":false,"given":"Lansong","family":"Diao","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2028-0780","authenticated-orcid":false,"given":"Lin","family":"Qu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3144-4398","authenticated-orcid":false,"given":"Chuan","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2024. Apache Openwhisk. https:\/\/github.com\/apache\/openwhisk."},{"key":"e_1_3_2_1_2_1","unstructured":"2024. AWS Lambda. https:\/\/aws.amazon.com\/cn\/pm\/lambda\/."},{"key":"e_1_3_2_1_3_1","unstructured":"2024. AWS-Placement Group. https:\/\/docs.aws.amazon.com\/AWSEC2\/latest\/UserGuide\/placement-groups.html."},{"key":"e_1_3_2_1_4_1","unstructured":"2024. Google Cloud Function. https:\/\/cloud.google.com\/functions."},{"key":"e_1_3_2_1_5_1","unstructured":"2024. google cluster data. https:\/\/github.com\/google\/cluster-data."},{"key":"e_1_3_2_1_6_1","unstructured":"2024. metrics-server. https:\/\/github.com\/kubernetes-sigs\/metrics-server."},{"key":"e_1_3_2_1_7_1","unstructured":"2024. Microsoft Azure. https:\/\/azure.microsoft.com\/en-us."},{"key":"e_1_3_2_1_8_1","unstructured":"2024. prometheus. https:\/\/github.com\/prometheus\/prometheus."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Fu Yao","year":"2024","unstructured":"Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian Brabete, Dmitrii Ustiugov, Yuvraj Patel, and Luo Mai. 2024. {ServerlessLLM}: {Low-Latency} Serverless Inference for Large Language Models. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 135--153."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575721"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605638"},{"key":"e_1_3_2_1_14_1","volume-title":"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). 721--739."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613175"},{"key":"e_1_3_2_1_16_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, et al. 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). 745--760."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6168-2"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587445"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607054"},{"key":"e_1_3_2_1_20_1","volume-title":"Jiagu: Optimizing Serverless Computing Resource Utilization with Harmonized Efficiency and Practicability. arXiv preprint arXiv:2403.00433","author":"Liu Qingyuan","year":"2024","unstructured":"Qingyuan Liu, Yanning Yang, Dong Du, Yubin Xia, Ping Zhang, Jia Feng, James Larus, and Haibo Chen. 2024. Jiagu: Optimizing Serverless Computing Resource Utilization with Harmonized Efficiency and Practicability. arXiv preprint arXiv:2403.00433 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"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--304."},{"key":"e_1_3_2_1_22_1","volume-title":"An empirical model of large-batch training. arXiv preprint arXiv:1812.06162","author":"McCandlish Sam","year":"2018","unstructured":"Sam McCandlish, Jared Kaplan, Dario Amodei, and OpenAI Dota Team. 2018. An empirical model of large-batch training. arXiv preprint arXiv:1812.06162 (2018)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488793"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMSNETS.2019.8711058"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"e_1_3_2_1_27_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_28_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2023.104764"},{"key":"e_1_3_2_1_30_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_31_1","first-page":"172","article-title":"Blink: Fast and generic collectives for distributed ml","volume":"2","author":"Wang Guanhua","year":"2020","unstructured":"Guanhua Wang, Shivaram Venkataraman, Amar Phanishayee, Nikhil Devanur, Jorgen Thelin, and Ion Stoica. 2020. Blink: Fast and generic collectives for distributed ml. Proceedings of Machine Learning and Systems 2 (2020), 172--186.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-023-2894-6"},{"key":"e_1_3_2_1_33_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, et al. 2018. Gandiva: Introspective cluster scheduling for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 595--610."},{"key":"e_1_3_2_1_34_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Xiao Wencong","year":"2020","unstructured":"Wencong Xiao, Shiru Ren, Yong Li, Yang Zhang, Pengyang Hou, Zhi Li, Yihui Feng, Wei Lin, and Yangqing Jia. 2020. {AntMan}: Dynamic scaling on {GPU} clusters for deep learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 533--548."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSOS52086.2021.00023"},{"key":"e_1_3_2_1_36_1","volume-title":"One-flow: Redesign the distributed deep learning framework from scratch. arXiv preprint arXiv:2110.15032","author":"Yuan Jinhui","year":"2021","unstructured":"Jinhui Yuan, Xinqi Li, Cheng Cheng, Juncheng Liu, Ran Guo, Shenghang Cai, Chi Yao, Fei Yang, Xiaodong Yi, Chuan Wu, et al. 2021. One-flow: Redesign the distributed deep learning framework from scratch. arXiv preprint arXiv:2110.15032 (2021)."},{"key":"e_1_3_2_1_37_1","volume-title":"Towards Fast Setup and High Throughput of GPU Serverless Computing. arXiv preprint arXiv:2404.14691","author":"Zhao Han","year":"2024","unstructured":"Han Zhao, Weihao Cui, Quan Chen, Shulai Zhang, Zijun Li, Jingwen Leng, Chao Li, Deze Zeng, and Minyi Guo. 2024. Towards Fast Setup and High Throughput of GPU Serverless Computing. arXiv preprint arXiv:2404.14691 (2024)."},{"key":"e_1_3_2_1_38_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Zheng Pengfei","year":"2023","unstructured":"Pengfei Zheng, Rui Pan, Tarannum Khan, Shivaram Venkataraman, and Aditya Akella. 2023. Shockwave: Fair and efficient cluster scheduling for dynamic adaptation in machine learning. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 703--723."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3143153"}],"event":{"name":"SoCC '24: ACM Symposium on Cloud Computing","location":"Redmond WA USA","acronym":"SoCC '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698548","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698038.3698548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:02:57Z","timestamp":1755889377000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698548"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":39,"alternative-id":["10.1145\/3698038.3698548","10.1145\/3698038"],"URL":"https:\/\/doi.org\/10.1145\/3698038.3698548","relation":{},"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"2024-11-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}