{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T19:10:08Z","timestamp":1755976208140,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T00:00:00Z","timestamp":1702252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2020R1A2C1102544,NRF-2022R1A5A7000765"],"award-info":[{"award-number":["NRF-2020R1A2C1102544,NRF-2022R1A5A7000765"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute for Information and Communications Technology Planning and Evaluation (IITP)","award":["RS-2022-00144309"],"award-info":[{"award-number":["RS-2022-00144309"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,11]]},"DOI":"10.1145\/3631295.3631400","type":"proceedings-article","created":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T12:05:18Z","timestamp":1700827518000},"page":"42-47","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["When Serverless Computing Meets Different Degrees of Customization for DNN Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9392-7808","authenticated-orcid":false,"given":"Moohyun","family":"Song","sequence":"first","affiliation":[{"name":"Computer Science. Kookmin Univ., Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3521-8021","authenticated-orcid":false,"given":"Yoonseo","family":"Hur","sequence":"additional","affiliation":[{"name":"Computer Science. Kookmin Univ., Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0312-4386","authenticated-orcid":false,"given":"Kyungyong","family":"Lee","sequence":"additional","affiliation":[{"name":"Computer Science. Kookmin Univ., Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. TensorFlow: a system for large-scale machine learning. In 12th USENIX symposium on operating systems design and implementation (OSDI 16). 265--283."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3429880.3430096"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3199197"},{"key":"e_1_3_2_1_4_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL 2019."},{"key":"e_1_3_2_1_5_1","volume-title":"Serverless Computing: One Step Forward, Two Steps Back. In 9th Biennial Conference on Innovative Data Systems Research, CIDR","author":"Hellerstein Joseph M.","year":"2019","unstructured":"Joseph M. Hellerstein, Jose M. Faleiro, Joseph Gonzalez, Johann Schleier-Smith, Vikram Sreekanti, Alexey Tumanov, and Chenggang Wu. 2019. Serverless Computing: One Step Forward, Two Steps Back. In 9th Biennial Conference on Innovative Data Systems Research, CIDR 2019, Asilomar, CA, USA, January 13-16, 2019, Online Proceedings. www.cidrdb.org. http:\/\/cidrdb.org\/cidr2019\/papers\/p119-hellerstein-cidr19.pdf"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Glenn Jocher Ayush Chaurasia Alex Stoken Jirka Borovec NanoCode012 Yonghye Kwon Kalen Michael TaoXie Jiacong Fang imyhxy Lorna Zeng Yifu Colin Wong Abhiram V Diego Montes Zhiqiang Wang Cristi Fati Jebastin Nadar Laughing UnglvKitDe Victor Sonck tkianai yxNONG Piotr Skalski Adam Hogan Dhruv Nair Max Strobel and Mrinal Jain. 2022. ultralytics\/yolov5: v7.0 - YOLOv5 SOTA Realtime Instance Segmentation. https:\/\/doi.org\/10.5281\/zenodo.7347926","DOI":"10.5281\/zenodo.7347926"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3128601"},{"key":"e_1_3_2_1_8_1","volume-title":"Joseph E. Gonzalez, Raluca Ada Popa, Ion Stoica, and David A. Patterson.","author":"Jonas Eric","year":"2019","unstructured":"Eric Jonas, Johann Schleier-Smith, Vikram Sreekanti, Chia-che Tsai, Anurag Khandelwal, Qifan Pu, Vaishaal Shankar, Joao Carreira, Karl Krauth, Neeraja Jayant Yadwadkar, Joseph E. Gonzalez, Raluca Ada Popa, Ion Stoica, and David A. Patterson. 2019. Cloud Programming Simplified: A Berkeley View on Serverless Computing. CoRR abs\/1902.03383 (2019). arXiv:1902.03383 http:\/\/arxiv.org\/abs\/1902.03383"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2019.00091"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3365439"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2021.3129000"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528535.3565241"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3406011"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2018.00088"},{"key":"e_1_3_2_1_16_1","volume-title":"Rethinking the Inception Architecture for Computer Vision. CoRR abs\/1512.00567","author":"Szegedy Christian","year":"2015","unstructured":"Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2015. Rethinking the Inception Architecture for Computer Vision. CoRR abs\/1512.00567 (2015). arXiv:1512.00567 http:\/\/arxiv.org\/abs\/1512.00567"},{"key":"e_1_3_2_1_17_1","volume-title":"Peeking Behind the Curtains of Serverless Platforms. In 2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Wang Liang","year":"2018","unstructured":"Liang Wang, Mengyuan Li, Yinqian Zhang, Thomas Ristenpart, and Michael Swift. 2018. Peeking Behind the Curtains of Serverless Platforms. In 2018 USENIX Annual Technical Conference (USENIX ATC 18). USENIX Association, Boston, MA, 133--146. https:\/\/www.usenix.org\/conference\/atc18\/presentation\/wang-liang"},{"key":"e_1_3_2_1_18_1","volume-title":"Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He.","author":"Aminabadi Reza Yazdani","year":"2022","unstructured":"Reza Yazdani Aminabadi, Samyam Rajbhandari, Minjia Zhang, Ammar Ahmad Awan, Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He. 2022. DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale. Technical Report MSR-TR-2022-21. Microsoft. https:\/\/www.microsoft.com\/en-us\/research\/publication\/deepspeed-inference-enabling-efficient-inference-of-transformer-models-at-unprecedented-scale\/"}],"event":{"name":"Middleware '23: 24th International Middleware Conference","sponsor":["ACM Association for Computing Machinery","IFIP International Federation for Information Processing"],"location":"Bologna Italy","acronym":"Middleware '23"},"container-title":["Proceedings of the 9th International Workshop on Serverless Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631295.3631400","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3631295.3631400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:40:40Z","timestamp":1755974440000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631295.3631400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,11]]},"references-count":18,"alternative-id":["10.1145\/3631295.3631400","10.1145\/3631295"],"URL":"https:\/\/doi.org\/10.1145\/3631295.3631400","relation":{},"subject":[],"published":{"date-parts":[[2023,12,11]]},"assertion":[{"value":"2023-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}