{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:44:02Z","timestamp":1757313842265,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":7,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Key R&D Program of China","award":["2022YFB3304100"],"award-info":[{"award-number":["2022YFB3304100"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1145\/3555041.3589720","type":"proceedings-article","created":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T16:25:14Z","timestamp":1685982314000},"page":"135-138","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SMILE: A Cost-Effective System for Serving Massive Pretrained Language Models in The Cloud"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6712-1929","authenticated-orcid":false,"given":"Jue","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3062-0900","authenticated-orcid":false,"given":"Ke","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8062-8356","authenticated-orcid":false,"given":"Lidan","family":"Shou","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2807-1068","authenticated-orcid":false,"given":"Dawei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7483-0045","authenticated-orcid":false,"given":"Gang","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2023,6,5]]},"reference":[{"key":"e_1_3_2_3_1_1","unstructured":"Rishi Bommasani Drew A Hudson Ehsan Adeli Russ Altman Simran Arora Sydney von Arx Michael S Bernstein Jeannette Bohg Antoine Bosselut Emma Brunskill et al. 2021. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)."},{"key":"e_1_3_2_3_2_1","volume-title":"Proc. of NAACL-HLT.","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 Proc. of NAACL-HLT."},{"key":"e_1_3_2_3_3_1","volume-title":"Proc. of ICML.","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In Proc. of ICML."},{"key":"e_1_3_2_3_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.152"},{"key":"e_1_3_2_3_5_1","volume-title":"NeurIPS","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_3_6_1","doi-asserted-by":"publisher","DOI":"10.2737\/FPL-GTR-290"},{"key":"e_1_3_2_3_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131365.3131372"}],"event":{"name":"SIGMOD\/PODS '23: International Conference on Management of Data","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"],"location":"Seattle WA USA","acronym":"SIGMOD\/PODS '23"},"container-title":["Companion of the 2023 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3555041.3589720","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3555041.3589720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:49Z","timestamp":1750178809000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3555041.3589720"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":7,"alternative-id":["10.1145\/3555041.3589720","10.1145\/3555041"],"URL":"https:\/\/doi.org\/10.1145\/3555041.3589720","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]},"assertion":[{"value":"2023-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}