{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:45:05Z","timestamp":1771026305182,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":10,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819615278","type":"print"},{"value":"9789819615285","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-1528-5_7","type":"book-chapter","created":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T17:23:16Z","timestamp":1739553796000},"page":"95-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Resource Management for\u00a0GPT-Based Model Deployed on\u00a0Clouds: Challenges, Solutions, and\u00a0Future Directions"],"prefix":"10.1007","author":[{"given":"Yongkang","family":"Dang","sequence":"first","affiliation":[]},{"given":"Yiyuan","family":"He","sequence":"additional","affiliation":[]},{"given":"Minxian","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Kejiang","family":"Ye","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,15]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","first-page":"1937","DOI":"10.1007\/s10462-020-09896-5","volume":"54","author":"C Bent\u00e9jac","year":"2021","unstructured":"Bent\u00e9jac, C., Cs\u00f6rg\u0151, A., Mart\u00ednez-Mu\u00f1oz, G.: A comparative analysis of gradient boosting algorithms. Artif. Intell. Rev. 54, 1937\u20131967 (2021)","journal-title":"Artif. Intell. Rev."},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Friedman, J.H.: Greedy function approximation: a gradient boosting machine. In: Annals of Statistics, pp. 1189\u20131232 (2001)","DOI":"10.1214\/aos\/1013203451"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Gunasekaran, J.R., Mishra, C.S., Thinakaran, P., Kandemir, M.T., Das, C.R.: Implications of public cloud resource heterogeneity for inference serving. In: Proceedings of the 2020 Sixth International Workshop on Serverless Computing, pp. 7\u201312 (2020)","DOI":"10.1145\/3429880.3430093"},{"key":"7_CR4","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.knosys.2012.01.006","volume":"30","author":"J Ji","year":"2012","unstructured":"Ji, J., Pang, W., Zhou, C., Han, X., Wang, Z.: A fuzzy k-prototype clustering algorithm for mixed numeric and categorical data. Knowl.-Based Syst. 30, 129\u2013135 (2012)","journal-title":"Knowl.-Based Syst."},{"key":"7_CR5","unstructured":"Li, Z., et al.: Alpaserve: statistical multiplexing with model parallelism for deep learning serving. arXiv preprint arXiv:2302.11665 (2023)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Tuli, S., et al.: Hunter: AI based holistic resource management for sustainable cloud computing. J. Syst. Softw. 184, 111124 (2022)","DOI":"10.1016\/j.jss.2021.111124"},{"key":"7_CR7","unstructured":"Xu, M., et al.: A survey of resource-efficient LLM and multimodal foundation models. arXiv preprint arXiv:2401.08092 (2024)"},{"issue":"3","key":"7_CR8","first-page":"1","volume":"22","author":"M Xu","year":"2022","unstructured":"Xu, M., Song, C., Wu, H., Gill, S.S., Ye, K., Xu, C.: ESDNN: deep neural network based multivariate workload prediction in cloud computing environments. ACM Trans. Internet Technol. 22(3), 1\u201324 (2022)","journal-title":"ACM Trans. Internet Technol."},{"key":"7_CR9","unstructured":"Yin, D., Liu, Y., Zhao, W.X., Wen, J.-R., Xu, J., Du, J.: A survey of resource-efficient LLM and multimodal foundation models. arXiv preprint arXiv:2310.13165 (2023)"},{"key":"7_CR10","unstructured":"Zhao, W.X., et al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1528-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T11:29:34Z","timestamp":1750937374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1528-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819615278","9789819615285"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1528-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"15 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macau","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ica3pp2024.scimeeting.cn\/en\/web\/index\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}