{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:21:34Z","timestamp":1757618494636,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819687275"},{"type":"electronic","value":"9789819687282"}],"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\/978-981-96-8728-2_35","type":"book-chapter","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T10:30:43Z","timestamp":1750588243000},"page":"431-443","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["vGPU Performance Testing Framework for\u00a0Large Model Inference"],"prefix":"10.1007","author":[{"given":"Hu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youli","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjun","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huifeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,21]]},"reference":[{"issue":"2","key":"35_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605943","volume":"56","author":"B Min","year":"2023","unstructured":"Min, B., Ross, H., et al.: Recent advances in natural language processing via large pre-trained language models: a survey. ACM Comput. Surv. 56(2), 1\u201340 (2023)","journal-title":"ACM Comput. Surv."},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Liu, J., Chen, W., Cheng, Y., et al.: Violin: a large-scale dataset for video-and-language inference, IEEE\/CVF CVPR 2020: 10900-10910","DOI":"10.1109\/CVPR42600.2020.01091"},{"key":"35_CR3","unstructured":"Zhou, Z., Ning, X., Hong, K., et al.: A survey on efficient inference for large language models. arXiv preprint arXiv:2404.14294, 2024"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Patel, A., Tian, S., Doerfert, J., et al.: A virtual GPU as developer-friendly OpenMP offload target, 50th ICPP Workshop, pp. 1\u20137 (2021)","DOI":"10.1145\/3458744.3473356"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Qiu, M., Gao, H.: Communication-efficient stochastic gradient descent ascent with momentum algorithms. IJCAI 4602\u20134610 (2023)","DOI":"10.24963\/ijcai.2023\/512"},{"key":"35_CR6","unstructured":"Ling, C., Jiang, J., et al.: Deep Graph Representation Learning and Optimization for Influence Maximization, ICML 2023"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Pan, B., et al.: Visual attention prompted prediction and learning. IJCAI 5517\u20135525 (2024)","DOI":"10.24963\/ijcai.2024\/610"},{"issue":"1","key":"35_CR8","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/924652","volume":"2014","author":"H Lu","year":"2014","unstructured":"Lu, H., Wang, X., et al.: The effects of using chaotic map on improving the performance of multiobjective evolutionary algorithms. Math. Probl. Eng. 2014(1), 924652 (2014)","journal-title":"Math. Probl. Eng."},{"issue":"1","key":"35_CR9","first-page":"43","volume":"4","author":"M Qiu","year":"2006","unstructured":"Qiu, M., Zhang, K., Huang, M.: Usability in mobile interface browsing. Web Intell. Agent Syst. 4(1), 43\u201359 (2006)","journal-title":"Web Intell. Agent Syst."},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Zhou, D., et al.: Self-consistent Deep Geometric Learning for Heterogeneous Multi-source Spatial Point Data Prediction, ACM KDD 2024, pp. 4001\u20144011","DOI":"10.1145\/3637528.3671737"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Zhao, X., Yao, J., Gao, P., et al.: Efficient sharing and fine-grained scheduling of virtualized GPU resources. In: IEEE 38th ICDCS, pp. 742\u2013752, 2018","DOI":"10.1109\/ICDCS.2018.00077"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Li, M., Wang, H., Dai, H., et al.: A survey of multi-dimensional indexes: past and future trends. IEEE TKDE (2024)","DOI":"10.1109\/TKDE.2024.3364183"},{"issue":"3","key":"35_CR13","first-page":"37","volume":"2","author":"X Wu","year":"2024","unstructured":"Wu, X., Wu, Y., Li, X., et al.: Application of adaptive machine learning systems in heterogeneous data environments. Glob. Acad. Front. 2(3), 37\u201350 (2024)","journal-title":"Glob. Acad. Front."},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Kwon, W., Li, Z., et al.: Efficient memory management for large language model serving with pagedattention. In: Proceedings of the 29th Symposium on Operating Systems Principles, pp. 611\u2013626, 2023","DOI":"10.1145\/3600006.3613165"},{"key":"35_CR15","unstructured":"Cui, Y., Cao, K., et al.: Client scheduling and resource management for efficient training in heterogeneous IoT-edge federated learning. IEEE TCAD, 2021"},{"issue":"3","key":"35_CR16","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1109\/MWC.2019.1800407","volume":"26","author":"K Gai","year":"2019","unstructured":"Gai, K., Xu, K., et al.: Fusion of cognitive wireless networks and edge computing. IEEE Wirel. Comm. 26(3), 69\u201375 (2019)","journal-title":"IEEE Wirel. Comm."},{"key":"35_CR17","unstructured":"Sheng, Y., Zheng, L., Yuan, B., et al.: Flexgen: high-throughput generative inference of large language models with a single GPU. IEEE ICML. PMLR, pp. 31094\u201331116, 2023"},{"key":"35_CR18","unstructured":"Choi, S., Lee, S., et al.: Serving heterogeneous machine learning models on Multi-GPU servers with Spatio-Temporal sharing. In: USENIX Annual Technical Conference, pp. 199\u2013216 (2022)"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Weaver, A., Kavi, K., Milojicic, D., et al.: Granularity-and interference-aware GPU sharing with MPS. In: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1630\u20131637. IEEE, 2024","DOI":"10.1109\/SCW63240.2024.00203"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Gu, J., Zhu, Y., et al.: FaST-GShare: enabling efficient spatio-temporal GPU sharing in serverless computing for deep learning inference. In: 52nd IEEE ICPP, pp. 635\u2013644 (2023)","DOI":"10.1145\/3605573.3605638"},{"issue":"3","key":"35_CR21","first-page":"812","volume":"34","author":"F Xu","year":"2022","unstructured":"Xu, F., Xu, J., Chen, J., et al.: Igniter: interference-aware GPU resource provisioning for predictable DNN inference in the cloud. IEEE TPDS 34(3), 812\u2013827 (2022)","journal-title":"IEEE TPDS"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Abdelkhalik, H., Arafa, Y., Santhi, N., et al.: Demystifying the nvidia ampere architecture through microbenchmarking and instruction-level analysis. In: IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20138 (2022)","DOI":"10.1109\/HPEC55821.2022.9926299"},{"key":"35_CR23","unstructured":"Choi, S., Lee, S., Kim, Y., et al.: Serving heterogeneous machine learning models on Multi-GPU servers with Spatio-Temporal sharing. In: USENIX Annual Technical Conference, pp. 199\u2013216 (2022)"}],"container-title":["Lecture Notes in Computer Science","Wireless Artificial Intelligent Computing Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8728-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T22:04:57Z","timestamp":1757196297000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8728-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819687275","9789819687282"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8728-2_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"21 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WASA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Wireless Artificial Intelligent Computing Systems and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wasa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/wasa-conference.org\/WASA2025\/index.html#","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}