{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:03:26Z","timestamp":1763190206226,"version":"3.45.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032104656","type":"print"},{"value":"9783032104663","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-10466-3_25","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:00:03Z","timestamp":1763190003000},"page":"303-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Millisecond-Level Interference-Aware Scheduling for\u00a0Multi-Inference Co-Location on\u00a0Ascend NPUs"],"prefix":"10.1007","author":[{"given":"Wenhao","family":"Huang","sequence":"first","affiliation":[]},{"given":"Fupeng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Laiping","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yeju","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Keqiu","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"key":"25_CR1","unstructured":"Jeon, M., Venkataraman, S., Phanishayee, A., et al.: Analysis of large-scale multi-tenant GPU clusters for DNN training workloads. In: 2019 USENIX Annual Technical Conference (USENIX ATC 19), pp. 947\u2013960 (2019)"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhao, L., Li, Y., et al.: Infless: a native serverless system for low-latency, high-throughput inference. In: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 768\u2013781 (2022)","DOI":"10.1145\/3503222.3507709"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Pei, Q., Yuan, Y., Hu, H., et al.: Asyfunc: a high-performance and resource-efficient serverless inference system via asymmetric functions. In: Proceedings of the 2023 ACM Symposium on Cloud Computing. 324\u2013340 (2023)","DOI":"10.1145\/3620678.3624664"},{"key":"25_CR4","unstructured":"Wang, H.S., Zhu, X., Peh, L.S., et al.: Orion: a power-performance simulator for interconnection networks. In: 35th Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 294\u2013305 (2002)"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Ng, K.K.W., Demoulin, H.M., Liu, V.: Paella: low-latency model serving with software-defined GPU scheduling. In: Proceedings of the 29th Symposium on Operating Systems Principles, pp. 595\u2013610 (2023)","DOI":"10.1145\/3600006.3613163"},{"key":"25_CR6","unstructured":"Yu, M., Wang, A., Chen, D., et al.: Faaswap: SLO-Aware, GPU-Efficient Serverless Inference via Model Swapping. arXiv preprint arXiv:2306.03622 (2023)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Zhao, M., Jha, K., Hong, S.: GPU-enabled function-as-a-service for machine learning inference. In: 2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 918\u2013928 (2023)","DOI":"10.1109\/IPDPS54959.2023.00096"},{"key":"25_CR8","unstructured":"Gujarati, A., Karimi, R., Alzayat, S., Hao, W., Kaufmann, A., Vigfusson, Y., Mace, J.: Serving DNNs like clockwork: performance predictability from the bottom up. In: 14th USENIX Symposium on Operating Systems Design and Implementation, pp. 443\u2013462 (2020)"},{"key":"25_CR9","unstructured":"Author, F.: Article title. Journal 2(5), 99\u2013110 (2016)"},{"key":"25_CR10","doi-asserted-by":"publisher","unstructured":"Author, F., Author, S.: Title of a proceedings paper. In: Editor, F., Editor, S. (eds.) CONFERENCE 2016, LNCS, vol. 9999, pp. 1\u201313. Springer, Heidelberg (2016). https:\/\/doi.org\/10.10007\/1234567890","DOI":"10.10007\/1234567890"},{"key":"25_CR11","unstructured":"Author, F., Author, S., Author, T.: Book title, 2nd edn. Publisher, Location (1999)"},{"key":"25_CR12","unstructured":"Author, A.-B.: Contribution title. In: 9th International Proceedings on Proceedings, pp. 1\u20132. Publisher, Location (2010)"},{"key":"25_CR13","unstructured":"LNCS Homepage. http:\/\/www.springer.com\/lncs. Accessed 25 Oct 2023"},{"key":"25_CR14","unstructured":"163.com Technology Article. https:\/\/www.163.com\/dy\/article\/ISF368MT0539IMJ0.html. Accessed 28 Mar 2025"},{"key":"25_CR15","unstructured":"IDC Whitepaper Documentation. https:\/\/my.idc.com\/getdoc.jsp?containerId=prCHC53286125. Accessed 28 Mar 2025"},{"key":"25_CR16","unstructured":"Shahrad, M., Fonseca, R., Goiri, I., et al.: Serverless in the wild: characterizing and optimizing the serverless workload at a large cloud provider. In: 2020 USENIX Annual Technical Conference (USENIX ATC 20), pp. 205\u2013218 (2020)"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Liao, H., Tu, J., Xia, J., et al.: Ascend: a scalable and unified architecture for ubiquitous deep neural network computing: Industry track paper. In: 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 789\u2013801 (2021)","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Ouyang, J., Du, X., Ma, Y., et al.: 3.3 Kunlun: a 14 nm high-performance AI processor for diversified workloads. In: 2021 IEEE International Solid-State Circuits Conference (ISSCC), pp. 50\u201351 (2021)","DOI":"10.1109\/ISSCC42613.2021.9366056"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10466-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:00:09Z","timestamp":1763190009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10466-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9783032104656","9783032104663"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10466-3_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nha Trang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"14 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.npc-conference.com\/#\/npc2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}