{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:06:14Z","timestamp":1784300774373,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,5]]},"DOI":"10.1145\/3803437.3805562","type":"proceedings-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:27:39Z","timestamp":1784298459000},"page":"1232-1236","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AIMS: A Content-Aware Resource Management Approach for AI Assistant Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4422-6323","authenticated-orcid":false,"given":"Chiming","family":"Duan","sequence":"first","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5946-9829","authenticated-orcid":false,"given":"Tong","family":"Jia","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4439-9810","authenticated-orcid":false,"given":"Minghua","family":"He","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1674-0308","authenticated-orcid":false,"given":"Pei","family":"Xiao","sequence":"additional","affiliation":[{"name":"Peking university"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9500-4489","authenticated-orcid":false,"given":"Lingzhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhewei","family":"Zhong","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9667-2423","authenticated-orcid":false,"given":"Ying","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_2_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J Franklin, Joseph E Gonzalez, and Ion Stoica. 2017. Clipper: A {Low-Latency} online prediction serving system. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 613\u2013627."},{"key":"e_1_3_2_1_3_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_4_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Fu Yao","year":"2024","unstructured":"Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian Brabete, Dmitrii Ustiugov, Yuvraj Patel, and Luo Mai. 2024. {ServerlessLLM}:{Low-Latency} serverless inference for large language models. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 135\u2013153."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446700"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623278.3624758"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2023.3241299"},{"key":"e_1_3_2_1_8_1","volume-title":"Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"Kubernetes: Production-Grade Container Orchestration. https:\/\/kubernetes.io.","author":"Authors Kubernetes","year":"2023","unstructured":"Kubernetes Authors. 2023. Kubernetes: Production-Grade Container Orchestration. https:\/\/kubernetes.io."},{"key":"e_1_3_2_1_10_1","unstructured":"Woosuk Kwon. 2025. vLLM: An Efficient Inference Engine for Large Language Models. Ph. D. Dissertation. UC Berkeley."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2322420121"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Andrei A Rusu Joel Veness Marc G Bellemare Alex Graves Martin Riedmiller Andreas K Fidjeland Georg Ostrovski et al. 2015. Human-level control through deep reinforcement learning. nature 518 7540 (2015) 529\u2013533.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_13_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/arxiv.org\/abs\/2303.08774. arXiv:2303.08774."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3393427"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-srw.61"},{"key":"e_1_3_2_1_16_1","volume-title":"Prometheus: Monitoring System & Time Series Database. https:\/\/prometheus.io.","author":"Authors Prometheus","year":"2023","unstructured":"Prometheus Authors. 2023. Prometheus: Monitoring System & Time Series Database. https:\/\/prometheus.io."},{"key":"e_1_3_2_1_17_1","volume-title":"14th USENIX symposium on operating systems design and implementation (OSDI 20)","author":"Qiu Haoran","year":"2020","unstructured":"Haoran Qiu, Subho S Banerjee, Saurabh Jha, Zbigniew T Kalbarczyk, and Ravishankar K Iyer. 2020. {FIRM}: An intelligent fine-grained resource management framework for {SLO-Oriented} microservices. In 14th USENIX symposium on operating systems design and implementation (OSDI 20). 805\u2013825."},{"key":"e_1_3_2_1_18_1","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero, Qian Li, Neeraja J Yadwadkar, and Christos Kozyrakis. 2021. {INFaaS}: Automated model-less inference serving. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). 397\u2013411."},{"key":"e_1_3_2_1_19_1","unstructured":"Foteini Strati Sara Mcallister Amar Phanishayee Jakub Tarnawski and Ana Klimovic. 2024. D\u00e9j\u00e0Vu: KV-cache Streaming for Fast Fault-tolerant Generative LLM Serving. arXiv:2403.01876 [cs.DC] https:\/\/arxiv.org\/abs\/2403.01876"},{"key":"e_1_3_2_1_20_1","volume-title":"Attention is all you need. Advances in neural information processing systems 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. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616249"},{"key":"e_1_3_2_1_22_1","volume-title":"16th USENIX symposium on operating systems design and implementation (OSDI 22)","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A distributed serving system for {Transformer-Based} generative models. In 16th USENIX symposium on operating systems design and implementation (OSDI 22). 521\u2013538."}],"event":{"name":"FSE Companion '26: 34th ACM International Conference on the Foundations of Software Engineering","location":"Concordia University Montreal QC Canada","acronym":"FSE Companion '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803437.3805562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:28:33Z","timestamp":1784298513000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803437.3805562"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":22,"alternative-id":["10.1145\/3803437.3805562","10.1145\/3803437"],"URL":"https:\/\/doi.org\/10.1145\/3803437.3805562","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}