{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T07:35:10Z","timestamp":1777102510286,"version":"3.51.4"},"reference-count":109,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"National Key Research and Development Program of China","award":["2023YFB3308501"],"award-info":[{"award-number":["2023YFB3308501"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62302300, 62472279"],"award-info":[{"award-number":["62302300, 62472279"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM113"],"award-info":[{"award-number":["JYB2025XDXM113"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Comput. Syst."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>\n                    Current serverless platforms struggle to optimize resource utilization for both CPU and GPU functions due to their dynamic and fine-grained nature. Conventional techniques like overcommitment and autoscaling fall short, often sacrificing utilization for practicability or incurring performance tradeoffs. Overcommitment requires predicting performance to prevent QoS violation, introducing tradeoff between prediction accuracy and overheads. Autoscaling requires scaling instances in response to load fluctuations quickly to reduce resource wastage, but more frequent scaling also leads to more cold start overheads. The rich concurrency of GPU resources further complicates GPU instance orchestration, such as setting right batch sizes. This article introduces\n                    <jats:sc>Jiagu<\/jats:sc>\n                    to harmonize efficiency with practicability through the following novel techniques. First,\n                    <jats:italic toggle=\"yes\">pre-decision scheduling<\/jats:italic>\n                    achieves accurate prediction while eliminating overheads by decoupling prediction and scheduling. Second,\n                    <jats:italic toggle=\"yes\">dual-staged scaling<\/jats:italic>\n                    achieves frequent adjustment of instances with minimum overhead. Third,\n                    <jats:sc>Jiagu<\/jats:sc>\n                    conducts an in-depth analysis about the complexity of the relationship between GPU function configuration and execution. It then proposes\n                    <jats:italic toggle=\"yes\">batch-aware scaling<\/jats:italic>\n                    that achieves optimal configurations for both batch size setting and autoscaling, addressing all the challenges according to the analysis. We have implemented a prototype and evaluated it using real-world applications and traces from the public cloud platform. Our evaluation shows an improvement in deployment density over commercial clouds (with Kubernetes) while maintaining QoS for both CPU and GPU functions (54.8% and 18% respectively), and 81.0%\u201393.7% lower scheduling costs and a 57.4%\u201369.3% reduction in cold start latency compared to existing QoS-aware schedulers.\n                  <\/jats:p>","DOI":"10.1145\/3788863","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:47:27Z","timestamp":1768337247000},"page":"1-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Resource-Efficient Orchestration for Heterogeneous Serverless Computing with Harmonized Effectiveness and Practicability"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9080-2720","authenticated-orcid":false,"given":"Qingyuan","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University School of Software","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1080-2924","authenticated-orcid":false,"given":"Yanning","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University School of Software","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7945-8430","authenticated-orcid":false,"given":"Dong","family":"Du","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University School of Software","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6558-5298","authenticated-orcid":false,"given":"Yubin","family":"Xia","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University School of Software","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1933-9886","authenticated-orcid":false,"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technologies Co Ltd","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4764-5997","authenticated-orcid":false,"given":"Jia","family":"Feng","sequence":"additional","affiliation":[{"name":"Huawei Cloud Computing Technologies Co Ltd","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9720-0361","authenticated-orcid":false,"given":"Haibo","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University School of Software","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"e_1_3_3_2_2","unstructured":"2026. Apache OpenWhisk is a serverless open source cloud platform. Retrieved from http:\/\/openwhisk.apache.org\/"},{"key":"e_1_3_3_3_2","unstructured":"2026. Cloud computing trends and statistics: Flexera 2023 State of the Cloud Report. Retrieved from https:\/\/www.flexera.com\/blog\/cloud\/cloud-computing-trends-flexera-2023-state-of-the-cloud-report\/"},{"key":"e_1_3_3_4_2","unstructured":"2026. Deployments | Kubernetes. Retrieved from https:\/\/kubernetes.io\/docs\/concepts\/services-networking\/service\/"},{"key":"e_1_3_3_5_2","unstructured":"2026. Knative Autoscaling. Retrieved from https:\/\/knative.dev\/docs\/serving\/autoscaling\/"},{"key":"e_1_3_3_6_2","unstructured":"2026. Kubernetes Scheduler. Retrieved from https:\/\/kubernetes.io\/docs\/concepts\/scheduling-eviction\/kube-scheduler\/"},{"key":"e_1_3_3_7_2","unstructured":"2026. OpenFaaS - Serverless Functions Made Simple. Retrieved from https:\/\/www.openfaas.com"},{"key":"e_1_3_3_8_2","unstructured":"2026. Openfaas Autoscaling. Retrieved from https:\/\/docs.openfaas.com\/architecture\/autoscaling\/"},{"key":"e_1_3_3_9_2","unstructured":"2026. Prometheus - Monitoring system and time series database. Retrieved from https:\/\/prometheus.io\/"},{"key":"e_1_3_3_10_2","unstructured":"2026. scikit-learn: machine learning in Python. Retrieved from https:\/\/scikit-learn.org\/"},{"key":"e_1_3_3_11_2","unstructured":"2026. Service | Kubernetes. Retrieved from https:\/\/kubernetes.io\/docs\/concepts\/services-networking\/service\/"},{"key":"e_1_3_3_12_2","unstructured":"2026. 1. Introduction - Multi-Process Service r555 documentation. Retrieved from https:\/\/docs.nvidia.com\/deploy\/mps\/index.html"},{"key":"e_1_3_3_13_2","unstructured":"2024. Fibonacci method. Retrieved from https:\/\/encyclopediaofmath.org\/wiki\/Fibonacci_method"},{"key":"e_1_3_3_14_2","unstructured":"2026. Multi-Process Service. Retrieved from https:\/\/docs.nvidia.com\/deploy\/mps\/"},{"key":"e_1_3_3_15_2","unstructured":"2026. Nvidia DCGM Documentation. Retrieved from https:\/\/docs.nvidia.com\/datacenter\/dcgm\/latest\/user-guide\/feature-overview.html"},{"key":"e_1_3_3_16_2","unstructured":"2026. NVIDIA\/k8s-device-plugin: NVIDIA device plugin for Kubernetes. Retrieved from https:\/\/github.com\/NVIDIA\/k8s-device-plugin"},{"key":"e_1_3_3_17_2","unstructured":"2024. Overview - NVIDIA Container Toolkit 1.17.3 documentation. Retrieved from https:\/\/docs.nvidia.com\/datacenter\/cloud-native\/container-toolkit\/latest\/index.html"},{"key":"e_1_3_3_18_2","unstructured":"2026. BERT base model. Retrieved from https:\/\/huggingface.co\/google-bert\/bert-base-uncased"},{"key":"e_1_3_3_19_2","unstructured":"2026. Enterprise resource planning. Retrieved from https:\/\/en.wikipedia.org\/wiki\/Enterprise_resource_planning"},{"key":"e_1_3_3_20_2","unstructured":"2026. KServe Documentation Website. Retrieved from https:\/\/kserve.github.io\/website"},{"key":"e_1_3_3_21_2","unstructured":"2026. Models and pre-trained weights. Retrieved from https:\/\/docs.pytorch.org\/vision\/stable\/models.html"},{"key":"e_1_3_3_22_2","unstructured":"2026. OPT : Open Pre-trained Transformer Language Models. Retrieved from https:\/\/huggingface.co\/facebook\/opt-125m"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567496"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155363"},{"key":"e_1_3_3_25_2","first-page":"923","volume-title":"Proceedings of the 2018  \\(USENIX\\)  Annual Technical Conference ( \\(USENIX\\)  \\(ATC\\)  18)","author":"Akkus Istemi Ekin","year":"2018","unstructured":"Istemi Ekin Akkus, Ruichuan Chen, Ivica Rimac, Manuel Stein, Klaus Satzke, Andre Beck, Paarijaat Aditya, and Volker Hilt. 2018. \\(SAND\\) : Towards high-performance serverless computing. In Proceedings of the 2018 \\(USENIX\\) Annual Technical Conference ( \\(USENIX\\) \\(ATC\\) 18). 923\u2013935."},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/862270"},{"key":"e_1_3_3_28_2","first-page":"623","volume-title":"Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Bhardwaj Romil","year":"2023","unstructured":"Romil Bhardwaj, Kirthevasan Kandasamy, Asim Biswal, Wenshuo Guo, Benjamin Hindman, Joseph Gonzalez, Michael Jordan, and Ion Stoica. 2023. Cilantro: Performance-aware resource allocation for general objectives via online feedback. In Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). USENIX Association, Boston, MA, 623\u2013643. Retrieved fromhttps:\/\/www.usenix.org\/conference\/osdi23\/presentation\/bhardwaj"},{"key":"e_1_3_3_29_2","article-title":"Lambda Snapstart, and snapshots as a tool for system builders","author":"Brooker Marc","year":"2026","unstructured":"Marc Brooker. 2026. Lambda Snapstart, and snapshots as a tool for system builders. Retrieved from https:\/\/brooker.co.za\/blog\/2022\/11\/29\/snapstart.html","journal-title":"https:\/\/brooker.co.za\/blog\/2022\/11\/29\/snapstart.html"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3392698"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"},{"key":"e_1_3_3_32_2","volume-title":"Proceedings of the 2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Chen Jiahao","year":"2024","unstructured":"Jiahao Chen, Zeyu Mi, Yubin Xia, Haibing Guan, and Haibo Chen. 2024. CPC: Flexible, secure, and efficient CVM maintenance with confidential procedure calls. In Proceedings of the 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA."},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330370"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037700"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304005"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00020"},{"key":"e_1_3_3_37_2","first-page":"199","volume-title":"Proceedings of the 2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Choi Seungbeom","year":"2022","unstructured":"Seungbeom Choi, Sunho Lee, Yeonjae Kim, Jongse Park, Youngjin Kwon, and Jaehyuk Huh. 2022. Serving heterogeneous machine learning models on multi-GPU servers with Spatio-Temporal sharing. In Proceedings of the 2022 USENIX Annual Technical Conference (USENIX ATC 22). USENIX Association, Carlsbad, CA, 199\u2013216. Retrieved fromhttps:\/\/www.usenix.org\/conference\/atc22\/presentation\/choi-seungbeom"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476143"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451125"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541941"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806779"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507732"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378512"},{"key":"e_1_3_3_45_2","volume-title":"Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation","author":"Fried Joshua","year":"2020","unstructured":"Joshua Fried, Zhenyuan Ruan, Amy Ousterhout, and Adam Belay. 2020. Caladan: Mitigating interference at microsecond timescales. In Proceedings of the 14th USENIX Conference on Operating Systems Design and Implementation. USENIX Association, USA, Article 16, 17 pages."},{"key":"e_1_3_3_46_2","first-page":"135","volume-title":"Proceedings of the 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 Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 135\u2013153. Retrieved fromhttps:\/\/www.usenix.org\/conference\/osdi24\/presentation\/fu"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446757"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446700"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304004"},{"key":"e_1_3_3_50_2","first-page":"443","volume-title":"Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Gujarati Arpan","year":"2020","unstructured":"Arpan Gujarati, Reza Karimi, Safya Alzayat, Wei Hao, Antoine Kaufmann, Ymir Vigfusson, and Jonathan Mace. 2020. Serving DNNs like Clockwork: Performance predictability from the bottom up. In Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 443\u2013462. Retrieved fromhttps:\/\/www.usenix.org\/conference\/osdi20\/presentation\/gujarati"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3423211.3425683"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698555"},{"key":"e_1_3_3_53_2","first-page":"539","volume-title":"Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Han Mingcong","year":"2022","unstructured":"Mingcong Han, Hanze Zhang, Rong Chen, and Haibo Chen. 2022. Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences. In Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 539\u2013558. Retrieved fromhttps:\/\/www.usenix.org\/conference\/osdi22\/presentation\/han"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483541"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446701"},{"key":"e_1_3_3_56_2","unstructured":"Eric Jonas Johann Schleier-Smith Vikram Sreekanti Chia-Che Tsai Anurag Khandelwal Qifan Pu Vaishaal Shankar Joao Carreira Karl Krauth Neeraja Yadwadkar Joseph E. Gonzalez Raluca Ada Popa Ion Stoica and David A. Patterson. 2019. Cloud programming simplified: A Berkeley view on serverless computing. arXiv:1902.03383. Retrieved from https:\/\/arxiv.org\/abs\/1902.03383"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624783"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563468"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3365439"},{"key":"e_1_3_3_60_2","first-page":"427","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Klimovic Ana","year":"2018","unstructured":"Ana Klimovic, Yawen Wang, Patrick Stuedi, Animesh Trivedi, Jonas Pfefferle, and Christos Kozyrakis. 2018. Pocket: Elastic ephemeral storage for serverless analytics. In Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA, 427\u2013444. Retrieved fromhttps:\/\/www.usenix.org\/conference\/osdi18\/presentation\/klimovic"},{"key":"e_1_3_3_61_2","volume-title":"Proceedings of the 53rd IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Kulkarni Neeraj","year":"2020","unstructured":"Neeraj Kulkarni, Gonzalo Gonzalez-Pumariega, Amulya Khurana, Christine Shoemaker, Christina Delimitrou, and David Albonesi. 2020. CuttleSys: Data-driven resource management for interactive applications on reconfigurable multicores. In Proceedings of the 53rd IEEE\/ACM International Symposium on Microarchitecture (MICRO)."},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2021.3066142"},{"key":"e_1_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624645"},{"key":"e_1_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507717"},{"key":"e_1_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624785"},{"key":"e_1_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749475"},{"key":"e_1_3_3_67_2","first-page":"303","volume-title":"Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Mahgoub Ashraf","year":"2022","unstructured":"Ashraf Mahgoub, Edgardo Barsallo Yi, Karthick Shankar, Sameh Elnikety, Somali Chaterji, and Saurabh Bagchi. 2022. ORION and the three rights: Sizing, bundling, and prewarming for serverless dags. In Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 303\u2013320. Retrieved from https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/mahgoub"},{"key":"e_1_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3530892"},{"key":"e_1_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/2663165.2663330"},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485975"},{"key":"e_1_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155650"},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2017.29"},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD49709.2020.00042"},{"key":"e_1_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMSNETS.2019.8711058"},{"key":"e_1_3_3_75_2","first-page":"57","volume-title":"Proceedings of the 2018  \\(USENIX\\)  Annual Technical Conference ( \\(USENIX\\)  \\(ATC\\)  18)","author":"Oakes Edward","year":"2018","unstructured":"Edward Oakes, Leon Yang, Dennis Zhou, Kevin Houck, Tyler Harter, Andrea Arpaci-Dusseau, and Remzi Arpaci-Dusseau. 2018. \\(SOCK\\) : Rapid task provisioning with serverless-optimized containers. In Proceedings of the 2018 \\(USENIX\\) Annual Technical Conference ( \\(USENIX\\) \\(ATC\\) 18). 57\u201370."},{"key":"e_1_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00025"},{"key":"e_1_3_3_77_2","volume-title":"FIRM: An Intelligent Fine-Grained Resource Management Framework for SLO-Oriented Microservices","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. USENIX Association, USA."},{"key":"e_1_3_3_78_2","first-page":"387","volume-title":"Proceedings of the 2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Qiu Haoran","year":"2023","unstructured":"Haoran Qiu, Weichao Mao, Chen Wang, Hubertus Franke, Alaa Youssef, Zbigniew T. Kalbarczyk, Tamer Ba\u015far, and Ravishankar K. Iyer. 2023. AWARE: Automate workload autoscaling with reinforcement learning in production cloud systems. In Proceedings of the 2023 USENIX Annual Technical Conference (USENIX ATC 23). USENIX Association, Boston, MA, 387\u2013402. Retrieved fromhttps:\/\/www.usenix.org\/conference\/atc23\/presentation\/qiu-haoran"},{"key":"e_1_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486972"},{"key":"e_1_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507750"},{"key":"e_1_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387524"},{"key":"e_1_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2018.00113"},{"key":"e_1_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527390"},{"key":"e_1_3_3_84_2","first-page":"205","volume-title":"Proceedings of the 2020  \\(USENIX\\)  Annual Technical Conference ( \\(USENIX\\)  \\(ATC\\)  20)","author":"Shahrad Mohammad","year":"2020","unstructured":"Mohammad Shahrad, Rodrigo Fonseca, \u00cd\u00f1igo Goiri, Gohar Chaudhry, Paul Batum, Jason Cooke, Eduardo Laureano, Colby Tresness, Mark Russinovich, and Ricardo Bianchini. 2020. Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider. In Proceedings of the 2020 \\(USENIX\\) Annual Technical Conference ( \\(USENIX\\) \\(ATC\\) 20). 205\u2013218."},{"key":"e_1_3_3_85_2","first-page":"419","volume-title":"Proceedings of the 2020  \\(USENIX\\)  Annual Technical Conference ( \\(USENIX\\)  \\(ATC\\)  20)","author":"Shillaker Simon","year":"2020","unstructured":"Simon Shillaker and Peter Pietzuch. 2020. Faasm: Lightweight isolation for efficient stateful serverless computing. In Proceedings of the 2020 \\(USENIX\\) Annual Technical Conference ( \\(USENIX\\) \\(ATC\\) 20). 419\u2013433."},{"key":"e_1_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519581"},{"key":"e_1_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486981"},{"key":"e_1_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407836"},{"key":"e_1_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629578"},{"key":"e_1_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421306"},{"key":"e_1_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563470"},{"key":"e_1_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605181.3626191"},{"key":"e_1_3_3_93_2","first-page":"443","volume-title":"Proceedings of the 2021 USENIX Annual Technical Conference, USENIX ATC 2021, July 14-16, 2021","author":"Wang Ao","year":"2021","unstructured":"Ao Wang, Shuai Chang, Huangshi Tian, Hongqi Wang, Haoran Yang, Huiba Li, Rui Du, and Yue Cheng. 2021. FaaSNet: Scalable and fast provisioning of custom serverless container runtimes at Alibaba cloud function compute. In Proceedings of the 2021 USENIX Annual Technical Conference, USENIX ATC 2021, July 14-16, 2021, Irina Calciu and Geoff Kuenning (Eds.). USENIX Association, 443\u2013457. Retrieved from https:\/\/www.usenix.org\/conference\/atc21\/presentation\/wang-ao"},{"key":"e_1_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303978"},{"key":"e_1_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563469"},{"key":"e_1_3_3_96_2","first-page":"945","volume-title":"Proceedings of the 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Weng Qizhen","year":"2022","unstructured":"Qizhen Weng, Wencong Xiao, Yinghao Yu, Wei Wang, Cheng Wang, Jian He, Yong Li, Liping Zhang, Wei Lin, and Yu Ding. 2022. MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters. In Proceedings of the 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, 945\u2013960. Retrieved fromhttps:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/weng"},{"key":"e_1_3_3_97_2","first-page":"69","volume-title":"Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wu Bingyang","year":"2023","unstructured":"Bingyang Wu, Zili Zhang, Zhihao Bai, Xuanzhe Liu, and Xin Jin. 2023. Transparent GPU sharing in container clouds for deep learning workloads. In Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, Boston, MA, 69\u201385. Retrieved from https:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/wu"},{"key":"e_1_3_3_98_2","first-page":"533","volume-title":"Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Xiao Wencong","year":"2020","unstructured":"Wencong Xiao, Shiru Ren, Yong Li, Yang Zhang, Pengyang Hou, Zhi Li, Yihui Feng, Wei Lin, and Yangqing Jia. 2020. AntMan: Dynamic scaling on GPU clusters for deep learning. In Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 533\u2013548. Retrieved fromhttps:\/\/www.usenix.org\/conference\/osdi20\/presentation\/xiao"},{"key":"e_1_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/3274808.3274820"},{"key":"e_1_3_3_100_2","doi-asserted-by":"publisher","DOI":"10.1145\/2508148.2485974"},{"key":"e_1_3_3_101_2","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698510"},{"key":"e_1_3_3_102_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507709"},{"key":"e_1_3_3_103_2","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421280"},{"key":"e_1_3_3_104_2","first-page":"787","volume-title":"Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Zhang Hong","year":"2023","unstructured":"Hong Zhang, Yupeng Tang, Anurag Khandelwal, and Ion Stoica. 2023. SHEPHERD: Serving DNNs in the wild. In Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, Boston, MA, 787\u2013808. Retrieved fromhttps:\/\/www.usenix.org\/conference\/nsdi23\/presentation\/zhang-hong"},{"key":"e_1_3_3_105_2","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465388"},{"key":"e_1_3_3_106_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483580"},{"key":"e_1_3_3_107_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446693"},{"key":"e_1_3_3_108_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.53"},{"key":"e_1_3_3_109_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476215"},{"key":"e_1_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3567955.3567960"}],"container-title":["ACM Transactions on Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T06:39:09Z","timestamp":1777099149000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788863"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":109,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3788863"],"URL":"https:\/\/doi.org\/10.1145\/3788863","relation":{},"ISSN":["0734-2071","1557-7333"],"issn-type":[{"value":"0734-2071","type":"print"},{"value":"1557-7333","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]},"assertion":[{"value":"2025-02-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-23","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}