{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:38:49Z","timestamp":1777459129112,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":85,"publisher":"ACM","funder":[{"DOI":"10.13039\/100018699","name":"HORIZON EUROPE Digital, Industry and Space","doi-asserted-by":"publisher","award":["101192750"],"award-info":[{"award-number":["101192750"]}],"id":[{"id":"10.13039\/100018699","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3805621.3807633","type":"proceedings-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:08:45Z","timestamp":1777381725000},"page":"13-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Sampling Where It Matters: Predicting LLM Serving Performance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9653-1848","authenticated-orcid":false,"given":"Emile","family":"Aydar","sequence":"first","affiliation":[{"name":"IBM Research Europe, Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7060-2742","authenticated-orcid":false,"given":"Christian","family":"Pinto","sequence":"additional","affiliation":[{"name":"IBM Research Europe, Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8320-724X","authenticated-orcid":false,"given":"Srikumar","family":"Venugopal","sequence":"additional","affiliation":[{"name":"IBM Research Europe, Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4765-5085","authenticated-orcid":false,"given":"Dimitris","family":"Chatzopoulos","sequence":"additional","affiliation":[{"name":"University College Dublin, Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Vidur: A Large-Scale Simulation Framework For LLM Inference","author":"Agrawal Amey","year":"2024","unstructured":"Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav Gulavani, Ramachandran Ramjee, and Alexey Tumanov. 2024. Vidur: A Large-Scale Simulation Framework For LLM Inference. http:\/\/arxiv.org\/abs\/2405.05465 arXiv:2405.05465 [cs]."},{"key":"e_1_3_2_1_2_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Agrawal Amey","year":"2024","unstructured":"Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, and Ramachandran Ramjee. 2024. Taming {Throughput-Latency} tradeoff in {LLM} inference with {Sarathi-Serve }. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 117\u2013134."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the ACM\/SPEC International Conference on Performance Engineering. 277\u2013288","author":"Pereira Juliana Alves","year":"2020","unstructured":"Juliana Alves Pereira, Mathieu Acher, Hugo Martin, and Jean-Marc J\u00e9z\u00e9quel. 2020. Sampling effect on performance prediction of configurable systems: A case study. In Proceedings of the ACM\/SPEC International Conference on Performance Engineering. 277\u2013288."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 29th International Conference on Machine Learning (ICML-12)","author":"Bach Francis","year":"2012","unstructured":"Francis Bach, Simon Lacoste-Julien, and Guillaume Obozinski. 2012. On the Equivalence between Herding and Conditional Gradient Algorithms. In Proceedings of the 29th International Conference on Machine Learning (ICML-12), John Langford and Joelle Pineau (Eds.). Omnipress, 1359\u20131366. https:\/\/icml.cc\/2012\/papers\/bibfiles\/683.bib Also available as arXiv:1203.4523."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_19"},{"key":"e_1_3_2_1_6_1","volume-title":"Understanding and Optimizing Multi-Stage AI Inference Pipelines. arXiv preprint arXiv:2504.09775","author":"Bambhaniya Abhimanyu Rajeshkumar","year":"2025","unstructured":"Abhimanyu Rajeshkumar Bambhaniya, Hanjiang Wu, Suvinay Subramanian, Sudarshan Srinivasan, Souvik Kundu, Amir Yazdanbakhsh, Midhilesh Elavazhagan, Madhu Kumar, and Tushar Krishna. 2025. Understanding and Optimizing Multi-Stage AI Inference Pipelines. arXiv preprint arXiv:2504.09775 (2025)."},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. PMLR, 115\u2013123","author":"Bergstra James","year":"2013","unstructured":"James Bergstra, Daniel Yamins, and David Cox. 2013. Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In International conference on machine learning. PMLR, 115\u2013123."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545611"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3229161"},{"key":"e_1_3_2_1_10_1","volume-title":"Random forests. Machine learning 45, 1","author":"Breiman Leo","year":"2001","unstructured":"Leo Breiman. 2001. Random forests. Machine learning 45, 1 (2001), 5\u201332."},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Distributional random forests: Heterogeneity adjustment and multivariate distributional regression","volume":"23","author":"Cevid Domagoj","year":"2022","unstructured":"Domagoj Cevid, Loris Michel, Jeffrey N\u00e4f, Peter B\u00fchlmann, and Nicolai Meinshausen. 2022. Distributional random forests: Heterogeneity adjustment and multivariate distributional regression. Journal of Machine Learning Research 23, 333 (2022), 1\u201379.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_12_1","volume-title":"NeurIPS 2020 Workshop on Pre-registration in Machine Learning. PMLR, 14\u201332","author":"Chandra Akshay L","year":"2021","unstructured":"Akshay L Chandra, Sai Vikas Desai, Chaitanya Devaguptapu, and Vineeth N Balasubramanian. 2021. On initial pools for deep active learning. In NeurIPS 2020 Workshop on Pre-registration in Machine Learning. PMLR, 14\u201332."},{"key":"e_1_3_2_1_13_1","unstructured":"Tianqi Chen Tong He Michael Benesty Vadim Khotilovich Yuan Tang Hyunsu Cho Kailong Chen Rory Mitchell Ignacio Cano Tianyi Zhou et al. 2015. Xgboost: extreme gradient boosting. R package version 0.4-2 1 4 (2015) 1\u20134."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv"},{"key":"e_1_3_2_1_15_1","volume-title":"2024 IEEE International Symposium on Workload Characterization (IISWC). IEEE, 15\u201329","author":"Cho Jaehong","year":"2024","unstructured":"Jaehong Cho, Minsu Kim, Hyunmin Choi, Guseul Heo, and Jongse Park. 2024. Llmservingsim: A hw\/sw co-simulation infrastructure for llm inference serving at scale. In 2024 IEEE International Symposium on Workload Characterization (IISWC). IEEE, 15\u201329."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622737.1622744"},{"key":"e_1_3_2_1_17_1","unstructured":"William Jay Conover. 1999. Practical nonparametric statistics. john wiley & sons."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13643"},{"key":"e_1_3_2_1_19_1","volume-title":"Relative Performance Prediction Using Few-Shot Learning. In 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC)","author":"Dey Arunavo","unstructured":"Arunavo Dey, Aakash Dhakal, Tanzima Z Islam, Jae-Seung Yeom, Tapasya Patki, Daniel Nichols, Alexander Movsesyan, and Abhinav Bhatele. 2024. Relative Performance Prediction Using Few-Shot Learning. In 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC). IEEE, 1764\u20131769."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492922000014"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/1941868"},{"key":"e_1_3_2_1_22_1","volume-title":"CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363","author":"Dorogush Anna Veronika","year":"2018","unstructured":"Anna Veronika Dorogush, Vasily Ershov, and Andrey Gulin. 2018. CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363 (2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data. arXiv preprint arXiv:2003.06505","author":"Erickson Nick","year":"2020","unstructured":"Nick Erickson, Jonas Mueller, Alexander Shirkov, Hang Zhang, Pedro Larroy, Mu Li, and Alexander Smola. 2020. AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data. arXiv preprint arXiv:2003.06505 (2020)."},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 1437\u20131446","author":"Falkner Stefan","year":"2018","unstructured":"Stefan Falkner, Aaron Klein, and Frank Hutter. 2018. BOHB: Robust and efficient hyperparameter optimization at scale. In International conference on machine learning. PMLR, 1437\u20131446."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 4th Workshop on Practical Adoption Challenges of ML for Systems. 25\u201330","author":"Feng Yicheng","year":"2025","unstructured":"Yicheng Feng, Xin Tan, Kin Hang Sew, Yimin Jiang, Yibo Zhu, and Hong Xu. 2025. Frontier: Simulating the Next Generation of LLM Inference Systems. In Proceedings of the 4th Workshop on Practical Adoption Challenges of ML for Systems. 25\u201330."},{"key":"e_1_3_2_1_26_1","volume-title":"Do we need hundreds of classifiers to solve real world classification problems? The journal of machine learning research 15, 1","author":"Fern\u00e1ndez-Delgado Manuel","year":"2014","unstructured":"Manuel Fern\u00e1ndez-Delgado, Eva Cernadas, Sen\u00e9n Barro, and Dinani Amorim. 2014. Do we need hundreds of classifiers to solve real world classification problems? The journal of machine learning research 15, 1 (2014), 3133\u20133181."},{"key":"e_1_3_2_1_27_1","volume-title":"A tutorial on Bayesian optimization. arXiv preprint arXiv:1807.02811","author":"Frazier Peter I","year":"2018","unstructured":"Peter I Frazier. 2018. A tutorial on Bayesian optimization. arXiv preprint arXiv:1807.02811 (2018)."},{"key":"e_1_3_2_1_28_1","volume-title":"Greedy function approximation: a gradient boosting machine. Annals of statistics","author":"Friedman Jerome H","year":"2001","unstructured":"Jerome H Friedman. 2001. Greedy function approximation: a gradient boosting machine. Annals of statistics (2001), 1189\u20131232."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Yanjie Gao Xianyu Gu Hongyu Zhang Haoxiang Lin and Mao Yang. 2023. Runtime Performance Prediction for Deep Learning Models with Graph Neural Network. In 2023 IEEE\/ACM 45th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). 368\u2013380. doi:10.1109\/ICSE-SEIP58684.2023.00039","DOI":"10.1109\/ICSE-SEIP58684.2023.00039"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.004"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1201\/9780367815493"},{"key":"e_1_3_2_1_32_1","article-title":"Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge","volume":"8","author":"H\u00e4se Florian","year":"2021","unstructured":"Florian H\u00e4se, Matteo Aldeghi, Riley J Hickman, Lo\u00efc M Roch, and Al\u00e1n Aspuru-Guzik. 2021. Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge. Applied Physics Reviews 8, 3 (2021).","journal-title":"Applied Physics Reviews"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.20944\/preprints202507.0252.v1"},{"key":"e_1_3_2_1_34_1","volume-title":"Numerical studies of the metamodel fitting and validation processes. arXiv preprint arXiv:1001.1049","author":"Iooss Bertrand","year":"2010","unstructured":"Bertrand Iooss, Lo\u00efc Boussouf, Vincent Feuillard, and Amandine Marrel. 2010. Numerical studies of the metamodel fitting and validation processes. arXiv preprint arXiv:1001.1049 (2010)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3774418"},{"key":"e_1_3_2_1_36_1","volume-title":"Regression conformal prediction with random forests. Machine learning 97, 1","author":"Johansson Ulf","year":"2014","unstructured":"Ulf Johansson, Henrik Bostr\u00f6m, Tuve L\u00f6fstr\u00f6m, and Henrik Linusson. 2014. Regression conformal prediction with random forests. Machine learning 97, 1 (2014), 155\u2013176."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/0378-3758(90)90122-B"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-023-00951-7"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00112"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: a highly efficient gradient boosting decision tree. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 3149\u20133157."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00294"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the 2018 USENIX Conference on Usenix Annual Technical Conference (Boston, MA, USA) (USENIX ATC '18). USENIX Association, USA, 759\u2013773","author":"Klimovic Ana","year":"2018","unstructured":"Ana Klimovic, Heiner Litz, and Christos Kozyrakis. 2018. Selecta: heterogeneous cloud storage configuration for data analytics. In Proceedings of the 2018 USENIX Conference on Usenix Annual Technical Conference (Boston, MA, USA) (USENIX ATC '18). USENIX Association, USA, 759\u2013773."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research","volume":"552","author":"Lacoste-Julien Simon","year":"2015","unstructured":"Simon Lacoste-Julien, Fredrik Lindsten, and Francis Bach. 2015. Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering. In Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 38). PMLR, 544\u2013552. https:\/\/proceedings.mlr.press\/v38\/lacoste-julien15.html"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00022"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1198\/TECH.2009.08040"},{"key":"e_1_3_2_1_48_1","volume-title":"On Latin hypercube sampling. The annals of statistics 24, 5","author":"Loh Wei-Liem","year":"1996","unstructured":"Wei-Liem Loh. 1996. On Latin hypercube sampling. The annals of statistics 24, 5 (1996), 2058\u20132080."},{"key":"e_1_3_2_1_49_1","first-page":"3","article-title":"Combining multitask and transfer learning with deep Gaussian processes for autotuning-based performance engineering","volume":"37","author":"Luszczek Piotr","year":"2023","unstructured":"Piotr Luszczek, Wissam M Sid-Lakhdar, and Jack Dongarra. 2023. Combining multitask and transfer learning with deep Gaussian processes for autotuning-based performance engineering. The International Journal of High Performance Computing Applications 37, 3\u20134 (2023), 229\u2013244.","journal-title":"The International Journal of High Performance Computing Applications"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.4.590"},{"key":"e_1_3_2_1_51_1","volume-title":"2020 USENIX Annual Technical Conference (USENIX ATC 20)","author":"Mahgoub Ashraf","year":"2020","unstructured":"Ashraf Mahgoub, Alexander Michaelson Medoff, Rakesh Kumar, Subrata Mitra, Ana Klimovic, Somali Chaterji, and Saurabh Bagchi. 2020. OPTIMUSCLOUD: Heterogeneous configuration optimization for distributed databases in the cloud. In 2020 USENIX Annual Technical Conference (USENIX ATC 20). 189\u2013203."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126969"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1979.10489755"},{"key":"e_1_3_2_1_54_1","volume-title":"coverforest: Conformal predictions with random forest in python. Neurocomputing","author":"Meehinkong Panisara","year":"2025","unstructured":"Panisara Meehinkong and Donlapark Ponnoprat. 2025. coverforest: Conformal predictions with random forest in python. Neurocomputing (2025), 132362."},{"key":"e_1_3_2_1_55_1","article-title":"Quantile regression forests","volume":"7","author":"Meinshausen Nicolai","year":"2006","unstructured":"Nicolai Meinshausen and Greg Ridgeway. 2006. Quantile regression forests. Journal of machine learning research 7, 6 (2006).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00090"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3754448","article-title":"Towards efficient generative large language model serving: A survey from algorithms to systems","volume":"58","author":"Miao Xupeng","year":"2025","unstructured":"Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Hongyi Jin, Tianqi Chen, and Zhihao Jia. 2025. Towards efficient generative large language model serving: A survey from algorithms to systems. Comput. Surveys 58, 1 (2025), 1\u201337.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640411"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06003-9"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970081"},{"key":"e_1_3_2_1_61_1","volume-title":"Combinatorial bayesian optimization using the graph cartesian product. Advances in Neural Information Processing Systems 32","author":"Oh Changyong","year":"2019","unstructured":"Changyong Oh, Jakub Tomczak, Efstratios Gavves, and Max Welling. 2019. Combinatorial bayesian optimization using the graph cartesian product. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1111\/j.2517-6161.1992.tb01895.x","article-title":"A central limit theorem for Latin hypercube sampling","volume":"54","author":"Owen Art B","year":"1992","unstructured":"Art B Owen. 1992. A central limit theorem for Latin hypercube sampling. Journal of the Royal Statistical Society: Series B (Methodological) 54, 2 (1992), 541\u2013551.","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)"},{"key":"e_1_3_2_1_63_1","volume-title":"Latin hypercube sampling with dependence and applications in finance. Available at SSRN 1269633","author":"Packham Natalie","year":"2008","unstructured":"Natalie Packham and Wolfgang M Schmidt. 2008. Latin hypercube sampling with dependence and applications in finance. Available at SSRN 1269633 (2008)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-011-9242-3"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593712"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263774"},{"key":"e_1_3_2_1_68_1","volume-title":"International Conference on Machine Learning. PMLR, 8276\u20138285","author":"Ru Binxin","year":"2020","unstructured":"Binxin Ru, Ahsan Alvi, Vu Nguyen, Michael A Osborne, and Stephen Roberts. 2020. Bayesian optimisation over multiple continuous and categorical inputs. In International Conference on Machine Learning. PMLR, 8276\u20138285."},{"key":"e_1_3_2_1_69_1","volume-title":"Design and analysis of computer experiments. Statistical science 4, 4","author":"Sacks Jerome","year":"1989","unstructured":"Jerome Sacks, William J Welch, Toby J Mitchell, and Henry P Wynn. 1989. Design and analysis of computer experiments. Statistical science 4, 4 (1989), 409\u2013423."},{"key":"e_1_3_2_1_70_1","unstructured":"Burr Settles. 2009. Active learning literature survey."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130417"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"e_1_3_2_1_73_1","volume-title":"Progressive Latin Hypercube Sampling: An efficient approach for robust sampling-based analysis of environmental models. Environmental modelling & software 93","author":"Sheikholeslami Razi","year":"2017","unstructured":"Razi Sheikholeslami and Saman Razavi. 2017. Progressive Latin Hypercube Sampling: An efficient approach for robust sampling-based analysis of environmental models. Environmental modelling & software 93 (2017), 109\u2013126."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(67)"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1987.10488205"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1993.10476423"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01169"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205321"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486987"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.09.060"},{"key":"e_1_3_2_1_82_1","unstructured":"Tianhao Xu Yiming Liu Xianglong Lu Yijia Zhao Xuting Zhou Aichen Feng Yiyi Chen Yi Shen Qin Zhou Xumeng Chen et al. 2026. AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving. arXiv preprint arXiv:2601.06288 (2026)."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1998.10473803"},{"key":"e_1_3_2_1_84_1","volume-title":"Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun.","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. 521\u2013538. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu"},{"key":"e_1_3_2_1_85_1","volume-title":"Propensity score and proximity matching using random forest. Contemporary clinical trials 47","author":"Zhao Peng","year":"2016","unstructured":"Peng Zhao, Xiaogang Su, Tingting Ge, and Juanjuan Fan. 2016. Propensity score and proximity matching using random forest. Contemporary clinical trials 47 (2016), 85\u201392."}],"event":{"name":"EuroSys '26: 21st European Conference on Computer Systems","location":"Edinburgh Scotland Uk","acronym":"EuroMLSys '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Sixth European Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805621.3807633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:09:20Z","timestamp":1777381760000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805621.3807633"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":85,"alternative-id":["10.1145\/3805621.3807633","10.1145\/3805621"],"URL":"https:\/\/doi.org\/10.1145\/3805621.3807633","relation":{},"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"2026-04-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}