{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:46:59Z","timestamp":1773726419544,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,4]]},"DOI":"10.1145\/3632366.3632396","type":"proceedings-article","created":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T17:02:02Z","timestamp":1712163722000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7474-2689","authenticated-orcid":false,"given":"Nathaniel C","family":"Hudson","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, United States"},{"name":"Data Science and Learning Division, Argonne National Laboratory, Lemont, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6547-6902","authenticated-orcid":false,"given":"J. Gregory","family":"Pauloski","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2227-2851","authenticated-orcid":false,"given":"Matt","family":"Baughman","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6428-4829","authenticated-orcid":false,"given":"Alok","family":"Kamatar","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0041-0160","authenticated-orcid":false,"given":"Mansi","family":"Sakarvadia","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1323-5939","authenticated-orcid":false,"given":"Logan","family":"Ward","sequence":"additional","affiliation":[{"name":"Data Science and Learning Division, Argonne National Laboratory, Lemont, Illinois, US"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6781-7432","authenticated-orcid":false,"given":"Ryan","family":"Chard","sequence":"additional","affiliation":[{"name":"Data Science and Learning Division, Argonne National Laboratory, Lemont, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5582-8812","authenticated-orcid":false,"given":"Andr\u00e9","family":"Bauer","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, United States"},{"name":"Data Science and Learning Division, Argonne National Laboratory, Lemont, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3450-2847","authenticated-orcid":false,"given":"Maksim","family":"Levental","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0934-8770","authenticated-orcid":false,"given":"Wenyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3372-080X","authenticated-orcid":false,"given":"Will","family":"Engler","sequence":"additional","affiliation":[{"name":"Globus, University of Chicago, Chicago, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8954-5549","authenticated-orcid":false,"given":"Owen","family":"Price Skelly","sequence":"additional","affiliation":[{"name":"Globus, University of Chicago, Chicago, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5326-4902","authenticated-orcid":false,"given":"Ben","family":"Blaiszik","sequence":"additional","affiliation":[{"name":"Globus, The University of Chicago, Chicago, Illinois, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4268-4020","authenticated-orcid":false,"given":"Rick","family":"Stevens","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, United States"},{"name":"Computing, Environment and Life Science Directorate, Argonne National Laboratory, Lemont, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7370-4805","authenticated-orcid":false,"given":"Kyle","family":"Chard","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, USA"},{"name":"Data Science and Learning Division, Argonne National Laboratory, Lemont, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2129-5269","authenticated-orcid":false,"given":"Ian","family":"Foster","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Chicago, Chicago, Illinois, USA"},{"name":"Data Science and Learning Division, Argonne National Laboratory, Lemont, Illinois, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,4,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"https:\/\/aws.amazon.com\/sagemaker\/. Last accessed on","author":"Services Amazon Web","year":"2023","unstructured":"Amazon Web Services. 2017. AWS SageMaker. https:\/\/aws.amazon.com\/sagemaker\/. Last accessed on October 8, 2023."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC '22)","author":"Aminabadi Reza Yazdani","year":"2022","unstructured":"Reza Yazdani Aminabadi, Samyam Rajbhandari, Ammar Ahmad Awan, Cheng Li, Du Li, Elton Zheng, Olatunji Ruwase, et al. 2022. DeepSpeed-Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC '22). IEEE Press, Article 46, 15 pages."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Nora Belrose Zach Furman Logan Smith Danny Halawi Igor Ostrovsky Lev McKinney Stella Biderman and Jacob Steinhardt. 2023. Eliciting latent predictions from transformers with the tuned lens. 10.48550\/arXiv.2303.08112","DOI":"10.48550\/arXiv.2303.08112"},{"key":"e_1_3_2_1_4_1","volume-title":"Optimizing feedforward artificial neural network architecture. Engineering applications of artificial intelligence 20, 3","author":"Benardos PG","year":"2007","unstructured":"PG Benardos and G-C Vosniakos. 2007. Optimizing feedforward artificial neural network architecture. Engineering applications of artificial intelligence 20, 3 (2007), 365--382."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.2c11420"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Jonathan Carter John Feddema Doug Kothe Rob Neely Jason Pruet Rick Stevens Prasanna Balaprakash et al. 2023. Advanced Research Directions on AI for Science Energy and Security: Report on Summer 2022 Workshops.","DOI":"10.2172\/1986455"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392683"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00038"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_10_1","volume-title":"Clipper: A Low-Latency Online Prediction Serving System. In 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). USENIX Association, 613--627."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3586589.3586709"},{"key":"e_1_3_2_1_12_1","volume-title":"https:\/\/thegardens.ai\/. Accessed","author":"Team Garden","year":"2023","unstructured":"Garden Team. 2023. Garden. https:\/\/thegardens.ai\/. Accessed October 2023."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Mor Geva Jasmijn Bastings Katja Filippova and Amir Globerson. 2023. Dissecting recall of factual associations in auto-regressive language models.","DOI":"10.18653\/v1\/2023.emnlp-main.751"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.7b00572"},{"key":"e_1_3_2_1_15_1","volume-title":"https:\/\/bard.google.com. Accessed","year":"2023","unstructured":"Google. 2023. Bard. https:\/\/bard.google.com. Accessed October 2023."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375395.3387641"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1021\/ja01062a035"},{"key":"e_1_3_2_1_18_1","volume-title":"Why Meta's latest large language model survived only three days online. https:\/\/www.technologyreview.com\/2022\/11\/18\/1063487\/. Accessed","author":"Heaven Will Douglas","year":"2023","unstructured":"Will Douglas Heaven. 2022. Why Meta's latest large language model survived only three days online. https:\/\/www.technologyreview.com\/2022\/11\/18\/1063487\/. Accessed October 2023.."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmolb.2021.636077"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN52240.2021.9522156"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPS.2019.2955098"},{"key":"e_1_3_2_1_23_1","volume-title":"Automated machine learning: methods, systems, challenges","author":"Hutter Frank","unstructured":"Frank Hutter, Lars Kotthoff, and Joaquin Vanschoren. 2019. Automated machine learning: methods, systems, challenges. Springer Nature."},{"key":"e_1_3_2_1_24_1","volume-title":"2016 3rd International conference on logistics operations management (GOL). IEEE Computer Society, 1--4.","author":"Janati Idrissi Mohammed Amine","year":"2016","unstructured":"Mohammed Amine Janati Idrissi, Hassan Ramchoun, Youssef Ghanou, and Mohamed Ettaouil. 2016. Genetic algorithm for neural network architecture optimization. In 2016 3rd International conference on logistics operations management (GOL). IEEE Computer Society, 1--4."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"John Jumper Richard Evans Alexander Pritzel Tim Green Michael Figurnov Olaf Ronneberger Kathryn Tunyasuvunakool et al. 2021. Highly accurate protein structure prediction with AlphaFold. Nature 596 7873 (01 Aug 2021) 583--589. 10.1038\/s41586-021-03819-2","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_1_27_1","unstructured":"Nikhil Kandpal Brian Lester Mohammed Muqeeth Anisha Mascarenhas Monty Evans Vishal Baskaran Tenghao Huang Haokun Liu and Colin Raffel. 2023. Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models."},{"key":"e_1_3_2_1_28_1","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling Laws for Neural Language Models. arXiv:2001.08361 [cs.LG]"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1021\/cr200066h"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the European conference on computer vision (ECCV). Springer, Cham, 19--34","author":"Liu Chenxi","year":"2018","unstructured":"Chenxi Liu, Barret Zoph, Maxim Neumann, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, et al. 2018. Progressive neural architecture search. In Proceedings of the European conference on computer vision (ECCV). Springer, Cham, 19--34."},{"key":"e_1_3_2_1_31_1","unstructured":"Qing Lu Weiwen Jiang Xiaowei Xu Yiyu Shi and Jingtong Hu. 2019. On neural architecture search for resource-constrained hardware platforms."},{"key":"e_1_3_2_1_32_1","unstructured":"Renqian Luo Fei Tian Tao Qin Enhong Chen and Tie-Yan Liu. 2018. Neural architecture optimization."},{"key":"e_1_3_2_1_33_1","first-page":"17359","article-title":"Locating and editing factual associations in GPT","volume":"35","author":"Meng Kevin","year":"2022","unstructured":"Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in GPT. Advances in Neural Information Processing Systems 35 (2022), 17359--17372.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2017.57"},{"key":"e_1_3_2_1_35_1","volume-title":"2017 IEEE 33rd International Conference on Data Engineering (ICDE). IEEE Computer Society, 571--582","author":"Miao Hui","year":"2017","unstructured":"Hui Miao, Ang Li, Larry S Davis, and Amol Deshpande. 2017. Towards unified data and lifecycle management for deep learning. In 2017 IEEE 33rd International Conference on Data Engineering (ICDE). IEEE Computer Society, 571--582."},{"key":"e_1_3_2_1_36_1","volume-title":"13th USENIX symposium on operating systems design and implementation (OSDI 18)","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, et al. 2018. Ray: A distributed framework for emerging AI applications. In 13th USENIX symposium on operating systems design and implementation (OSDI 18). USENIX Association, 561--577."},{"key":"e_1_3_2_1_37_1","unstructured":"Neel Nanda Lawrence Chan Tom Liberum Jess Smith and Jacob Steinhardt. 2023. Progress measures for grokking via mechanistic interpretability."},{"key":"e_1_3_2_1_38_1","volume-title":"graph2vec: Learning distributed representations of graphs. arXiv preprint arXiv:1707.05005","author":"Narayanan Annamalai","year":"2017","unstructured":"Annamalai Narayanan, Mahinthan Chandramohan, Rajasekar Venkatesan, Lihui Chen, Yang Liu, and Shantanu Jaiswal. 2017. graph2vec: Learning distributed representations of graphs. arXiv preprint arXiv:1707.05005 (2017)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_40_1","volume-title":"Logit Lens on Non-GPT2 Models + Extensions. https:\/\/colab.research.google.com\/drive\/1MjdfK2srcerLrAJDRaJQKO0sUiZ-hQtA. Accessed","year":"2023","unstructured":"nostalgebraist. 2021. Logit Lens on Non-GPT2 Models + Extensions. https:\/\/colab.research.google.com\/drive\/1MjdfK2srcerLrAJDRaJQKO0sUiZ-hQtA. Accessed October 2023."},{"key":"e_1_3_2_1_41_1","volume-title":"https:\/\/chat.openai.com. Accessed","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. ChatGPT. https:\/\/chat.openai.com. Accessed October 2023."},{"key":"e_1_3_2_1_43_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen et al. 2019. PyTorch: An Imperative Style High-Performance Deep Learning Library. arXiv:1912.01703 [cs.LG]"},{"key":"e_1_3_2_1_44_1","volume-title":"Pinecone Vector Database. https:\/\/pinecone.io. Accessed","year":"2023","unstructured":"Pinecone. 2023. Pinecone Vector Database. https:\/\/pinecone.io. Accessed October 2023."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-18008-4"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8821--8831. https:\/\/proceedings.mlr.press\/v139\/ramesh21a.html"},{"key":"e_1_3_2_1_48_1","first-page":"1","article-title":"A comprehensive survey of neural architecture search: Challenges and solutions","volume":"54","author":"Ren Pengzhen","year":"2021","unstructured":"Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Xiaojiang Chen, and Xin Wang. 2021. A comprehensive survey of neural architecture search: Challenges and solutions. Comput. Surveys 54, 4 (2021), 1--34.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_49_1","unstructured":"Xiaozhe Ren Pingyi Zhou Xinfan Meng Xinjing Huang Yadao Wang Weichao Wang Pengfei Li et al. 2023. PanGu-\u03a3: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing. arXiv:2303.10845 [cs.CL]"},{"key":"e_1_3_2_1_50_1","volume-title":"Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models. arXiv:2309.05605 [cs.CL]","author":"Sakarvadia Mansi","year":"2023","unstructured":"Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Daniel Grzenda, Nathaniel Hudson, Andr\u00e9 Bauer, Kyle Chard, and Ian Foster. 2023. Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models. arXiv:2309.05605 [cs.CL]"},{"key":"e_1_3_2_1_51_1","volume-title":"Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism. arXiv preprint arXiv:2310.16270","author":"Sakarvadia Mansi","year":"2023","unstructured":"Mansi Sakarvadia, Arham Khan, Aswathy Ajith, Daniel Grzenda, Nathaniel Hudson, Andr\u00e9 Bauer, Kyle Chard, and Ian Foster. 2023. Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism. arXiv preprint arXiv:2310.16270 (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","unstructured":"David Silver Aja Huang Chris J. Maddison Arthur Guez Laurent Sifre George van den Driessche Julian Schrittwieser et al. 2016. Mastering the game of Go with deep neural networks and tree search. Nature 529 7587 (01 Jan 2016) 484--489. 10.1038\/nature16961","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_1_53_1","volume-title":"Galactica: A Large Language Model for Science. arXiv:2211.09085 [cs.CL]","author":"Taylor Ross","year":"2022","unstructured":"Ross Taylor, Marcin Kardas, Guillem Cucurull, Thomas Scialom, Anthony Hartshorn, Elvis Saravia, Andrew Poulton, Viktor Kerkez, and Robert Stojnic. 2022. Galactica: A Large Language Model for Science. arXiv:2211.09085 [cs.CL]"},{"key":"e_1_3_2_1_54_1","volume-title":"https:\/\/www.kubeflow.org. Last accessed on","author":"Authors The Kubeflow","year":"2023","unstructured":"The Kubeflow Authors. 2018. Kubeflow. https:\/\/www.kubeflow.org. Last accessed on October 8, 2023."},{"key":"e_1_3_2_1_55_1","volume-title":"Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, et al.","author":"Thoppilan Romal","year":"2022","unstructured":"Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, et al. 2022. LaMDA: Language Models for Dialog Applications. arXiv:2201.08239 [cs.CL]"},{"key":"e_1_3_2_1_56_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_2_1_57_1","unstructured":"Kevin Wang Alexandre Variengien Arthur Conmy Buck Shlegeris and Jacob Steinhardt. 2022. Interpretability in the wild: a circuit for indirect object identification in GPT-2 small."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","unstructured":"Logan Ward J. Gregory Pauloski Valerie Hayot-Sasson Ryan Chard Yadu Babuji Ganesh Sivaraman et al. 2023. Cloud Services Enable Efficient AI-Guided Simulation Workflows across Heterogeneous Resources. 10.48550\/ARXIV.2303.08803","DOI":"10.48550\/ARXIV.2303.08803"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","unstructured":"Logan Ward Ganesh Sivaraman J. Gregory Pauloski Yadu Babuji Ryan Chard Naveen Dandu Paul C. Redfern et al. 2021. Colmena: Scalable Machine-Learning-Based Steering of Ensemble Simulations for High Performance Computing. In 2021 IEEE\/ACM Workshop on Machine Learning in High Performance Computing Environments (MLHPC). IEEE Press 9--20. 10.1109\/MLHPC54614.2021.00007","DOI":"10.1109\/MLHPC54614.2021.00007"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci025620t"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_62_1","first-page":"39","article-title":"Accelerating the machine learning lifecycle with MLflow","volume":"41","author":"Zaharia Matei","year":"2018","unstructured":"Matei Zaharia, Andrew Chen, Aaron Davidson, Ali Ghodsi, Sue Ann Hong, Andy Konwinski, Siddharth Murching, et al. 2018. Accelerating the machine learning lifecycle with MLflow. IEEE Data Eng. Bull. 41, 4 (2018), 39--45.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_1_63_1","volume-title":"2020 IEEE Globecom Workshops. IEEE, 1--6.","author":"Zhao Xiaobo","year":"2020","unstructured":"Xiaobo Zhao, Minoo Hosseinzadeh, Nathaniel Hudson, Hana Khamfroush, and Daniel E Lucani. 2020. Improving the accuracy-latency trade-off of edge-cloud computation offloading for deep learning services. In 2020 IEEE Globecom Workshops. IEEE, 1--6."},{"key":"e_1_3_2_1_64_1","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zheng Lianmin","year":"2022","unstructured":"Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, et al. 2022. Alpa: Automating inter-and Intra-Operator parallelism for distributed deep learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, 559--578."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1101\/2022.10.10.511571"}],"event":{"name":"BDCAT '23: IEEE\/ACM 10th International Conference on Big Data Computing, Applications and Technologies","location":"Taormina (Messina) Italy","acronym":"BDCAT '23","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE TCSC"]},"container-title":["Proceedings of the IEEE\/ACM 10th International Conference on Big Data Computing, Applications and Technologies"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632366.3632396","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3632366.3632396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:45:43Z","timestamp":1750178743000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3632366.3632396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":65,"alternative-id":["10.1145\/3632366.3632396","10.1145\/3632366"],"URL":"https:\/\/doi.org\/10.1145\/3632366.3632396","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]},"assertion":[{"value":"2024-04-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}