{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:38:28Z","timestamp":1785605908491,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1145\/3630106.3658542","type":"proceedings-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T09:14:21Z","timestamp":1717578861000},"page":"85-99","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":275,"title":["Power Hungry Processing: Watts Driving the Cost of AI Deployment?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6238-7050","authenticated-orcid":false,"given":"Sasha","family":"Luccioni","sequence":"first","affiliation":[{"name":"Hugging Face, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8053-6862","authenticated-orcid":false,"given":"Yacine","family":"Jernite","sequence":"additional","affiliation":[{"name":"Hugging Face, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2798-0726","authenticated-orcid":false,"given":"Emma","family":"Strubell","sequence":"additional","affiliation":[{"name":"Carnegie Mellon, Allen AI Institute, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,5]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sustainlp-1.2"},{"key":"e_1_3_2_2_2_1","unstructured":"Jeff Barr. 2019. Amazon ec2 update\u2013inf1 instances with AWS inferentia chips for high performance cost-effective inferencing. https:\/\/aws.amazon.com\/blogs\/aws\/amazon-ec2-update-inf1-instances-with-aws-inferentia-chips-for-high-performance-cost-effective-inferencing\/"},{"key":"e_1_3_2_2_3_1","unstructured":"Bing. 2019. Bing delivers its largest improvement in search experience using Azure GPUs. https:\/\/azure.microsoft.com\/en-us\/blog\/bing-delivers-its-largest-improvement-in-search-experience-using-azure-gpus\/"},{"key":"e_1_3_2_2_4_1","unstructured":"Bing. 2023. Confirmed: the new Bing runs on OpenAI\u2019s GPT-4. https:\/\/blogs.bing.com\/search\/march_2023\/Confirmed-the-new-Bing-runs-on-OpenAI%E2%80%99s-GPT-4"},{"key":"e_1_3_2_2_5_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604930.3605705"},{"key":"e_1_3_2_2_7_1","volume-title":"Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung\u00a0Won Chung, Charles Sutton, Sebastian Gehrmann, 2022. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","unstructured":"Hyung\u00a0Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang\u00a0Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Sharan Narang Gaurav Mishra Adams Yu Vincent Zhao Yanping Huang Andrew Dai Hongkun Yu Slav Petrov Ed\u00a0H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc\u00a0V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. https:\/\/doi.org\/10.48550\/ARXIV.2210.11416","DOI":"10.48550\/ARXIV.2210.11416"},{"key":"e_1_3_2_2_9_1","unstructured":"Rishit Dagli and Ali\u00a0Mustufa Shaikh. 2021. CPPE-5: Medical Personal Protective Equipment Dataset. arxiv:2112.09569\u00a0[cs.CV]"},{"key":"e_1_3_2_2_10_1","unstructured":"Karan Desai Gaurav Kaul Zubin Aysola and Justin Johnson. 2021. RedCaps: web-curated image-text data created by the people for the people. arxiv:2111.11431\u00a0[cs.CV]"},{"key":"e_1_3_2_2_11_1","volume-title":"Compute and energy consumption trends in deep learning inference. arXiv preprint arXiv:2109.05472","author":"Desislavov Radosvet","year":"2021","unstructured":"Radosvet Desislavov, Fernando Mart\u00ednez-Plumed, and Jos\u00e9 Hern\u00e1ndez-Orallo. 2021. Compute and energy consumption trends in deep learning inference. arXiv preprint arXiv:2109.05472 (2021)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533234"},{"key":"e_1_3_2_2_13_1","volume-title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models. arXiv preprint arXiv:2309.14393","author":"Faiz Ahmad","year":"2023","unstructured":"Ahmad Faiz, Sotaro Kaneda, Ruhan Wang, Rita Osi, Parteek Sharma, Fan Chen, and Lei Jiang. 2023. LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models. arXiv preprint arXiv:2309.14393 (2023)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","unstructured":"Leo Gao Jonathan Tow Stella Biderman Sid Black Anthony DiPofi Charles Foster Laurence Golding Jeffrey Hsu Kyle McDonell Niklas Muennighoff Jason Phang Laria Reynolds Eric Tang Anish Thite Ben Wang Kevin Wang and Andy Zou. 2021. A framework for few-shot language model evaluation. https:\/\/doi.org\/10.5281\/zenodo.5371628","DOI":"10.5281\/zenodo.5371628"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5409"},{"key":"e_1_3_2_2_16_1","unstructured":"Google. 2019. Understanding searches better than ever before. https:\/\/blog.google\/products\/search\/search-language-understanding-bert\/"},{"key":"e_1_3_2_2_17_1","unstructured":"Google. 2023. Bard can now connect to your Google apps and services. https:\/\/blog.google\/products\/bard\/google-bard-new-features-update-sept-2023\/"},{"key":"e_1_3_2_2_18_1","unstructured":"Google. 2023. An important next step on our AI journey. https:\/\/blog.google\/technology\/ai\/bard-google-ai-search-updates\/"},{"key":"e_1_3_2_2_19_1","volume-title":"CarbonScaler: Leveraging Cloud Workload Elasticity for Optimizing Carbon-Efficiency. arXiv preprint arXiv:2302.08681","author":"Hanafy A","year":"2023","unstructured":"Walid\u00a0A Hanafy, Qianlin Liang, Noman Bashir, David Irwin, and Prashant Shenoy. 2023. CarbonScaler: Leveraging Cloud Workload Elasticity for Optimizing Carbon-Efficiency. arXiv preprint arXiv:2302.08681 (2023)."},{"key":"e_1_3_2_2_20_1","unstructured":"Karl\u00a0Moritz Hermann Tom\u00e1s Kocisk\u00fd Edward Grefenstette Lasse Espeholt Will Kay Mustafa Suleyman and Phil Blunsom. 2015. Teaching Machines to Read and Comprehend. In NeurIPS. 1693\u20131701. http:\/\/papers.nips.cc\/paper\/5945-teaching-machines-to-read-and-comprehend"},{"key":"e_1_3_2_2_21_1","volume-title":"Cloud computing drives the growth of the data center industry and its energy consumption. Data centers","author":"Hintemann Ralph","year":"2022","unstructured":"Ralph Hintemann and Simon Hinterholzer. 2022. Cloud computing drives the growth of the data center industry and its energy consumption. Data centers 2022. ResearchGate (2022)."},{"key":"e_1_3_2_2_22_1","unstructured":"International Energy Authority. 2023. Data Centres and Data Transmission Networks. https:\/\/www.iea.org\/energy-system\/buildings\/data-centres-and-data-transmission-networks"},{"key":"e_1_3_2_2_23_1","unstructured":"Matt\u00a0Gardner Johannes\u00a0Welbl Nelson F.\u00a0Liu. 2017. Crowdsourcing Multiple Choice Science Questions. arXiv:1707.06209v1."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_2_25_1","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Technical Report."},{"key":"e_1_3_2_2_26_1","volume-title":"Quantifying the carbon emissions of machine learning. arXiv preprint arXiv:1910.09700","author":"Lacoste Alexandre","year":"2019","unstructured":"Alexandre Lacoste, Alexandra Luccioni, Victor Schmidt, and Thomas Dandres. 2019. Quantifying the carbon emissions of machine learning. arXiv preprint arXiv:1910.09700 (2019)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.8"},{"key":"e_1_3_2_2_28_1","unstructured":"George Leopold. 2019. AWS to Offer NVIDIA\u2019s T4 GPUs for AI Inferencing. www.hpcwire.com\/2019\/03\/19\/aws-upgrades-its-gpu-backed-ai-inference-platform\/"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_30_1","volume-title":"Counting carbon: A survey of factors influencing the emissions of machine learning. arXiv preprint arXiv:2302.08476","author":"Luccioni Alexandra\u00a0Sasha","year":"2023","unstructured":"Alexandra\u00a0Sasha Luccioni and Alex Hernandez-Garcia. 2023. Counting carbon: A survey of factors influencing the emissions of machine learning. arXiv preprint arXiv:2302.08476 (2023)."},{"key":"e_1_3_2_2_31_1","volume-title":"Estimating the carbon footprint of BLOOM, a 176B parameter language model. arXiv preprint arXiv:2211.02001","author":"Luccioni Alexandra\u00a0Sasha","year":"2022","unstructured":"Alexandra\u00a0Sasha Luccioni, Sylvain Viguier, and Anne-Laure Ligozat. 2022. Estimating the carbon footprint of BLOOM, a 176B parameter language model. arXiv preprint arXiv:2211.02001 (2022)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_2_33_1","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer Sentinel Mixture Models. arxiv:1609.07843\u00a0[cs.CL]"},{"key":"e_1_3_2_2_34_1","volume-title":"Crosslingual generalization through multitask finetuning. arXiv preprint arXiv:2211.01786","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven\u00a0Le Scao, M\u00a0Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, 2022. Crosslingual generalization through multitask finetuning. arXiv preprint arXiv:2211.01786 (2022)."},{"key":"e_1_3_2_2_35_1","volume-title":"Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization. ArXiv abs\/1808.08745","author":"Narayan Shashi","year":"2018","unstructured":"Shashi Narayan, Shay\u00a0B. Cohen, and Mirella Lapata. 2018. Don\u2019t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization. ArXiv abs\/1808.08745 (2018)."},{"key":"e_1_3_2_2_36_1","volume-title":"AI chatbots lose money every time you use them. That is a problem. Washington Post","author":"Oremus Will","year":"2023","unstructured":"Will Oremus. 2023. AI chatbots lose money every time you use them. That is a problem. Washington Post (2023). https:\/\/www.washingtonpost.com\/technology\/2023\/06\/05\/chatgpt-hidden-cost-gpu-compute\/"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.14618\/ids-pub-9021"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1178"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219855"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","unstructured":"David Patterson Joseph Gonzalez Urs H\u00f6lzle Quoc Le Chen Liang Lluis-Miquel Munguia Daniel Rothchild David So Maud Texier and Jeff Dean. 2022. The Carbon Footprint of Machine Learning Training Will Plateau Then Shrink. https:\/\/doi.org\/10.48550\/ARXIV.2204.05149","DOI":"10.48550\/ARXIV.2204.05149"},{"key":"e_1_3_2_2_41_1","volume-title":"Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350","author":"Patterson David","year":"2021","unstructured":"David Patterson, Joseph Gonzalez, Quoc Le, Chen Liang, Lluis-Miquel Munguia, Daniel Rothchild, David So, Maud Texier, and Jeff Dean. 2021. Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350 (2021)."},{"key":"e_1_3_2_2_42_1","volume-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv e-prints","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter\u00a0J. Liu. 2019. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv e-prints (2019). arxiv:1910.10683"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Pranav Rajpurkar Robin Jia and Percy Liang. 2018. Know What You Don\u2019t Know: Unanswerable Questions for SQuAD. arxiv:1806.03822\u00a0[cs.CL]","DOI":"10.18653\/v1\/P18-2124"},{"key":"e_1_3_2_2_44_1","volume-title":"100,000+ Questions for Machine Comprehension of Text. arXiv:1606.05250","author":"Rajpurkar Pranav","year":"2016","unstructured":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ Questions for Machine Comprehension of Text. arXiv:1606.05250 (2016). arxiv:1606.05250"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_46_1","unstructured":"Gustavo Santana. 2023. Stable Diffusion Prompts. https:\/\/huggingface.co\/datasets\/Gustavosta\/Stable-Diffusion-Prompts"},{"key":"e_1_3_2_2_47_1","unstructured":"Victor Schmidt Kamal Goyal Aditya Joshi Boris Feld Liam Conell Nikolas Laskaris Doug Blank Jonathan Wilson Sorelle Friedler and Sasha Luccioni. 2021. CodeCarbon: Estimate and Track Carbon Emissions from Machine Learning Computing."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"e_1_3_2_2_49_1","volume-title":"Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243","author":"Strubell Emma","year":"2019","unstructured":"Emma Strubell, Ananya Ganesh, and Andrew McCallum. 2019. Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243 (2019)."},{"key":"e_1_3_2_2_50_1","first-page":"03","volume-title":"Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL","author":"F.","year":"2003","unstructured":"Erik\u00a0F. Tjong Kim\u00a0Sang and Fien De\u00a0Meulder. 2003. Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003. 142\u2013147. https:\/\/www.aclweb.org\/anthology\/W03-0419"},{"key":"e_1_3_2_2_51_1","unstructured":"US Environmental Protection Agencyy. 2024. Greenhouse Gases Equivalencies Calculator - Calculations and References. https:\/\/www.epa.gov\/energy\/greenhouse-gases-equivalencies-calculator-calculations-and-references"},{"key":"e_1_3_2_2_52_1","volume-title":"Better Best Practices for Data and Model Measurement. arXiv preprint arXiv:2210.01970","author":"Von\u00a0Werra Leandro","year":"2022","unstructured":"Leandro Von\u00a0Werra, Lewis Tunstall, Abhishek Thakur, Alexandra\u00a0Sasha Luccioni, Tristan Thrush, Aleksandra Piktus, Felix Marty, Nazneen Rajani, Victor Mustar, Helen Ngo, 2022. Evaluate & Evaluation on the Hub: Better Best Practices for Data and Model Measurement. arXiv preprint arXiv:2210.01970 (2022)."},{"key":"e_1_3_2_2_53_1","volume-title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems. arXiv preprint arXiv:1905.00537","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel\u00a0R Bowman. 2019. SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems. arXiv preprint arXiv:1905.00537 (2019)."},{"key":"e_1_3_2_2_54_1","volume-title":"DiffusionDB: A Large-Scale Prompt Gallery Dataset for Text-to-Image Generative Models. arXiv:2210.14896 [cs]","author":"Wang J.","year":"2022","unstructured":"Zijie\u00a0J. Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, and Duen\u00a0Horng Chau. 2022. DiffusionDB: A Large-Scale Prompt Gallery Dataset for Text-to-Image Generative Models. arXiv:2210.14896 [cs] (2022). https:\/\/arxiv.org\/abs\/2210.14896"},{"key":"e_1_3_2_2_55_1","volume-title":"Huggingface\u2019s transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771","author":"Wolf Thomas","year":"2019","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, 2019. Huggingface\u2019s transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)."},{"key":"e_1_3_2_2_56_1","volume-title":"Workshop, Teven\u00a0Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra\u00a0Sasha Luccioni","year":"2022","unstructured":"BigScience Workshop, Teven\u00a0Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra\u00a0Sasha Luccioni, Fran\u00e7ois Yvon, 2022. BLOOM: A 176B-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_2_57_1","volume-title":"Sustainable AI: Environmental Implications, Challenges and Opportunities. arXiv preprint arXiv:2111.00364","author":"Wu Carole-Jean","year":"2021","unstructured":"Carole-Jean Wu, Ramya Raghavendra, Udit Gupta, Bilge Acun, Newsha Ardalani, Kiwan Maeng, Gloria Chang, Fiona\u00a0Aga Behram, James Huang, Charles Bai, 2021. Sustainable AI: Environmental Implications, Challenges and Opportunities. arXiv preprint arXiv:2111.00364 (2021)."},{"key":"e_1_3_2_2_58_1","unstructured":"Jiazheng Xu Xiao Liu Yuchen Wu Yuxuan Tong Qinkai Li Ming Ding Jie Tang and Yuxiao Dong. 2023. ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation. arxiv:2304.05977\u00a0[cs.CV]"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"}],"event":{"name":"FAccT '24: The 2024 ACM Conference on Fairness, Accountability, and Transparency","location":"Rio de Janeiro Brazil","acronym":"FAccT '24"},"container-title":["The 2024 ACM Conference on Fairness Accountability and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658542","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3630106.3658542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:35:20Z","timestamp":1755884120000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":59,"alternative-id":["10.1145\/3630106.3658542","10.1145\/3630106"],"URL":"https:\/\/doi.org\/10.1145\/3630106.3658542","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-06-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}