{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:50:19Z","timestamp":1782996619093,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":93,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC02-06CH11357; DE-SC0024559"],"award-info":[{"award-number":["DE-AC02-06CH11357; DE-SC0024559"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2540175, 2544839, and 2546265"],"award-info":[{"award-number":["2540175, 2544839, and 2546265"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3800513","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"972-985","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Not All Errors Are Equal: A Systematic Study of Error Propagation in Large Language Model Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7370-6766","authenticated-orcid":false,"given":"Yafan","family":"Huang","sequence":"first","affiliation":[{"name":"University of Iowa, Iowa City, Iowa, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9935-5674","authenticated-orcid":false,"given":"Sheng","family":"Di","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, Illinois, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7773-7826","authenticated-orcid":false,"given":"Guanpeng","family":"Li","sequence":"additional","affiliation":[{"name":"University of Florida, Gainesville, Florida, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Marah Abdin Sam\u00a0Ade Jacobs Ammar\u00a0Ahmad Awan Jyoti Aneja Ahmed Awadallah Hany\u00a0Hassan Awadalla Nguyen Bach Amit Bahree Arash Bakhtiari Harkirat\u00a0Singh Behl Alon Benhaim Misha Bilenko Johan Bjorck S\u00e9bastien Bubeck Martin Cai Caio C\u2019esar\u00a0Teodoro Mendes Weizhu Chen Vishrav Chaudhary Parul Chopra Allison\u00a0Del Giorno Gustavo de Rosa Matthew Dixon Ronen Eldan Dan Iter Abhishek Goswami Suriya Gunasekar Emman Haider Junheng Hao Russell\u00a0J. Hewett Jamie Huynh Mojan Javaheripi Xin Jin Piero Kauffmann Nikos Karampatziakis Dongwoo Kim Young\u00a0Jin Kim Mahoud Khademi Lev Kurilenko James\u00a0R. Lee Yin\u00a0Tat Lee Yuanzhi Li Chen Liang Weishung Liu Eric Lin Zeqi Lin Piyush Madan Arindam Mitra Hardik Modi Anh Nguyen Brandon Norick Barun Patra Daniel Perez-Becker Thomas Portet Reid Pryzant Heyang Qin Marko Radmilac Liliang Ren Corby Rosset Sambudha Roy Olli Saarikivi Amin Saied Adil Salim Michael Santacroce Shital Shah Ning Shang Hiteshi Sharma Xianmin Song Olatunji Ruwase Praneetha Vaddamanu Xin Wang Rachel Ward Guanhua Wang Philipp\u00a0Andre Witte Michael Wyatt Can Xu Jiahang Xu Sonali Yadav Fan Yang Ziyi Yang Donghan Yu Cheng-Yuan Zhang Cyril Zhang Jianwen Zhang Li\u00a0Lyna Zhang Yi Zhang Yunan Zhang Xiren Zhou and Yifan Yang. 2024. Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone. ArXiv abs\/2404.14219 (2024). https:\/\/api.semanticscholar.org\/CorpusID:269293048"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00052"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476153"},{"key":"e_1_3_3_2_5_2","unstructured":"et\u00a0al Albert Q\u00a0Jiang. 2023. Mistral 7B. https:\/\/arxiv.org\/abs\/2310.06825 (2023)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00092"},{"key":"e_1_3_3_2_7_2","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le et\u00a0al. 2021. Program synthesis with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.07732 (2021)."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00021"},{"key":"e_1_3_3_2_9_2","unstructured":"Xiao Bi Deli Chen Guanting Chen Shanhuang Chen Damai Dai Chengqi Deng Honghui Ding Kai Dong Qiushi Du Zhe Fu et\u00a0al. 2024. Deepseek llm: Scaling open-source language models with longtermism. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.02954 (2024)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"e_1_3_3_2_11_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00013"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.15"},{"key":"e_1_3_3_2_14_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde De\u00a0Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et\u00a0al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.03374 (2021)."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Zizhong Chen. 2013. Online-ABFT: An online algorithm based fault tolerance scheme for soft error detection in iterative methods. ACM SIGPLAN Notices 48 8 (2013) 167\u2013176.","DOI":"10.1145\/2517327.2442533"},{"key":"e_1_3_3_2_16_2","unstructured":"Christopher Clark Kenton Lee Ming-Wei Chang Tom Kwiatkowski Michael Collins and Kristina Toutanova. 2019. Boolq: Exploring the surprising difficulty of natural yes\/no questions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1905.10044 (2019)."},{"key":"e_1_3_3_2_17_2","unstructured":"Peter Clark Isaac Cowhey Oren Etzioni Tushar Khot Ashish Sabharwal Carissa Schoenick and Oyvind Tafjord. 2018. Think you have solved question answering? try arc the ai2 reasoning challenge. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1803.05457 (2018)."},{"key":"e_1_3_3_2_18_2","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et\u00a0al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.14168 (2021)."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759853"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624172"},{"key":"e_1_3_3_2_21_2","unstructured":"Harish\u00a0Dattatraya Dixit Sneha Pendharkar Matt Beadon Chris Mason Tejasvi Chakravarthy Bharath Muthiah and Sriram Sankar. 2021. Silent data corruptions at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2102.11245 (2021)."},{"key":"e_1_3_3_2_22_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The llama 3 herd of models. arXiv e-prints (2024) arXiv\u20132407."},{"key":"e_1_3_3_2_23_2","unstructured":"Ege Erdil. 2025. Inference economics of language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.04645 (2025)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2016.24"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Siyuan Feng Jiawei Liu Ruihang Lai Charlie Ruan Yong Yu Lingming Zhang and Tianqi Chen. 2025. Productively Deploying Emerging Models on Emerging Platforms: A Top-Down Approach for Testing and Debugging. Proceedings of the ACM on Software Engineering 2 ISSTA (2025) 1818\u20131840.","DOI":"10.1145\/3728957"},{"key":"e_1_3_3_2_26_2","unstructured":"Elias Frantar Saleh Ashkboos Torsten Hoefler and Dan Alistarh. 2022. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.17323 (2022)."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607078"},{"key":"e_1_3_3_2_28_2","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.03300 (2020)."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458336.3465297"},{"key":"e_1_3_3_2_30_2","unstructured":"Ke Hong Guohao Dai Jiaming Xu Qiuli Mao Xiuhong Li Jun Liu Kangdi Chen Yuhan Dong and Yu Wang. 2024. Flashdecoding++: Faster large language model inference with asynchronization flat gemm optimization and heuristics. Proceedings of Machine Learning and Systems 6 (2024) 148\u2013161."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Kuang-Hua Huang and Jacob\u00a0A Abraham. 1984. Algorithm-based fault tolerance for matrix operations. IEEE transactions on computers 100 6 (1984) 518\u2013528.","DOI":"10.1109\/TC.1984.1676475"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607048"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00061"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571907"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00043"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715996"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854059"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00022"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126964"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.20"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2018.00016"},{"key":"e_1_3_3_2_42_2","unstructured":"Haobo Li Zhaowei Wang Jiachen Wang YueYa Wang Alexis Kai\u00a0Hon Lau and Huamin Qu. 2024. CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.19058 (2024)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710870"},{"key":"e_1_3_3_2_44_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lightman Hunter","year":"2023","unstructured":"Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. Let\u2019s verify step by step. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_45_2","unstructured":"Stephanie Lin Jacob Hilton and Owain Evans. 2021. Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2109.07958 (2021)."},{"key":"e_1_3_3_2_46_2","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et\u00a0al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.19437 (2024)."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672274"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Zichang Liu Aditya Desai Fangshuo Liao Weitao Wang Victor Xie Zhaozhuo Xu Anastasios Kyrillidis and Anshumali Shrivastava. 2023. Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time. Advances in Neural Information Processing Systems 36 (2023) 52342\u201352364.","DOI":"10.52202\/075280-2279"},{"key":"e_1_3_3_2_49_2","unstructured":"Robert Lucas James Ang Keren Bergman Shekhar Borkar William Carlson Laura Carrington George Chiu Robert Colwell William Dally Jack Dongarra et\u00a0al. 2014. Top ten exascale research challenges. DOE ASCAC subcommittee report (2014) 1\u201386."},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-W50199.2020.00014"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00070"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Todor Mihaylov Peter Clark Tushar Khot and Ashish Sabharwal. 2018. Can a suit of armor conduct electricity? a new dataset for open book question answering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1809.02789 (2018).","DOI":"10.18653\/v1\/D18-1260"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2003.1253181"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3625549.3658689"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2024.10528929"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446091"},{"key":"e_1_3_3_2_57_2","unstructured":"et\u00a0al Nishant\u00a0George. 2023. Silent Data Corruption in AI. https:\/\/www.opencompute.org\/documents\/sdc-in-ai-ocp-whitepaper-final-pdf (2023)."},{"key":"e_1_3_3_2_58_2","unstructured":"NVIDIA. 2024. NVIDIA LLM Benchmarking. https:\/\/docs.nvidia.com\/nim\/benchmarking\/llm\/latest\/metrics.html (2024)."},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00075"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00032"},{"key":"e_1_3_3_2_61_2","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et\u00a0al. 2019. Pytorch: An imperative style high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_3_2_63_2","unstructured":"Max Peeperkorn Tom Kouwenhoven Dan Brown and Anna Jordanous. 2024. Is temperature the creativity parameter of large language models? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.00492 (2024)."},{"key":"e_1_3_3_2_64_2","unstructured":"Edoardo\u00a0Maria Ponti Goran Glava\u0161 Olga Majewska Qianchu Liu Ivan Vuli\u0107 and Anna Korhonen. 2020. XCOPA: A multilingual dataset for causal commonsense reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.00333 (2020)."},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707256"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476147"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759841"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"crossref","unstructured":"Shauli Ravfogel Yoav Goldberg and Jacob Goldberger. 2023. Conformal nucleus sampling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.02633 (2023).","DOI":"10.18653\/v1\/2023.findings-acl.3"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"crossref","unstructured":"Keisuke Sakaguchi Ronan\u00a0Le Bras Chandra Bhagavatula and Yejin Choi. 2021. Winogrande: An adversarial winograd schema challenge at scale. Commun. ACM 64 9 (2021) 99\u2013106.","DOI":"10.1145\/3474381"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532384"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2009.4798243"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716025"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759803"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3731545.3731570"},{"key":"e_1_3_3_2_75_2","unstructured":"Gemma Team Thomas Mesnard Cassidy Hardin Robert Dadashi Surya Bhupatiraju Shreya Pathak Laurent Sifre Morgane Rivi\u00e8re Mihir\u00a0Sanjay Kale Juliette Love et\u00a0al. 2024. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.08295 (2024)."},{"key":"e_1_3_3_2_76_2","unstructured":"Qwen Team. 2024. Qwen2 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.10671 2 (2024)."},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"crossref","unstructured":"Vasileios Titopoulos Kosmas Alexandridis and Giorgos Dimitrakopoulos. 2025. Custom Algorithm-based Fault Tolerance for Attention Layers in Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.16676 (2025).","DOI":"10.1109\/SOCC66126.2025.11235399"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056044"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN48987.2021.00041"},{"key":"e_1_3_3_2_80_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_81_2","unstructured":"Yang Wang and Hassan\u00a0A Karimi. 2024. Exploring large language models for climate forecasting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.13724 (2024)."},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2014.2"},{"key":"e_1_3_3_2_83_2","unstructured":"Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz et\u00a0al. 2019. Huggingface\u2019s transformers: State-of-the-art natural language processing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1910.03771 (2019)."},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00114"},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"crossref","unstructured":"Lishan Yang Bin Nie Adwait Jog and Evgenia Smirni. 2021. Sugar: Speeding up gpgpu application resilience estimation with input sizing. Proceedings of the ACM on Measurement and Analysis of Computing Systems 5 1 (2021) 1\u201329.","DOI":"10.1145\/3447375"},{"key":"e_1_3_3_2_86_2","first-page":"523","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Yao Zhiyi","year":"2025","unstructured":"Zhiyi Yao, Pengbo Hu, Congcong Miao, Xuya Jia, Zuning Liang, Yuedong Xu, Chunzhi He, Hao Lu, Mingzhuo Chen, Xiang Li, et\u00a0al. 2025. Holmes: Localizing irregularities in { LLM} training with mega-scale { GPU} clusters. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). 523\u2013540."},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"crossref","unstructured":"Junqi Yin Jesse Hines Emily Herron Tirthankar Ghosal Hong Liu Suzanne Prentice Vanessa Lama and Feiyi Wang. 2024. chathpc: Empowering hpc users with large language models. Journal of Supercomputing 81 1 (2024).","DOI":"10.1007\/s11227-024-06637-1"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759893"},{"key":"e_1_3_3_2_89_2","unstructured":"Jiayi Yuan Hao Li Xinheng Ding Wenya Xie Yu-Jhe Li Wentian Zhao Kun Wan Jing Shi Xia Hu and Zirui Liu. [n. d.]. Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference. ([n. d.])."},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"crossref","unstructured":"Rowan Zellers Ari Holtzman Yonatan Bisk Ali Farhadi and Yejin Choi. 2019. Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1905.07830 (2019).","DOI":"10.18653\/v1\/P19-1472"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656605"},{"key":"e_1_3_3_2_92_2","unstructured":"Jiawei Zhao Zhenyu Zhang Beidi Chen Zhangyang Wang Anima Anandkumar and Yuandong Tian. 2024. Galore: Memory-efficient llm training by gradient low-rank projection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.03507 (2024)."},{"key":"e_1_3_3_2_93_2","unstructured":"Kai Zhao Sheng Di Sihuan Li Xin Liang Yujia Zhai Jieyang Chen Kaiming Ouyang Franck Cappello and Zizhong Chen. 2020. FT-CNN: Algorithm-based fault tolerance for convolutional neural networks. IEEE Transactions on Parallel and Distributed Systems 32 7 (2020) 1677\u20131689."},{"key":"e_1_3_3_2_94_2","first-page":"193","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong Yinmin","year":"2024","unstructured":"Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, and Hao Zhang. 2024. { DistServe} : Disaggregating prefill and decoding for goodput-optimized large language model serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 193\u2013210."}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3797905.3800513","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:34:53Z","timestamp":1782995693000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3800513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":93,"alternative-id":["10.1145\/3797905.3800513","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3800513","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}