{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T05:12:25Z","timestamp":1783746745891,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100017090","name":"Sony","doi-asserted-by":"publisher","award":["4300135854"],"award-info":[{"award-number":["4300135854"]}],"id":[{"id":"10.13039\/100017090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017090","name":"COGNISENSE","doi-asserted-by":"publisher","award":["AWD-004308-S11"],"award-info":[{"award-number":["AWD-004308-S11"]}],"id":[{"id":"10.13039\/100017090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,13]]},"DOI":"10.1145\/3806645.3807580","type":"proceedings-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:21:11Z","timestamp":1783743671000},"page":"139-151","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Accelerating Block Low-Rank Foundation Model Inference on Memory-Constrained GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9523-6152","authenticated-orcid":false,"given":"Pierre","family":"Abillama","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5610-0671","authenticated-orcid":false,"given":"Changwoo","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8855-9962","authenticated-orcid":false,"given":"Juechu","family":"Dong","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6744-7075","authenticated-orcid":false,"given":"David","family":"Blaauw","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2598-0458","authenticated-orcid":false,"given":"Dennis","family":"Sylvester","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6658-5502","authenticated-orcid":false,"given":"Hun-Seok","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"Nader Al\u00a0Awar Muhammad\u00a0Hannan Naeem James Almgren-Bell George Biros and Milos Gligoric. 2025. Dynamically Fusing Python HPC Kernels. Proc. ACM Softw. Eng. 2 ISSTA Article ISSTA082 (June 2025) 22\u00a0pages. 10.1145\/3728959","DOI":"10.1145\/3728959"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3180"},{"key":"e_1_3_3_2_4_2","unstructured":"Jeff Barr. 2019. Amazon EC2 Update \u2013 Inf1 Instances with AWS Inferentia Chips for High Performance Cost-Effective Inferencing. AWS News Blog. 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_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"e_1_3_3_2_6_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_7_2","doi-asserted-by":"crossref","unstructured":"Shuai Che Michael Boyer Jiayuan Meng David Tarjan Jeremy\u00a0W Sheaffer and Kevin Skadron. 2008. A performance study of general-purpose applications on graphics processors using CUDA. Journal of parallel and distributed computing 68 10 (2008) 1370\u20131380.","DOI":"10.1016\/j.jpdc.2008.05.014"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPDC.2014.29"},{"key":"e_1_3_3_2_9_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_10_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_11_2","unstructured":"Tri Dao. 2023. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. arxiv:https:\/\/arXiv.org\/abs\/2307.08691\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2307.08691"},{"key":"e_1_3_3_2_12_2","series-title":"Proceedings of Machine Learning Research","first-page":"4690","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Beidi Chen, Nimit\u00a0S Sohoni, Arjun Desai, Michael Poli, Jessica Grogan, Alexander Liu, Aniruddh Rao, Atri Rudra, and Christopher Re. 2022. Monarch: Expressive Structured Matrices for Efficient and Accurate Training. In Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0162), Kamalika Chaudhuri, Stefanie Jegelka, Le\u00a0Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 4690\u20134721. https:\/\/proceedings.mlr.press\/v162\/dao22a.html"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_2_14_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR) (2021)."},{"key":"e_1_3_3_2_15_2","volume-title":"International Conference on Learning Representations","author":"Fu Daniel\u00a0Y.","year":"2024","unstructured":"Daniel\u00a0Y. Fu, Hermann Kumbong, Eric Nguyen, and Christopher R\u00e9. 2024. FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_16_2","series-title":"Proceedings of Machine Learning Research","first-page":"20075","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","volume":"267","author":"Gonon Antoine","year":"2025","unstructured":"Antoine Gonon, L\u00e9on Zheng, Pascal Carrivain, and Tung\u00a0Quoc Le. 2025. Fast Inference with Kronecker-Sparse Matrices. In Proceedings of the 42nd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0267). PMLR, 20075\u201320102."},{"key":"e_1_3_3_2_17_2","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_2_18_2","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 574, 12\u00a0pages."},{"key":"e_1_3_3_2_19_2","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de\u00a0Las Casas Lisa\u00a0Anne Hendricks Johannes Welbl Aidan Clark et\u00a0al. 2022. Training compute-optimal large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.15556 (2022)."},{"key":"e_1_3_3_2_20_2","unstructured":"Minyoung Huh Hossein Mobahi Richard Zhang Brian Cheung Pulkit Agrawal and Phillip Isola. 2021. The low-rank simplicity bias in deep networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.10427 (2021)."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00807"},{"key":"e_1_3_3_2_22_2","unstructured":"Zhe Jia Marco Maggioni Benjamin Staiger and Daniele\u00a0P Scarpazza. 2018. Dissecting the NVIDIA volta GPU architecture via microbenchmarking. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1804.06826 (2018)."},{"key":"e_1_3_3_2_23_2","unstructured":"Juyong Jiang Fan Wang Jiasi Shen Sungju Kim and Sunghun Kim. 2024. A survey on large language models for code generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.00515 (2024)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.619"},{"key":"e_1_3_3_2_25_2","series-title":"Proceedings of Machine Learning Research","first-page":"1009","volume-title":"Proceedings of The 27th International Conference on Artificial Intelligence and Statistics","volume":"238","author":"Kwon Soo\u00a0Min","year":"2024","unstructured":"Soo\u00a0Min Kwon, Zekai Zhang, Dogyoon Song, Laura Balzano, and Qing Qu. 2024. Efficient Low-Dimensional Compression of Overparameterized Models. In Proceedings of The 27th International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol.\u00a0238), Sanjoy Dasgupta, Stephan Mandt, and Yingzhen Li (Eds.). PMLR, 1009\u20131017. https:\/\/proceedings.mlr.press\/v238\/min-kwon24a.html"},{"key":"e_1_3_3_2_26_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lee Changwoo","year":"2024","unstructured":"Changwoo Lee and Hun-Seok Kim. 2024. Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=pAVJKp3Dvn"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0479"},{"key":"e_1_3_3_2_28_2","unstructured":"George Leopold. 2019. AWS Upgrades its GPU-Backed AI Inference Platform. HPCwire (2019). https:\/\/www.hpcwire.com\/2019\/03\/19\/aws-upgrades-its-gpu-backed-ai-inference-platform\/."},{"key":"e_1_3_3_2_29_2","unstructured":"Jianling Li Shangzhan Li Zhenye Gao Qi Shi Yuxuan Li Zefan Wang Jiacheng Huang Haojie Wang Jianrong Wang Xu Han Zhiyuan Liu and Maosong Sun. 2025. TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators. arxiv:https:\/\/arXiv.org\/abs\/2502.14752\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2502.14752"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"e_1_3_3_2_31_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu Zechun","year":"2025","unstructured":"Zechun Liu, Changsheng Zhao, Igor Fedorov, Bilge Soran, Dhruv Choudhary, Raghuraman Krishnamoorthi, Vikas Chandra, Yuandong Tian, and Tijmen Blankevoort. 2025. SpinQuant: LLM Quantization with Learned Rotations. In International Conference on Learning Representations (ICLR). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.16406."},{"key":"e_1_3_3_2_32_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_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_3_2_34_2","unstructured":"NVIDIA. 2022. NVIDIA A40 Data Center GPU."},{"key":"e_1_3_3_2_35_2","unstructured":"NVIDIA. 2024. Jetson Orin Nano Developer Kit."},{"key":"e_1_3_3_2_36_2","unstructured":"William Peebles and Saining Xie. 2022. Scalable Diffusion Models with Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.09748 (2022)."},{"key":"e_1_3_3_2_37_2","series-title":"(ICML\u201924)","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Qiu Shikai","year":"2024","unstructured":"Shikai Qiu, Andres Potapczynski, Marc Finzi, Micah Goldblum, and Andrew\u00a0Gordon Wilson. 2024. Compute better spent: replacing dense layers with structured matrices. In Proceedings of the 41st International Conference on Machine Learning (Vienna, Austria) (ICML\u201924). JMLR.org, Article 1695, 19\u00a0pages."},{"key":"e_1_3_3_2_38_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. OpenAI Blog 1 8 (2019) 9."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345220"},{"key":"e_1_3_3_2_40_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_41_2","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2019. Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1909.08053 (2019)."},{"key":"e_1_3_3_2_42_2","unstructured":"Daria Soboleva Faisal Al-Khateeb Robert Myers Jacob\u00a0R Steeves Joel Hestness and Nolan Dey. 2023. SlimPajama: A 627B token cleaned and deduplicated version of RedPajama. https:\/\/cerebras.ai\/blog\/slimpajama-a-627b-token-cleaned-and-deduplicated-version-of-redpajama. https:\/\/huggingface.co\/datasets\/cerebras\/SlimPajama-627B"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Wei Sun Ang Li Sander Stuijk and Henk Corporaal. 2024. How Much Can We Gain From Tensor Kernel Fusion on GPUs? IEEE Access 12 (2024) 126135\u2013126144. 10.1109\/ACCESS.2024.3411473","DOI":"10.1109\/ACCESS.2024.3411473"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_3_2_45_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023)."},{"key":"e_1_3_3_2_46_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Wang Xin","year":"2025","unstructured":"Xin Wang, Yu Zheng, Zhongwei Wan, and Mi Zhang. 2025. SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression. In International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=LNYIUouhdt"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Samuel Williams Andrew Waterman and David Patterson. 2009. Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52 4 (2009) 65\u201376. 10.1145\/1498765.1498785","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC.2018.00005"},{"key":"e_1_3_3_2_49_2","unstructured":"Can Yaras Peng Wang Wei Hu Zhihui Zhu Laura Balzano and Qing Qu. 2023. The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.01154 (2023)."},{"key":"e_1_3_3_2_50_2","unstructured":"Zhihang Yuan Yuzhang Shang Yang Zhou Zhen Dong Zhe Zhou Chenhao Xue Bingzhe Wu Zhikai Li Qingyi Gu Yong\u00a0Jae Lee Yan Yan Beidi Chen Guangyu Sun and Kurt Keutzer. 2024. LLM Inference Unveiled: Survey and Roofline Model Insights. arxiv:https:\/\/arXiv.org\/abs\/2402.16363\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2402.16363"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Zhihang Yuan Hanling Zhang Lu Pu Xuefei Ning Linfeng Zhang Tianchen Zhao Shengen Yan Guohao Dai and Yu Wang. 2024. Ditfastattn: Attention compression for diffusion transformer models. Advances in Neural Information Processing Systems 37 (2024) 1196\u20131219.","DOI":"10.52202\/079017-0037"},{"key":"e_1_3_3_2_52_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_53_2","doi-asserted-by":"crossref","unstructured":"Keren Zhou Mario Lezcano Adam Goucher Akhmed Rakhmati Jeff Niu Justin Lebar Pawel Szczerbuk Peter Bell Phil Tillet Thomas Raoux et\u00a0al. 2025. Linear Layouts: Robust Code Generation of Efficient Tensor Computation Using \\(\\mathbb {F}_2\\). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.23819 (2025).","DOI":"10.1145\/3760250.3762221"}],"event":{"name":"HPDC '26: 35th International Symposium on High-Performance Parallel and Distributed Computing","location":"Cleveland USA","acronym":"HPDC '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 35th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:24:39Z","timestamp":1783743879000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3806645.3807580"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":52,"alternative-id":["10.1145\/3806645.3807580","10.1145\/3806645"],"URL":"https:\/\/doi.org\/10.1145\/3806645.3807580","relation":{},"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"2026-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}