{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:54:20Z","timestamp":1776930860623,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767395","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:18:44Z","timestamp":1762532324000},"page":"500-507","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enabling Unstructured Sparse Fine-Tuning and Inference for Foundation Models on Wafer-Scale Engine"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1319-6439","authenticated-orcid":false,"given":"Haoyu","family":"Zheng","sequence":"first","affiliation":[{"name":"Oregon State University, Corvallis, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3174-9255","authenticated-orcid":false,"given":"Yifan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7450-2842","authenticated-orcid":false,"given":"Linghao","family":"Song","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6279-0007","authenticated-orcid":false,"given":"Murali","family":"Emani","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Chicago, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8376-6647","authenticated-orcid":false,"given":"Wenqian","family":"Dong","sequence":"additional","affiliation":[{"name":"Oregon State University, Corvallis, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Yonatan Bisk Rowan Zellers Ronan\u00a0Le Bras Jianfeng Gao and Yejin Choi. 2019. PIQA: Reasoning about Physical Commonsense in Natural Language. arxiv:https:\/\/arXiv.org\/abs\/1911.11641\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1911.11641"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-69766-1_22"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1300"},{"key":"e_1_3_3_1_5_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 abs\/1803.05457 (2018). https:\/\/api.semanticscholar.org\/CorpusID:3922816"},{"key":"e_1_3_3_1_6_2","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arxiv:https:\/\/arXiv.org\/abs\/2110.14168\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_3_1_7_2","unstructured":"Elias Frantar and Dan Alistarh. 2023. SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.00774 (2023)."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Leo Gao Jonathan Tow Baber Abbasi Stella Biderman Sid Black Anthony DiPofi Charles Foster Laurence Golding Jeffrey Hsu Alain Le\u00a0Noac\u2019h Haonan Li Kyle McDonell Niklas Muennighoff Chris Ociepa Jason Phang Laria Reynolds Hailey Schoelkopf Aviya Skowron Lintang Sutawika Eric Tang Anish Thite Ben Wang Kevin Wang and Andy Zou. 2024. A framework for few-shot language model evaluation. 10.5281\/zenodo.12608602","DOI":"10.5281\/zenodo.12608602"},{"key":"e_1_3_3_1_9_2","series-title":"(NIPS\u201915)","first-page":"1135","volume-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems - Volume 1","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William\u00a0J. Dally. 2015. Learning both weights and connections for efficient neural networks. In Proceedings of the 29th International Conference on Neural Information Processing Systems - Volume 1 (Montreal, Canada) (NIPS\u201915). MIT Press, Cambridge, MA, USA, 1135\u20131143."},{"key":"e_1_3_3_1_10_2","unstructured":"Edward\u00a0J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2106.09685\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1136"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Sean Lie. 2023. Cerebras Architecture Deep Dive: First Look Inside the Hardware\/Software Co-Design for Deep Learning. IEEE Micro 43 3 (2023) 18\u201330. 10.1109\/MM.2023.3256384","DOI":"10.1109\/MM.2023.3256384"},{"key":"e_1_3_3_1_13_2","unstructured":"Alexandra\u00a0Sasha Luccioni Yacine Jernite and Victor Schmidt. 2023. What\u2019s the Carbon Footprint of ChatGPT? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.08476 (2023)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-industry.34"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.749"},{"key":"e_1_3_3_1_17_2","first-page":"10760","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Munoz Juan\u00a0Pablo","year":"2024","unstructured":"Juan\u00a0Pablo Munoz, Jinjie Yuan, Yi Zheng, and Nilesh Jain. 2024. LoNAS: Elastic Low-Rank Adapters for Efficient Large Language Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, Torino, Italia, 10760\u201310776. https:\/\/aclanthology.org\/2024.lrec-main.940\/"},{"key":"e_1_3_3_1_18_2","unstructured":"OpenAI. [n. d.]. https:\/\/openai.com\/index\/gpt-4-research\/ ."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Keisuke Sakaguchi Ronan\u00a0Le Bras Chandra Bhagavatula and Yejin Choi. 2021. WinoGrande: an adversarial winograd schema challenge at scale. Commun. ACM 64 9 (Aug. 2021) 99\u2013106. 10.1145\/3474381","DOI":"10.1145\/3474381"},{"key":"e_1_3_3_1_21_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Sun Mingjie","year":"2024","unstructured":"Mingjie Sun, Zhuang Liu, Anna Bair, and J\u00a0Zico Kolter. 2024. A Simple and Effective Pruning Approach for Large Language Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PxoFut3dWW"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895534"},{"key":"e_1_3_3_1_23_2","unstructured":"Rohan Taori Ishaan Gulrajani Tianyi Zhang Yann Dubois Xuechen Li Carlos Guestrin Percy Liang and Tatsunori\u00a0B. Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA Model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_3_1_24_2","series-title":"(UAI \u201923)","volume-title":"Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence","author":"Thangarasa Vithursan","year":"2023","unstructured":"Vithursan Thangarasa, Abhay Gupta, William Marshall, Tianda Li, Kevin Leong, Dennis DeCoste, Sean Lie, and Shreyas Saxena. 2023. SPDF: sparse pre-training and dense fine-tuning for large language models. In Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (Pittsburgh, PA, USA) (UAI \u201923). JMLR.org, Article 200, 13\u00a0pages."},{"key":"e_1_3_3_1_25_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_1_26_2","unstructured":"Rowan Zellers Ari Holtzman Yonatan Bisk Ali Farhadi and Yejin Choi. 2019. HellaSwag: Can a Machine Really Finish Your Sentence? arxiv:https:\/\/arXiv.org\/abs\/1905.07830\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1905.07830"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.178"},{"key":"e_1_3_3_1_28_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang Qingru","year":"2023","unstructured":"Qingru Zhang, Minshuo Chen, Alexander Bukharin, Pengcheng He, Yu Cheng, Weizhu Chen, and Tuo Zhao. 2023. Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=lq62uWRJjiY"}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:34:40Z","timestamp":1767987280000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767395"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":27,"alternative-id":["10.1145\/3731599.3767395","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767395","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}