{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:09:01Z","timestamp":1755907741561,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":4,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"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":[[2025,2,27]]},"DOI":"10.1145\/3706628.3708849","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:22:11Z","timestamp":1740572531000},"page":"51-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["BAQET: BRAM-aware Quantization for Efficient Transformer Inference via Stream-based Architecture on an FPGA"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3064-6108","authenticated-orcid":false,"given":"Ling-Chi","family":"Yang","sequence":"first","affiliation":[{"name":"Institute of Electronics National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7991-920X","authenticated-orcid":false,"given":"Chi-Jui","family":"Chen","sequence":"additional","affiliation":[{"name":"Graduate Degree Program of College of Electrical and Computer Engineering in National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7047-8451","authenticated-orcid":false,"given":"Trung","family":"Le","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering in University of Washington, Seattle, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9729-5196","authenticated-orcid":false,"given":"Bo-Cheng","family":"Lai","sequence":"additional","affiliation":[{"name":"Institute of Electronics National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9516-0311","authenticated-orcid":false,"given":"Scott","family":"Hauck","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering University of Washington, Seattle, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6214-8500","authenticated-orcid":false,"given":"Shih-Chieh","family":"Hsu","sequence":"additional","affiliation":[{"name":"Physics University of Washington, Seattle, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Tri Dao. 2023. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. https:\/\/doi.org\/10.48550\/arXiv.2307.08691","DOI":"10.48550\/arXiv.2307.08691"},{"key":"e_1_3_2_1_2_1","unstructured":"Farah Fahim Benjamin Hawks Christian Herwig James Hirschauer Sergo Jindariani Nhan Tran Luca P. Carloni Giuseppe Di Guglielmo Philip Harris Jeffrey Krupa Dylan Rankin Manuel Blanco Valentin Josiah Hester Yingyi Luo John Mamish Seda Orgrenci-Memik Thea Aarrestad Hamza Javed Vladimir Loncar Maurizio Pierini Adrian Alan Pol Sioni Summers Javier Duarte Scott Hauck Shih-Chieh Hsu Jennifer Ngadiuba Mia Liu Duc Hoang Edward Kreinar and Zhenbin Wu. 2021. hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices. arXiv:2103.05579 [physics] (03 2021). https:\/\/arxiv.org\/abs\/2103.05579"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Zhixing Jiang Dennis Yin Yihui Chen Elham E Khoda Scott Hauck Shih-Chieh Hsu Ekaterina Govorkova Philip Harris Vladimir Loncar and Eric A Moreno. 2024. Low Latency Transformer Inference on FPGAs for Physics Applications with hls4ml. https:\/\/arxiv.org\/abs\/2409.05207","DOI":"10.1088\/1748-0221\/20\/04\/P04014"},{"key":"e_1_3_2_1_4_1","first-page":"17926","article-title":"Stndt: Modeling neural population activity with spatiotemporal transformers","volume":"35","author":"Le Trung","year":"2022","unstructured":"Trung Le and Eli Shlizerman. 2022. Stndt: Modeling neural population activity with spatiotemporal transformers. Advances in Neural Information Processing Systems, Vol. 35 (2022), 17926--17939.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"FPGA '25: The 2025 ACM\/SIGDA International Symposium on Field Programmable Gate Arrays","sponsor":["SIGDA ACM Special Interest Group on Design Automation"],"location":"Monterey CA USA","acronym":"FPGA '25"},"container-title":["Proceedings of the 2025 ACM\/SIGDA International Symposium on Field Programmable Gate Arrays"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706628.3708849","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706628.3708849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T21:54:11Z","timestamp":1755899651000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706628.3708849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":4,"alternative-id":["10.1145\/3706628.3708849","10.1145\/3706628"],"URL":"https:\/\/doi.org\/10.1145\/3706628.3708849","relation":{},"subject":[],"published":{"date-parts":[[2025,2,27]]},"assertion":[{"value":"2025-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}