{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T21:03:49Z","timestamp":1780434229974,"version":"3.54.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["JP24K02918"],"award-info":[{"award-number":["JP24K02918"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3696226","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:36:47Z","timestamp":1779478607000},"page":"78920-78930","source":"Crossref","is-referenced-by-count":0,"title":["Hardware-Friendly Fully Quantized Mamba-2 Model and Its FPGA-Based Accelerator"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0171-6679","authenticated-orcid":false,"given":"Hiroshi","family":"Fuketa","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5641-9252","authenticated-orcid":false,"given":"Masakazu","family":"Hioki","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2020.3034951"},{"key":"ref2","article-title":"BitNet: Scaling 1-bit transformers for large language models","author":"Wang","year":"2023","journal-title":"arXiv:2310.11453"},{"key":"ref3","article-title":"Keep the cost down: A review on methods to optimize LLM\u2019 s KV-cache consumption","author":"Shi","year":"2024","journal-title":"arXiv:2407.18003"},{"key":"ref4","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref5","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024","journal-title":"arXiv:2405.21060"},{"key":"ref6","first-page":"10411","article-title":"Quamba2: A robust and scalable post-training quantization framework for selective state space models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chiang"},{"key":"ref7","first-page":"33231","article-title":"MambaQuant: Quantizing the mamba family with variance aligned rotation methods","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref8","first-page":"4715","article-title":"Slender-Mamba: Fully quantized mamba in 1.58 bits from head to toe","volume-title":"Proc. Int. Conf. Comput. Linguistics (COLING)","author":"Yu"},{"key":"ref9","first-page":"1","article-title":"Bi-Mamba: Towards accurate 1-bit state space model","author":"Tang","year":"2025","journal-title":"Trans. Mach. Learn. Res. (TMLR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3290151"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3432979"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3581957"},{"key":"ref13","article-title":"NLI: Non-uniform linear interpolation approximation of nonlinear operations for efficient LLMs inference","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref14","first-page":"1","article-title":"Genetic quantization-aware approximation for non-linear operations in transformers","volume-title":"Proc. 61st ACM\/IEEE Design Autom. Conf.","author":"Dong"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD66269.2025.11240777"},{"key":"ref16","first-page":"5506","article-title":"I-BERT: Integer-only BERT quantization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kim"},{"key":"ref17","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref18","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Oord"},{"key":"ref19","article-title":"The FineWeb datasets: Decanting the web for the finest text data at scale","author":"Penedo","year":"2024","journal-title":"arXiv:2406.17557"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1472"},{"key":"ref24","article-title":"Think you have solved question answering? Try ARC, the AI2 reasoning challenge","author":"Clark","year":"2018","journal-title":"arXiv:1803.05457"},{"key":"ref25","volume-title":"Ultra96-V2 Product Brief (Datasheet)","year":"2026"},{"key":"ref26","article-title":"TeLLMe: An energy-efficient ternary LLM accelerator for prefilling and decoding on edge FPGAs","author":"Qiao","year":"2025","journal-title":"arXiv:2504.16266"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC66049.2026.11420289"},{"key":"ref28","volume-title":"UltraScale Architecture DSP Slice User Guide (UG579)","year":"2026"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT47387.2019.00029"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI65124.2025.11130250"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD66269.2025.11240811"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10993079"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD66269.2025.11241002"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/OJCAS.2022.3220499"},{"key":"ref35","volume-title":"Alveo U280 Data Center Accelerator Card Data Sheet (DS963)","year":"2026"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11534219.pdf?arnumber=11534219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:08:33Z","timestamp":1780430913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11534219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3696226","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}