{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:43:35Z","timestamp":1782999815583,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":47,"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":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3807877","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"1065-1075","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Three Birds, One Stone: Fast, Accurate-aware and Cost-Efficient Accelerator for Ternary LLM"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0478-4256","authenticated-orcid":false,"given":"Wonseok","family":"Jung","sequence":"first","affiliation":[{"name":"Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8471-4259","authenticated-orcid":false,"given":"Junseok","family":"Kang","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9488-6104","authenticated-orcid":false,"given":"Sangwon","family":"Shin","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2903-7157","authenticated-orcid":false,"given":"Hongjun","family":"Um","sequence":"additional","affiliation":[{"name":"Hanyang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2685-9847","authenticated-orcid":false,"given":"Jangho","family":"Lim","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3725-0380","authenticated-orcid":false,"given":"Yongjun","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1706-6850","authenticated-orcid":false,"given":"Gunjae","family":"Koo","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5831-2176","authenticated-orcid":false,"given":"Sangwoo","family":"Park","sequence":"additional","affiliation":[{"name":"Seoul Women's University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6377-5482","authenticated-orcid":false,"given":"Taeweon","family":"Suh","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218756"},{"key":"e_1_3_3_1_3_2","volume-title":"Alveo U280 FPGA Accelerator Card Datasheet","author":"Inc. Avnet,","year":"2019","unstructured":"Avnet, Inc.2019. Alveo U280 FPGA Accelerator Card Datasheet. https:\/\/www.avnet.com\/fsp\/opasdata\/d120001\/medias\/docus\/196\/XLX-A-U280-A32G-DEV-G-Datasheet.pdf Accessed: 2026."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228584"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Jerry Chee Yaohui Cai Volodymyr Kuleshov and Christopher\u00a0M De\u00a0Sa. 2023. Quip: 2-bit quantization of large language models with guarantees. Advances in Neural Information Processing Systems 36 (2023) 4396\u20134429.","DOI":"10.52202\/075280-0196"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.498"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.787"},{"key":"e_1_3_3_1_8_2","unstructured":"Steve Dai Rangha Venkatesan Mark Ren Brian Zimmer William Dally and Brucek Khailany. 2021. VS-Quant: Per-vector Scaled Quantization for Accurate Low-precision Neural Network Inference. Proceedings of Machine Learning and Systems 3 (2021) 873\u2013884."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589351"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Tim Dettmers Mike Lewis Younes Belkada and Luke Zettlemoyer. 2022. Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale. Advances in neural information processing systems 35 (2022) 30318\u201330332.","DOI":"10.52202\/068431-2198"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"e_1_3_3_1_12_2","volume-title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2023. GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. arxiv:https:\/\/arXiv.org\/abs\/2210.17323"},{"key":"e_1_3_3_1_13_2","unstructured":"Gemma Team Morgane Riviere Shreya Pathak Pier\u00a0Giuseppe Sessa Cassidy Hardin Surya Bhupatiraju L\u00e9onard Hussenot Thomas Mesnard Bobak Shahriari Alexandre Ram\u00e9 et\u00a0al. 2024. Gemma 2: Improving Open Language Models at a Practical Size. arxiv:https:\/\/arXiv.org\/abs\/2408.00118\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2408.00118"},{"key":"e_1_3_3_1_14_2","volume-title":"llama.cpp: Efficient LLaMA inference in C\/C++","author":"Gerganov Georgi","year":"2023","unstructured":"Georgi Gerganov et\u00a0al. 2023. llama.cpp: Efficient LLaMA inference in C\/C++. https:\/\/github.com\/ggml-org\/llama.cpp GitHub repository, accessed: 2025."},{"key":"e_1_3_3_1_15_2","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan Amy Yang et\u00a0al. 2024. The Llama 3 Herd of Models. arxiv:https:\/\/arXiv.org\/abs\/2407.21783\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Yufei Guo Zecheng Hao Jiahang Shao Jie Zhou Xiaode Liu Xin Tong Yuhan Zhang Yuanpei Chen Weihang Peng and Zhe Ma. 2025. PT-BitNet: Scaling up the 1-Bit Large Language Model with Post-Training Quantization. Neural Networks 191 (Nov. 2025). 10.1016\/j.neunet.2025.107855","DOI":"10.1016\/j.neunet.2025.107855"},{"key":"e_1_3_3_1_17_2","unstructured":"Hong Huang Decheng Wu Rui Cen Guanghua Yu Zonghang Li Kai Liu Jianchen Zhu Peng Chen Xue Liu and Dapeng Wu. 2025. Tequila: Trapping-free ternary quantization for large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.23809 (2025)."},{"key":"e_1_3_3_1_18_2","volume-title":"TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge","author":"Huang Zhirui","year":"2025","unstructured":"Zhirui Huang, Rui Ma, Shijie Cao, Ran Shu, Ian Wang, Ting Cao, Chixiao Chen, and Yongqiang Xiong. 2025. TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge. arxiv:https:\/\/arXiv.org\/abs\/2509.13765"},{"key":"e_1_3_3_1_19_2","volume-title":"Mistral 7B","author":"Jiang Albert\u00a0Q.","year":"2023","unstructured":"Albert\u00a0Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra\u00a0Singh Chaplot, Diego de\u00a0las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, L\u00e9lio Renard\u00a0Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le\u00a0Scao, Thibaut Lavril, Thomas Wang, Timoth\u00e9e Lacroix, and William El\u00a0Sayed. 2023. Mistral 7B. arxiv:https:\/\/arXiv.org\/abs\/2310.06825\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"e_1_3_3_1_20_2","volume-title":"Generic Standard Cell Library: Functional Specifications","author":"Lamant Gilles","year":"2002","unstructured":"Gilles Lamant. 2002. Generic Standard Cell Library: Functional Specifications. Cadence Design Systems, San Jose, CA. Revision 0.8."},{"key":"e_1_3_3_1_21_2","unstructured":"Ji Lin Jiaming Tang Haotian Tang Shang Yang Wei-Ming Chen Wei-Chen Wang Guangxuan Xiao Xingyu Dang Chuang Gan and Song Han. 2024. Awq: Activation-aware weight quantization for on-device llm compression and acceleration. Proceedings of machine learning and systems 6 (2024) 87\u2013100."},{"key":"e_1_3_3_1_22_2","volume-title":"Advances in Neural Information Processing Systems 38 (NeurIPS 2025)","author":"Liu Zechun","year":"2025","unstructured":"Zechun Liu, Changsheng Zhao, Hanxian Huang, Sijia Chen, Jing Zhang, Jiawei Zhao, Scott Roy, Lisa Jin, Yunyang Xiong, Yangyang Shi, Lin Xiao, Yuandong Tian, Bilge Soran, Raghuraman Krishnamoorthi, Tijmen Blankevoort, and Vikas Chandra. 2025. ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization. In Advances in Neural Information Processing Systems 38 (NeurIPS 2025). https:\/\/openreview.net\/forum?id=PMSNd8xTHp NeurIPS 2025 poster."},{"key":"e_1_3_3_1_23_2","volume-title":"BitNet b1.58 2B4T Technical Report","author":"Ma Shuming","year":"2025","unstructured":"Shuming Ma, Hongyu Wang, Shaohan Huang, Xingxing Zhang, Ying Hu, Ting Song, Yan Xia, and Furu Wei. 2025. BitNet b1.58 2B4T Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2504.12285"},{"key":"e_1_3_3_1_24_2","volume-title":"The Era of 1-bit LLMs: All Large Language Models Are in 1.58 Bits","author":"Ma Shuming","year":"2024","unstructured":"Shuming Ma, Hongyu Wang, Lingxiao Ma, Lei Wang, Wenhui Wang, Shaohan Huang, Li Dong, Ruiping Wang, Jilong Xue, and Furu Wei. 2024. The Era of 1-bit LLMs: All Large Language Models Are in 1.58 Bits. arxiv:https:\/\/arXiv.org\/abs\/2402.17764"},{"key":"e_1_3_3_1_25_2","volume-title":"Llama 3.2 1B","author":"AI Meta","year":"2024","unstructured":"Meta AI. 2024. Llama 3.2 1B. https:\/\/huggingface.co\/meta-llama\/Llama-3.2-1B Hugging Face model card, accessed: 2025."},{"key":"e_1_3_3_1_26_2","volume-title":"Llama 3.2 3B","author":"AI Meta","year":"2024","unstructured":"Meta AI. 2024. Llama 3.2 3B. https:\/\/huggingface.co\/meta-llama\/Llama-3.2-3B Hugging Face model card, accessed: 2025."},{"key":"e_1_3_3_1_27_2","volume-title":"microsoft\/BitNet: Official inference framework for 1-bit LLMs","year":"2025","unstructured":"Microsoft. 2025. microsoft\/BitNet: Official inference framework for 1-bit LLMs. https:\/\/github.com\/microsoft\/BitNet Accessed: 2025."},{"key":"e_1_3_3_1_28_2","unstructured":"Microsoft. 2026. MicroXcaling: PyTorch Emulation Library for Microscaling (MX)-Compatible Data Formats. https:\/\/github.com\/microsoft\/microxcaling. Accessed: 2026."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731057"},{"key":"e_1_3_3_1_30_2","first-page":"16318","volume-title":"International Conference on Machine Learning","author":"Nagel Markus","year":"2022","unstructured":"Markus Nagel, Marios Fournarakis, Yelysei Bondarenko, and Tijmen Blankevoort. 2022. Overcoming Oscillations in Quantization-Aware Training. In International Conference on Machine Learning. 16318\u201316330."},{"key":"e_1_3_3_1_31_2","volume-title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","author":"Nie Yixin","year":"2020","unstructured":"Yixin Nie, Adina Williams, Emily Dinan, Mohit Bansal, Jason Weston, and Douwe Kiela. 2020. Adversarial NLI: A New Benchmark for Natural Language Understanding. arxiv:https:\/\/arXiv.org\/abs\/1910.14599\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1910.14599"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.5220\/0013382400003890"},{"key":"e_1_3_3_1_33_2","volume-title":"NVIDIA Ampere GPU Architecture","author":"Corporation NVIDIA","year":"2020","unstructured":"NVIDIA Corporation. 2020. NVIDIA Ampere GPU Architecture. https:\/\/www.nvidia.com\/en-us\/data-center\/ampere-architecture\/"},{"key":"e_1_3_3_1_34_2","volume-title":"NVIDIA Hopper GPU Architecture Technical Brief","author":"Corporation NVIDIA","year":"2022","unstructured":"NVIDIA Corporation. 2022. NVIDIA Hopper GPU Architecture Technical Brief. https:\/\/www.nvidia.com\/en-us\/data-center\/technologies\/hopper-architecture\/"},{"key":"e_1_3_3_1_35_2","first-page":"1267","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: Human language technologies, volume 1 (Long and short papers)","author":"Pilehvar Mohammad\u00a0Taher","year":"2019","unstructured":"Mohammad\u00a0Taher Pilehvar and Jose Camacho-Collados. 2019. WiC: the word-in-context dataset for evaluating context-sensitive meaning representations. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: Human language technologies, volume 1 (Long and short papers). 1267\u20131273."},{"key":"e_1_3_3_1_36_2","volume-title":"TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs","author":"Qiao Ye","year":"2025","unstructured":"Ye Qiao, Zhiheng Chen, Yifan Zhang, Yian Wang, and Sitao Huang. 2025. TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs. arxiv:https:\/\/arXiv.org\/abs\/2504.16266"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","unstructured":"Keisuke Sakaguchi Ronan Le\u00a0Bras 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_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401196"},{"key":"e_1_3_3_1_39_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tailor Shyam\u00a0A.","year":"2021","unstructured":"Shyam\u00a0A. Tailor, Javier Fernandez-Marques, and Nicholas\u00a0D. Lane. 2021. Degree-Quant: Quantization-Aware Training for Graph Neural Networks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.457"},{"key":"e_1_3_3_1_41_2","volume-title":"ES-FoMo III: 3rd Workshop on Efficient Systems for Foundation Models","author":"Wang Xinyu","year":"2025","unstructured":"Xinyu Wang, Vahid Partovi\u00a0Nia, Peng Lu, Jerry Huang, Xiao-Wen Chang, Boxing Chen, and Yufei Cui. 2025. PoTPTQ: A Two-step Power-of-Two Post-training for LLMs. In ES-FoMo III: 3rd Workshop on Efficient Systems for Foundation Models. https:\/\/openreview.net\/forum?id=QjRIozXQNy"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696099"},{"key":"e_1_3_3_1_43_2","first-page":"38087","volume-title":"International Conference on Machine Learning","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023. SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models. In International Conference on Machine Learning. 38087\u201338099."},{"key":"e_1_3_3_1_44_2","volume-title":"PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models","author":"Xiao He","year":"2026","unstructured":"He Xiao, Runming Yang, Qingyao Yang, Wendong Xu, Zhen Li, Yupeng Su, Zhengwu Liu, Hongxia Yang, and Ngai Wong. 2026. PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2509.16989\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2509.16989"},{"key":"e_1_3_3_1_45_2","volume-title":"Qwen2 Technical Report","author":"Yang An","year":"2024","unstructured":"An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jianxin Yang, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Junyang Lin, Kai Dang, Keming Lu, Keqin Chen, Kexin Yang, Mei Li, Mingfeng Xue, Na Ni, Pei Zhang, Peng Wang, Ru Peng, Rui Men, Ruize Gao, Runji Lin, Shijie Wang, Shuai Bai, Sinan Tan, Tianhang Zhu, Tianhao Li, Tianyu Liu, Wenbin Ge, Xiaodong Deng, Xiaohuan Zhou, Xingzhang Ren, Xinyu Zhang, Xipin Wei, Xuancheng Ren, Xuejing Liu, Yang Fan, Yang Yao, Yichang Zhang, Yu Wan, Yunfei Chu, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Zhifang Guo, and Zhihao Fan. 2024. Qwen2 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2407.10671\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_3_1_46_2","volume-title":"TerEffic: Highly Efficient Ternary LLM Inference on FPGA","author":"Yin Chenyang","year":"2025","unstructured":"Chenyang Yin, Zhenyu Bai, Pranav Venkatram, Shivam Aggarwal, Zhaoying Li, and Tulika Mitra. 2025. TerEffic: Highly Efficient Ternary LLM Inference on FPGA. arxiv:https:\/\/arXiv.org\/abs\/2502.16473"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"crossref","unstructured":"Wei Zhang Lu Hou Yichun Yin Lifeng Shang Xiao Chen Xin Jiang and Qun Liu. 2020. Ternarybert: Distillation-aware ultra-low bit bert. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.12812 (2020).","DOI":"10.18653\/v1\/2020.emnlp-main.37"}],"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":[],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:50:14Z","timestamp":1782996614000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3807877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":47,"alternative-id":["10.1145\/3797905.3807877","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3807877","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"}}]}}