{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:34:41Z","timestamp":1780500881415,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB4504200"],"award-info":[{"award-number":["2024YFB4504200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou-HKUST(GZ) Joint Funding Program","award":["2025A03J3568"],"award-info":[{"award-number":["2025A03J3568"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756094","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"839-853","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["AxCore: A Quantization-Aware Approximate GEMM Unit for LLM Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8613-2589","authenticated-orcid":false,"given":"Jiaxiang","family":"Zou","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6273-9894","authenticated-orcid":false,"given":"Yonghao","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6028-0019","authenticated-orcid":false,"given":"Xingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0405-436X","authenticated-orcid":false,"given":"Chenxi","family":"Xu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1951-5015","authenticated-orcid":false,"given":"Xinyu","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","unstructured":"2019. IEEE Standard for Floating-Point Arithmetic. IEEE Std 754-2019 (Revision of IEEE 754-2008) (2019) 1\u201384. 10.1109\/IEEESTD.2019.8766229","DOI":"10.1109\/IEEESTD.2019.8766229"},{"key":"e_1_3_3_1_3_2","unstructured":"2019. WinoGrande: An Adversarial Winograd Schema Challenge at Scale."},{"key":"e_1_3_3_1_4_2","volume-title":"Heterogeneous Accelerated Compute Cluster (HACC) at NUS","year":"2025","unstructured":"AMD Xilinx 2025. Heterogeneous Accelerated Compute Cluster (HACC) at NUS. https:\/\/xacchead.d2.comp.nus.edu.sg\/."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"e_1_3_3_1_6_2","unstructured":"Tom\u00a0B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel\u00a0M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. arxiv:https:\/\/arXiv.org\/abs\/2005.14165\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC63849.2025.11133083"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Jack Choquette Wishwesh Gandhi Olivier Giroux Nick Stam and Ronny Krashinsky. 2021. NVIDIA A100 Tensor Core GPU: Performance and Innovation. IEEE Micro 41 2 (2021) 29\u201335. 10.1109\/MM.2021.3061394","DOI":"10.1109\/MM.2021.3061394"},{"key":"e_1_3_3_1_9_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:https:\/\/arXiv.org\/abs\/1803.05457v1 (2018)."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589351"},{"key":"e_1_3_3_1_11_2","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai Daya Guo Dejian Yang Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fucong Dai Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Han Bao Hanwei Xu Haocheng Wang Haowei Zhang Honghui Ding Huajian Xin Huazuo Gao Hui Li Hui Qu J.\u00a0L. Cai Jian Liang Jianzhong Guo Jiaqi Ni Jiashi Li Jiawei Wang Jin Chen Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li Junxiao Song Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Lei Xu Leyi Xia Liang Zhao Litong Wang Liyue Zhang Meng Li Miaojun Wang Mingchuan Zhang Minghua Zhang Minghui Tang Mingming Li Ning Tian Panpan Huang Peiyi Wang Peng Zhang Qiancheng Wang Qihao Zhu Qinyu Chen Qiushi Du R.\u00a0J. Chen R.\u00a0L. Jin Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang Runxin Xu Ruoyu Zhang Ruyi Chen S.\u00a0S. Li Shanghao Lu Shangyan Zhou Shanhuang Chen Shaoqing Wu Shengfeng Ye Shengfeng Ye Shirong Ma Shiyu Wang Shuang Zhou Shuiping Yu Shunfeng Zhou Shuting Pan T. Wang Tao Yun Tian Pei Tianyu Sun W.\u00a0L. Xiao Wangding Zeng Wanjia Zhao Wei An Wen Liu Wenfeng Liang Wenjun Gao Wenqin Yu Wentao Zhang X.\u00a0Q. Li Xiangyue Jin Xianzu Wang Xiao Bi Xiaodong Liu Xiaohan Wang Xiaojin Shen Xiaokang Chen Xiaokang Zhang Xiaosha Chen Xiaotao Nie Xiaowen Sun Xiaoxiang Wang Xin Cheng Xin Liu Xin Xie Xingchao Liu Xingkai Yu Xinnan Song Xinxia Shan Xinyi Zhou Xinyu Yang Xinyuan Li Xuecheng Su Xuheng Lin Y.\u00a0K. Li Y.\u00a0Q. Wang Y.\u00a0X. Wei Y.\u00a0X. Zhu Yang Zhang Yanhong Xu Yanhong Xu Yanping Huang Yao Li Yao Zhao Yaofeng Sun Yaohui Li Yaohui Wang Yi Yu Yi Zheng Yichao Zhang Yifan Shi Yiliang Xiong Ying He Ying Tang Yishi Piao Yisong Wang Yixuan Tan Yiyang Ma Yiyuan Liu Yongqiang Guo Yu Wu Yuan Ou Yuchen Zhu Yuduan Wang Yue Gong Yuheng Zou Yujia He Yukun Zha Yunfan Xiong Yunxian Ma Yuting Yan Yuxiang Luo Yuxiang You Yuxuan Liu Yuyang Zhou Z.\u00a0F. Wu Z.\u00a0Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhean Xu Zhen Huang Zhen Zhang Zhenda Xie Zhengyan Zhang Zhewen Hao Zhibin Gou Zhicheng Ma Zhigang Yan Zhihong Shao Zhipeng Xu Zhiyu Wu Zhongyu Zhang Zhuoshu Li Zihui Gu Zijia Zhu Zijun Liu Zilin Li Ziwei Xie Ziyang Song Ziyi Gao and Zizheng Pan. 2024. DeepSeek-V3 Technical Report. (dec 2024). arxiv:https:\/\/arXiv.org\/abs\/2412.19437http:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_3_1_12_2","volume-title":"Advances in Neural Information Processing Systems","author":"Dettmers Tim","year":"2022","unstructured":"Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer. 2022. LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale. In Advances in Neural Information Processing Systems , Vol.\u00a035. arxiv:https:\/\/arXiv.org\/abs\/2208.07339http:\/\/arxiv.org\/abs\/2208.07339"},{"key":"e_1_3_3_1_13_2","series-title":"(ICML\u201923)","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Dettmers Tim","year":"2023","unstructured":"Tim Dettmers and Luke Zettlemoyer. 2023. The case for 4-bit precision: k-bit inference scaling laws. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML\u201923). JMLR.org, Article 307, 25\u00a0pages."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Dolu1990. 2017. SpinalHDL : An alternative hardware description language. Chaos Computer Club e.V.. 10.5446\/43800","DOI":"10.5446\/43800"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Massimiliano Fasi Nicholas Higham Mantas Mikaitis and Srikara Pranesh. 2021. Numerical behavior of NVIDIA tensor cores. PeerJ Computer Science 7 (02 2021) e330. 10.7717\/peerj-cs.330","DOI":"10.7717\/peerj-cs.330"},{"key":"e_1_3_3_1_16_2","volume-title":"11th International Conference on Learning Representations, ICLR 2023","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2023. OPTQ: ACCURATE POST-TRAINING QUANTIZATION FOR GENERATIVE PRE-TRAINED TRANSFORMERS. In 11th International Conference on Learning Representations, ICLR 2023. arxiv:https:\/\/arXiv.org\/abs\/2210.17323http:\/\/arxiv.org\/abs\/2210.17323"},{"key":"e_1_3_3_1_17_2","unstructured":"Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima et\u00a0al. 2020. The Pile: An 800GB dataset of diverse text for language modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2101.00027 (2020)."},{"key":"e_1_3_3_1_18_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. 2021. A framework for few-shot language model evaluation. 10.5281\/zenodo.5371628","DOI":"10.5281\/zenodo.5371628"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658498"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00095"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH51176.2021.00019"},{"key":"e_1_3_3_1_22_2","unstructured":"Weiming Hu Haoyan Zhang Cong Guo Yu Feng Renyang Guan Zhendong Hua Zihan Liu Yue Guan Minyi Guo and Jingwen Leng. 2025. M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type. arxiv:https:\/\/arXiv.org\/abs\/2502.18755\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2502.18755"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00064"},{"key":"e_1_3_3_1_24_2","volume-title":"11th International Conference on Learning Representations, ICLR 2023","author":"Kim Yulhwa","year":"2023","unstructured":"Yulhwa Kim, Jaeyong Jang, Jehun Lee, Jihoon Park, Jeonghoon Kim, Byeongwook Kim, Baeseong Park, Se\u00a0Jung Kwon, Dongsoo Lee, and Jae\u00a0Joon Kim. 2023. WINNING BOTH THE ACCURACY OF FLOATING POINT ACTIVATION AND THE SIMPLICITY OF INTEGER ARITHMETIC. In 11th International Conference on Learning Representations, ICLR 2023."},{"key":"e_1_3_3_1_25_2","volume-title":"Advances in Neural Information Processing Systems","author":"Kosson Atli","year":"2023","unstructured":"Atli Kosson and Martin Jaggi. 2023. Multiplication-Free Transformer Training via Piecewise Affine Operations. In Advances in Neural Information Processing Systems , Vol.\u00a036. arxiv:https:\/\/arXiv.org\/abs\/2305.17190http:\/\/arxiv.org\/abs\/2305.17190"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00080"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Jinhao Li Jiaming Xu Shiyao Li Shan Huang Jun Liu Yaoxiu Lian and Guohao Dai. 2023. Fast and Efficient 2-bit LLM Inference on GPU: 2\/4\/16-bit in a Weight Matrix with Asynchronous Dequantization. IEEE\/ACM International Conference on Computer-Aided Design (ICCAD \u201924) October 27\u00e2\u2022\ufb0131 2024 New York NY USA 1 (2023). 10.1145\/3676536.3676796 arxiv:https:\/\/arXiv.org\/abs\/2311.16442","DOI":"10.1145\/3676536.3676796"},{"key":"e_1_3_3_1_28_2","unstructured":"Shiyao Li Xuefei Ning Luning Wang Tengxuan Liu Xiangsheng Shi Shengen Yan Guohao Dai Huazhong Yang and Yu Wang. 2024. Evaluating Quantized Large Language Models. ArXiv abs\/2402.18158 (2024). https:\/\/api.semanticscholar.org\/CorpusID:268041618"},{"key":"e_1_3_3_1_29_2","unstructured":"Yuhang Li Ruokai Yin Donghyun Lee Shiting Xiao and Priyadarshini Panda. 2025. GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.02692 (2025)."},{"key":"e_1_3_3_1_30_2","first-page":"87","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Lin Ji","year":"2024","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. In Proceedings of Machine Learning and Systems , P.\u00a0Gibbons, G.\u00a0Pekhimenko, and C.\u00a0De Sa (Eds.), Vol.\u00a06. 87\u2013100. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/42a452cbafa9dd64e9ba4aa95cc1ef21-Paper-Conference.pdf"},{"key":"e_1_3_3_1_31_2","unstructured":"Yujun Lin Haotian Tang Shang Yang Zhekai Zhang Guangxuan Xiao Chuang Gan and Song Han. 2024. QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving. arxiv:https:\/\/arXiv.org\/abs\/2405.04532\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2405.04532"},{"key":"e_1_3_3_1_32_2","unstructured":"Theodor Lindberg and Oscar Gustafsson. 2024. On Approximate 8-bit Floating-Point Operations Using Integer Operations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.18441 (2024)."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.39"},{"key":"e_1_3_3_1_34_2","unstructured":"Hongyin Luo and Wei Sun. 2024. Addition is all you need for energy-efficient language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.00907 (2024)."},{"key":"e_1_3_3_1_35_2","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer Sentinel Mixture Models. arxiv:https:\/\/arXiv.org\/abs\/1609.07843\u00a0[cs.CL]"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"John\u00a0N Mitchell. 1962. Computer multiplication and division using binary logarithms. IRE Transactions on Electronic Computers4 (1962) 512\u2013517.","DOI":"10.1109\/TEC.1962.5219391"},{"key":"e_1_3_3_1_37_2","unstructured":"Tsuguo Mogami. 2020. Deep Neural Network Training without Multiplications. ArXiv abs\/2012.03458 (2020). https:\/\/api.semanticscholar.org\/CorpusID:227340950"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.33"},{"key":"e_1_3_3_1_39_2","volume-title":"NVIDIA TensorRT Developer Guide (10.11.0 ed.)","author":"Corporation NVIDIA","year":"2024","unstructured":"NVIDIA Corporation. 2024. Accuracy Considerations for the Inference Library. In NVIDIA TensorRT Developer Guide (10.11.0 ed.). NVIDIA. https:\/\/docs.nvidia.com\/deeplearning\/tensorrt\/10.11.0\/inference-library\/accuracy-considerations.html Accessed: 2025-06-15."},{"key":"e_1_3_3_1_40_2","unstructured":"NVIDIA Corporation. 2025. NVIDIA TensorRT-LLM: Numerical Precision. https:\/\/nvidia.github.io\/TensorRT-LLM\/reference\/precision.html."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00085"},{"key":"e_1_3_3_1_42_2","first-page":"155","volume-title":"23rd USENIX Conference on File and Storage Technologies (FAST 25)","author":"Qin Ruoyu","year":"2025","unstructured":"Ruoyu Qin, Zheming Li, Weiran He, Jialei Cui, Feng Ren, Mingxing Zhang, Yongwei Wu, Weimin Zheng, and Xinran Xu. 2025. Mooncake: Trading More Storage for Less Computation \u2014 A KVCache-centric Architecture for Serving LLM Chatbot. In 23rd USENIX Conference on File and Storage Technologies (FAST 25). USENIX Association, Santa Clara, CA, 155\u2013170. https:\/\/www.usenix.org\/conference\/fast25\/presentation\/qin"},{"key":"e_1_3_3_1_43_2","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Ori Schweitzer Uri Weiser and Freddy Gabbay. 2024. Enhancing DNN Computational Efficiency via Decomposition and Approximation. IEEE Access (2024).","DOI":"10.1109\/ACCESS.2024.3521980"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"e_1_3_3_1_46_2","series-title":"(ICML\u201923)","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Sheng Ying","year":"2023","unstructured":"Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher R\u00e9, Ion Stoica, and Ce Zhang. 2023. FlexGen: high-throughput generative inference of large language models with a single GPU. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML\u201923). JMLR.org, Article 1288, 23\u00a0pages."},{"key":"e_1_3_3_1_47_2","unstructured":"Gil Shomron Freddy Gabbay Samer Kurzum and Uri Weiser. 2021. Post-training sparsity-aware quantization. Advances in Neural Information Processing Systems 34 (2021) 17737\u201317748."},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"e_1_3_3_1_49_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 Aur\u00e9lien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. ArXiv abs\/2302.13971 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257219404"},{"key":"e_1_3_3_1_50_2","first-page":"307","volume-title":"Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2024","author":"Wang Lei","year":"2024","unstructured":"Lei Wang, Lingxiao Ma, Shijie Cao, Quanlu Zhang, Jilong Xue, Yining Shi, Ningxin Zheng, Ziming Miao, Fan Yang, Ting Cao, Yuqing Yang, and Mao Yang. 2024. LADDER: Enabling Efficient Low-Precision Deep Learning Computing through Hardware-aware Tensor Transformation. In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2024. 307\u2013323. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/wang-lei"},{"key":"e_1_3_3_1_51_2","unstructured":"Jianyu Wei Shijie Cao Ting Cao Lingxiao Ma Lei Wang Yanyong Zhang and Mao Yang. 2024. T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge. (jun 2024). arxiv:https:\/\/arXiv.org\/abs\/2407.00088http:\/\/arxiv.org\/abs\/2407.00088"},{"key":"e_1_3_3_1_52_2","unstructured":"Guangxuan Xiao Ji Lin Mickael Seznec Julien Demouth and Song Han. 2022. SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models. ArXiv abs\/2211.10438 (2022). https:\/\/api.semanticscholar.org\/CorpusID:253708271"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"e_1_3_3_1_54_2","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona\u00a0T. Diab Xian Li Xi\u00a0Victoria Lin Todor Mihaylov Myle Ott Sam Shleifer Kurt Shuster Daniel Simig Punit\u00a0Singh Koura Anjali Sridhar Tianlu Wang and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. ArXiv abs\/2205.01068 (2022). https:\/\/api.semanticscholar.org\/CorpusID:248496292"},{"key":"e_1_3_3_1_55_2","unstructured":"Yu Zhang Mingzi Wang Lancheng Zou Wulong Liu Hui-Ling Zhen Mingxuan Yuan and Bei Yu. 2024. MixPE: Quantization and Hardware Co-design for Efficient LLM Inference. arxiv:https:\/\/arXiv.org\/abs\/2411.16158\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2411.16158"},{"key":"e_1_3_3_1_56_2","unstructured":"Yilong Zhao Chien-Yu Lin Kan Zhu Zihao Ye Lequn Chen Size Zheng Luis Ceze Arvind Krishnamurthy Tianqi Chen and Baris Kasikci. 2023. Atom: Low-bit Quantization for Efficient and Accurate LLM Serving. (oct 2023). arxiv:https:\/\/arXiv.org\/abs\/2310.19102http:\/\/arxiv.org\/abs\/2310.19102"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:45:00Z","timestamp":1769463900000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756094"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":55,"alternative-id":["10.1145\/3725843.3756094","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756094","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}