{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T11:58:27Z","timestamp":1792756707986,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":154,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3676641.3716013","type":"proceedings-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:47:32Z","timestamp":1743094052000},"page":"845-861","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["PICACHU: Plug-In CGRA Handling Upcoming Nonlinear Operations in LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8845-2371","authenticated-orcid":false,"given":"Jiajun","family":"Qin","sequence":"first","affiliation":[{"name":"New York University, New York, NY, USA and Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4376-0885","authenticated-orcid":false,"given":"Tianhua","family":"Xia","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3727-2889","authenticated-orcid":false,"given":"Cheng","family":"Tan","sequence":"additional","affiliation":[{"name":"Google, Mountain view, CA, USA and Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7411-8923","authenticated-orcid":false,"given":"Jeff","family":"Zhang","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4815-9235","authenticated-orcid":false,"given":"Sai Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"New York University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"G Abarajithan Zhenghua Ma Zepeng Li Shrideep Koparkar Ravidu Munasinghe Francesco Restuccia and Ryan Kastner. 2024. CGRA4ML: A Framework to Implement Modern Neural Networks for Scientific Edge Computing. arxiv: 2408.15561 [cs.AR] https:\/\/arxiv.org\/abs\/2408.15561"},{"key":"e_1_3_2_1_2_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv","author":"Alexey Dosovitskiy","year":"2010","unstructured":"Dosovitskiy Alexey. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929 (2020)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.4236\/cs.2017.86010"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS61541.2024.00012"},{"key":"e_1_3_2_1_5_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E. Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer Normalization. arxiv: 1607.06450 [stat.ML] https:\/\/arxiv.org\/abs\/1607.06450"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2857278"},{"key":"e_1_3_2_1_7_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"e_1_3_2_1_9_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1069--1074","author":"Balasubramanian Mahesh","year":"2018","unstructured":"Mahesh Balasubramanian, Shail Dave, Aviral Shrivastava, and Reiley Jeyapaul. 2018. LASER: A hardware\/software approach to accelerate complicated loops on CGRAs. In 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1069--1074."},{"key":"e_1_3_2_1_10_1","volume-title":"Efficient 8-bit quantization of transformer neural machine language translation model. arXiv preprint arXiv:1906.00532","author":"Bhandare Aishwarya","year":"2019","unstructured":"Aishwarya Bhandare, Vamsi Sripathi, Deepthi Karkada, Vivek Menon, Sun Choi, Kushal Datta, and Vikram Saletore. 2019. Efficient 8-bit quantization of transformer neural machine language translation model. arXiv preprint arXiv:1906.00532 (2019)."},{"key":"e_1_3_2_1_11_1","unstructured":"Xiao Bi Deli Chen Guanting Chen Shanhuang Chen Damai Dai Chengqi Deng Honghui Ding Kai Dong Qiushi Du Zhe Fu et al. 2024. Deepseek llm: Scaling open-source language models with longtermism. arXiv preprint arXiv:2401.02954 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Sid Black Stella Biderman Eric Hallahan Quentin Anthony Leo Gao Laurence Golding Horace He Connor Leahy Kyle McDonell Jason Phang et al. 2022. Gpt-neox-20b: An open-source autoregressive language model. arXiv preprint arXiv:2204.06745 (2022).","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"e_1_3_2_1_14_1","volume-title":"Language Models are Few-Shot Learners. arxiv","author":"Brown Tom B.","year":"2005","unstructured":"Tom B. 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 M. 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: 2005.14165 [cs.CL] https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_1_15_1","unstructured":"Zheng Cai Maosong Cao Haojiong Chen Kai Chen Keyu Chen Xin Chen Xun Chen Zehui Chen Zhi Chen Pei Chu et al. 2024. Internlm2 technical report. arXiv preprint arXiv:2403.17297 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357nolinkurl10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_2_1_17_1","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham Hyung Won Chung Charles Sutton Sebastian Gehrmann Parker Schuh Kensen Shi Sasha Tsvyashchenko Joshua Maynez Abhishek Rao Parker Barnes Yi Tay Noam Shazeer Vinodkumar Prabhakaran Emily Reif Nan Du Ben Hutchinson Reiner Pope James Bradbury Jacob Austin Michael Isard Guy Gur-Ari Pengcheng Yin Toju Duke Anselm Levskaya Sanjay Ghemawat Sunipa Dev Henryk Michalewski Xavier Garcia Vedant Misra Kevin Robinson Liam Fedus Denny Zhou Daphne Ippolito David Luan Hyeontaek Lim Barret Zoph Alexander Spiridonov Ryan Sepassi David Dohan Shivani Agrawal Mark Omernick Andrew M. Dai Thanumalayan Sankaranarayana Pillai Marie Pellat Aitor Lewkowycz Erica Moreira Rewon Child Oleksandr Polozov Katherine Lee Zongwei Zhou Xuezhi Wang Brennan Saeta Mark Diaz Orhan Firat Michele Catasta Jason Wei Kathy Meier-Hellstern Douglas Eck Jeff Dean Slav Petrov and Noah Fiedel. 2022. PaLM: Scaling Language Modeling with Pathways. arxiv: 2204.02311 [cs.CL] https:\/\/arxiv.org\/abs\/2204.02311"},{"key":"e_1_3_2_1_18_1","volume-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457","author":"Clark Peter","year":"2018","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 preprint arXiv:1803.05457 (2018)."},{"key":"e_1_3_2_1_19_1","unstructured":"Tri Dao Daniel Y. Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. arxiv: 2205.14135 [cs.LG] https:\/\/arxiv.org\/abs\/2205.14135"},{"key":"e_1_3_2_1_20_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_21_1","unstructured":"Xiaoyi Dong Pan Zhang Yuhang Zang Yuhang Cao Bin Wang Linke Ouyang Xilin Wei Songyang Zhang Haodong Duan Maosong Cao et al. 2024. Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model. arXiv preprint arXiv:2401.16420 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"e_1_3_2_1_23_1","volume-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323","author":"Frantar Elias","year":"2022","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2022. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323 (2022)."},{"key":"e_1_3_2_1_24_1","volume-title":"SoftAct: A High-Precision Softmax Architecture for Transformers Supporting Nonlinear Functions","author":"Fu Yuzhe","year":"2024","unstructured":"Yuzhe Fu, Changchun Zhou, Tianling Huang, Eryi Han, Yifan He, and Hailong Jiao. 2024. SoftAct: A High-Precision Softmax Architecture for Transformers Supporting Nonlinear Functions. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10256836nolinkurl10.5281\/zenodo.10256836"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9180870"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640365nolinkurl10.1145\/3620665.3640365"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00084"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"e_1_3_2_1_31_1","volume-title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization. 2022 55th IEEE\/ACM International Symposium on Microarchitecture (MICRO) (2022","author":"Guo Cong","year":"2022","unstructured":"Cong Guo, Chen Zhang, Jingwen Leng, Zihan Liu, Fan Yang, Yun-Bo Liu, Minyi Guo, and Yuhao Zhu. 2022. ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization. 2022 55th IEEE\/ACM International Symposium on Microarchitecture (MICRO) (2022), 1414--1433. https:\/\/api.semanticscholar.org\/CorpusID:251928917"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"e_1_3_2_1_34_1","volume-title":"2014 51st ACM\/EDAC\/IEEE Design Automation Conference (DAC). 1--6.","author":"Hamzeh Mahdi","year":"2014","unstructured":"Mahdi Hamzeh, Aviral Shrivastava, and Sarma Vrudhula. 2014. Branch-aware loop mapping on CGRAs. In 2014 51st ACM\/EDAC\/IEEE Design Automation Conference (DAC). 1--6."},{"key":"e_1_3_2_1_35_1","unstructured":"Dan Hendrycks and Kevin Gimpel. 2023. Gaussian Error Linear Units (GELUs). arxiv: 1606.08415 [cs.LG] https:\/\/arxiv.org\/abs\/1606.08415"},{"key":"e_1_3_2_1_36_1","volume-title":"DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation. arxiv: 2209.10797 [eess.SY] https:\/\/arxiv.org\/abs\/2209.10797","author":"Hong Seongmin","year":"2022","unstructured":"Seongmin Hong, Seungjae Moon, Junsoo Kim, Sungjae Lee, Minsub Kim, Dongsoo Lee, and Joo-Young Kim. 2022. DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation. arxiv: 2209.10797 [eess.SY] https:\/\/arxiv.org\/abs\/2209.10797"},{"key":"e_1_3_2_1_37_1","volume-title":"Ruby: Improving Hardware Efficiency for Tensor Algebra Accelerators Through Imperfect Factorization. In 2022 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).","author":"Horeni M.","unstructured":"M. Horeni, P. Taheri, P. Tsai, A. Parashar, J. Emer, and S. Joshi. 2022. Ruby: Improving Hardware Efficiency for Tensor Algebra Accelerators Through Imperfect Factorization. In 2022 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)."},{"key":"e_1_3_2_1_38_1","unstructured":"Xing Hu Yuan Cheng Dawei Yang Zhihang Yuan Jiangyong Yu Chen Xu and Sifan Zhou. 2024. I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models. arxiv: 2405.17849 [cs.LG] https:\/\/arxiv.org\/abs\/2405.17849"},{"key":"e_1_3_2_1_39_1","volume-title":"Edgellm: A highly efficient cpu-fpga heterogeneous edge accelerator for large language models. arXiv preprint arXiv:2407.21325","author":"Huang Mingqiang","year":"2024","unstructured":"Mingqiang Huang, Ao Shen, Kai Li, Haoxiang Peng, Boyu Li, and Hao Yu. 2024. Edgellm: A highly efficient cpu-fpga heterogeneous edge accelerator for large language models. arXiv preprint arXiv:2407.21325 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS51828.2021.9458541"},{"key":"e_1_3_2_1_41_1","volume-title":"Retrieved June","volume":"14","author":"Jacob Benoit","year":"2017","unstructured":"Benoit Jacob and Pete Warden. 2017. gemmlowp: A small self-contained low-precision gemm library. Retrieved June, Vol. 14 (2017), 2018."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia59966.2023.10326397"},{"key":"e_1_3_2_1_43_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360307"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942148"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/NEWCAS.2017.8010157"},{"key":"e_1_3_2_1_49_1","volume-title":"I-BERT: Integer-only BERT Quantization. CoRR","author":"Kim Sehoon","year":"2021","unstructured":"Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, and Kurt Keutzer. 2021. I-BERT: Integer-only BERT Quantization. CoRR, Vol. abs\/2101.01321 (2021). showeprint[arXiv]2101.01321 https:\/\/arxiv.org\/abs\/2101.01321"},{"key":"e_1_3_2_1_50_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, Vol. 35 (2022), 22199--22213."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589081"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304028"},{"key":"e_1_3_2_1_53_1","volume-title":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 1--16","author":"Kung Hsiang-Tsung","year":"2020","unstructured":"Hsiang-Tsung Kung, Bradley McDanel, and Sai Qian Zhang. 2020. Term quantization: Furthering quantization at run time. In SC20: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, 1--16."},{"key":"e_1_3_2_1_54_1","volume-title":"Logic synthesis using Synopsys\u00ae","author":"Kurup Pran","unstructured":"Pran Kurup and Taher Abbasi. 1997. Logic synthesis using Synopsys\u00ae. Springer Science & Business Media."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665nolinkurl10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_1_56_1","volume-title":"MLIR: A Compiler Infrastructure for the End of Moore's Law. arxiv","author":"Lattner Chris","year":"2020","unstructured":"Chris Lattner, Mehdi Amini, Uday Bondhugula, Albert Cohen, Andy Davis, Jacques Pienaar, River Riddle, Tatiana Shpeisman, Nicolas Vasilache, and Oleksandr Zinenko. 2020. MLIR: A Compiler Infrastructure for the End of Moore's Law. arxiv: 2002.11054 [cs.PL] https:\/\/arxiv.org\/abs\/2002.11054"},{"key":"e_1_3_2_1_57_1","volume-title":"Fran\u00e7ois Yvon, Matthias Gall\u00e9, et al.","author":"Scao Teven Le","year":"2023","unstructured":"Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ili\u0107, Daniel Hesslow, Roman Castagn\u00e9, Alexandra Sasha Luccioni, Fran\u00e7ois Yvon, Matthias Gall\u00e9, et al. 2023. Bloom: A 176b-parameter open-access multilingual language model. (2023)."},{"key":"e_1_3_2_1_58_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1408--1413","author":"Lee Jungi","year":"2021","unstructured":"Jungi Lee and Jongeun Lee. 2021. NP-CGRA: Extending CGRAs for efficient processing of light-weight deep neural networks. In 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1408--1413."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00080"},{"key":"e_1_3_2_1_60_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, Vol. 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3058313"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00040"},{"key":"e_1_3_2_1_64_1","volume-title":"Jurassic-1: Technical details and evaluation. White Paper. AI21 Labs","author":"Lieber Opher","year":"2021","unstructured":"Opher Lieber, Or Sharir, Barak Lenz, and Yoav Shoham. 2021. Jurassic-1: Technical details and evaluation. White Paper. AI21 Labs, Vol. 1, 9 (2021)."},{"key":"e_1_3_2_1_65_1","first-page":"87","article-title":"AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration","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. 2024a. AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. Proceedings of Machine Learning and Systems, Vol. 6 (2024), 87--100.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00015"},{"key":"e_1_3_2_1_68_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024a. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357375"},{"key":"e_1_3_2_1_70_1","volume-title":"International Conference on Machine Learning. PMLR, 22137--22176","author":"Liu Zichang","year":"2023","unstructured":"Zichang Liu, Jue Wang, Tri Dao, Tianyi Zhou, Binhang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher Re, et al. 2023. Deja vu: Contextual sparsity for efficient llms at inference time. In International Conference on Machine Learning. PMLR, 22137--22176."},{"key":"e_1_3_2_1_71_1","volume-title":"Auto-LUT: Auto Approximation of Non-Linear Operations for Neural Networks on FPGA. In 2023 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 1--5.","author":"Lu Haodong","year":"2023","unstructured":"Haodong Lu, Qichang Mei, and Kun Wang. 2023. Auto-LUT: Auto Approximation of Non-Linear Operations for Neural Networks on FPGA. In 2023 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 1--5."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247873"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191521nolinkurl10.1109\/IJCNN54540.2023.10191521"},{"key":"e_1_3_2_1_76_1","unstructured":"Alberto Marchisio Davide Dura Maurizio Capra Maurizio Martina Guido Masera and Muhammad Shafique. 2023b. SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers. arxiv: 2304.03986 [cs.LG] https:\/\/arxiv.org\/abs\/2304.03986"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2003.1253623nolinkurl10.1109\/DATE.2003.1253623"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582070"},{"key":"e_1_3_2_1_79_1","volume-title":"Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843","author":"Merity Stephen","year":"2016","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080255"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6939"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"e_1_3_2_1_83_1","volume-title":"The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116","author":"Penedo Guilherme","year":"2023","unstructured":"Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Alessandro Cappelli, Hamza Alobeidli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. 2023. The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116 (2023)."},{"key":"e_1_3_2_1_84_1","volume-title":"Instruction tuning with gpt-4. arXiv preprint arXiv:2304.03277","author":"Peng Baolin","year":"2023","unstructured":"Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, and Jianfeng Gao. 2023. Instruction tuning with gpt-4. arXiv preprint arXiv:2304.03277 (2023)."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"e_1_3_2_1_87_1","unstructured":"A Radford. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_88_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_89_1","unstructured":"Jack W Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young et al. 2021. Scaling language models: Methods analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)."},{"key":"e_1_3_2_1_90_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"e_1_3_2_1_92_1","volume-title":"Scale-sim: Systolic cnn accelerator simulator. arXiv preprint arXiv:1811.02883","author":"Samajdar Ananda","year":"2018","unstructured":"Ananda Samajdar, Yuhao Zhu, Paul Whatmough, Matthew Mattina, and Tushar Krishna. 2018. Scale-sim: Systolic cnn accelerator simulator. arXiv preprint arXiv:1811.02883 (2018)."},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533040"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614283"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3001220"},{"key":"e_1_3_2_1_96_1","volume-title":"Omniquant: Omnidirectionally calibrated quantization for large language models. arXiv preprint arXiv:2308.13137","author":"Shao Wenqi","year":"2023","unstructured":"Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao, Yu Qiao, and Ping Luo. 2023. Omniquant: Omnidirectionally calibrated quantization for large language models. arXiv preprint arXiv:2308.13137 (2023)."},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"e_1_3_2_1_98_1","volume-title":"Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Network. 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA) (2017","author":"Sharma Hardik","year":"2017","unstructured":"Hardik Sharma, Jongse Park, Naveen Suda, Liangzhen Lai, Benson Chau, Joon Kyung Kim, Vikas Chandra, and Hadi Esmaeilzadeh. 2017. Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Network. 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA) (2017), 764--775. https:\/\/api.semanticscholar.org\/CorpusID:21681898"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI59464.2023.10238676"},{"key":"e_1_3_2_1_101_1","first-page":"1652","article-title":"Aggressive approximation of the softmax function for power-efficient hardware implementations","volume":"69","author":"Spagnolo Fanny","year":"2021","unstructured":"Fanny Spagnolo, Stefania Perri, and Pasquale Corsonello. 2021. Aggressive approximation of the softmax function for power-efficient hardware implementations. IEEE Transactions on Circuits and Systems II: Express Briefs, Vol. 69, 3 (2021), 1652--1656.","journal-title":"IEEE Transactions on Circuits and Systems II: Express Briefs"},{"key":"e_1_3_2_1_102_1","unstructured":"Richard Stallman et al. 1998. The GNU project. http:\/\/www.gnu.org\/software\/libc\/."},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480095"},{"key":"e_1_3_2_1_106_1","volume-title":"ICED: An Integrated CGRA Framework Enabling DVFS-Aware Acceleration. In 2024 57th IEEE\/ACM International Symposium on Microarchitecture (MICRO). IEEE, 1338--1352","author":"Tan Cheng","year":"2024","unstructured":"Cheng Tan, Miaomiao Jiang, Deepak Patil, Yanghui Ou, Zhaoying Li, Lei Ju, Tulika Mitra, Hyunchul Park, Antonino Tumeo, and Jeff Zhang. 2024. ICED: An Integrated CGRA Framework Enabling DVFS-Aware Acceleration. In 2024 57th IEEE\/ACM International Symposium on Microarchitecture (MICRO). IEEE, 1338--1352."},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323910nolinkurl10.1109\/ICCAD57390.2023.10323910"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD50377.2020.00070"},{"key":"e_1_3_2_1_109_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1388--1393","author":"Tan Cheng","year":"2021","unstructured":"Cheng Tan, Chenhao Xie, Ang Li, Kevin J Barker, and Antonino Tumeo. 2021. Aurora: Automated refinement of coarse-grained reconfigurable accelerators. In 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1388--1393."},{"key":"e_1_3_2_1_110_1","volume-title":"Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al.","author":"Thoppilan Romal","year":"2022","unstructured":"Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. 2022. Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022)."},{"key":"e_1_3_2_1_111_1","unstructured":"Shyamkumar Thoziyoor N Muralimanohar J Ahn and N Jouppi. 2009. Cacti 6.5. hpl.hp.com."},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00042"},{"key":"e_1_3_2_1_113_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023a. LLaMA: Open and Efficient Foundation Language Models. arxiv: 2302.13971 [cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_1_114_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023b. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv: 2307.09288 [cs.CL] https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213542"},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2017.2688340"},{"key":"e_1_3_2_1_117_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_118_1","volume-title":"Efficient softmax approximation for deep neural networks with attention mechanism. arXiv preprint arXiv:2111.10770","author":"Vasyltsov Ihor","year":"2021","unstructured":"Ihor Vasyltsov and Wooseok Chang. 2021. Efficient softmax approximation for deep neural networks with attention mechanism. arXiv preprint arXiv:2111.10770 (2021)."},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_2_1_120_1","volume-title":"A high-speed and low-complexity architecture for softmax function in deep learning. In 2018 IEEE asia pacific conference on circuits and systems (APCCAS)","author":"Wang Meiqi","unstructured":"Meiqi Wang, Siyuan Lu, Danyang Zhu, Jun Lin, and Zhongfeng Wang. 2018. A high-speed and low-complexity architecture for softmax function in deep learning. In 2018 IEEE asia pacific conference on circuits and systems (APCCAS). IEEE, 223--226."},{"key":"e_1_3_2_1_121_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Wenhai","year":"2024","unstructured":"Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al. 2024. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_122_1","volume-title":"SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 1--9.","author":"Wang Wenxun","year":"2023","unstructured":"Wenxun Wang, Shuchang Zhou, Wenyu Sun, Peiqin Sun, and Yongpan Liu. 2023. SOLE: Hardware-Software Co-design of Softmax and LayerNorm for Efficient Transformer Inference. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 1--9."},{"key":"e_1_3_2_1_123_1","volume-title":"Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)."},{"key":"e_1_3_2_1_124_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824--24837."},{"key":"e_1_3_2_1_125_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00063"},{"key":"e_1_3_2_1_126_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785nolinkurl10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_127_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942149"},{"key":"e_1_3_2_1_128_1","volume-title":"Sparseloop: An Analytical Approach To Sparse Tensor Accelerator Modeling. In ACM\/IEEE International Symposium on Microarchitecture (MICRO).","author":"Wu Yannan N.","unstructured":"Yannan N. Wu, Po-An Tsai, Angshuman Parashar, Vivienne Sze, and Joel S. Emer. 2022. Sparseloop: An Analytical Approach To Sparse Tensor Accelerator Modeling. In ACM\/IEEE International Symposium on Microarchitecture (MICRO)."},{"key":"e_1_3_2_1_129_1","volume-title":"Hyft: A Reconfigurable Softmax Accelerator with Hybrid Numeric Format for both Training and Inference. arxiv: 2311.13290 [cs.AR] https:\/\/arxiv.org\/abs\/2311.13290","author":"Xia Tianhua","year":"2024","unstructured":"Tianhua Xia and Sai Qian Zhang. 2024. Hyft: A Reconfigurable Softmax Accelerator with Hybrid Numeric Format for both Training and Inference. arxiv: 2311.13290 [cs.AR] https:\/\/arxiv.org\/abs\/2311.13290"},{"key":"e_1_3_2_1_130_1","volume-title":"International Conference on Machine Learning. PMLR, 38087--38099","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. PMLR, 38087--38099."},{"key":"e_1_3_2_1_131_1","volume-title":"Aurora: A Versatile and Flexible Accelerator for Graph Neural Networks. In 2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 890--902","author":"Yang Jiaqi","year":"2024","unstructured":"Jiaqi Yang, Hao Zheng, and Ahmed Louri. 2024. Aurora: A Versatile and Flexible Accelerator for Graph Neural Networks. In 2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, 890--902."},{"key":"e_1_3_2_1_132_1","first-page":"27168","article-title":"Zeroquant: Efficient and affordable post-training quantization for large-scale transformers","volume":"35","author":"Yao Zhewei","year":"2022","unstructured":"Zhewei Yao, Reza Yazdani Aminabadi, Minjia Zhang, Xiaoxia Wu, Conglong Li, and Yuxiong He. 2022. Zeroquant: Efficient and affordable post-training quantization for large-scale transformers. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27168--27183.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_133_1","doi-asserted-by":"publisher","DOI":"10.1145\/3549937"},{"key":"e_1_3_2_1_134_1","doi-asserted-by":"publisher","DOI":"10.23919\/VLSIC.2017.8008534"},{"key":"e_1_3_2_1_135_1","volume-title":"Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652","author":"Young Alex","year":"2024","unstructured":"Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Heng Li, Jiangcheng Zhu, Jianqun Chen, Jing Chang, et al. 2024. Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652 (2024)."},{"key":"e_1_3_2_1_136_1","volume-title":"Dong Hyun Lee, and Jungwook Choi","author":"Yu Joonsang","year":"2021","unstructured":"Joonsang Yu, Junki Park, Seongmin Park, Minsoo Kim, Sihwa Lee, Dong Hyun Lee, and Jungwook Choi. 2021. NN-LUT: Neural Approximation of Non-Linear Operations for Efficient Transformer Inference. CoRR, Vol. abs\/2112.02191 (2021). showeprint[arXiv]2112.02191 https:\/\/arxiv.org\/abs\/2112.02191"},{"key":"e_1_3_2_1_137_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yu Lijun","year":"2024","unstructured":"Lijun Yu, Yong Cheng, Zhiruo Wang, Vivek Kumar, Wolfgang Macherey, Yanping Huang, David Ross, Irfan Essa, Yonatan Bisk, Ming-Hsuan Yang, et al. 2024. Spae: Semantic pyramid autoencoder for multimodal generation with frozen llms. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_138_1","volume-title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models. ArXiv","author":"Yuan Zhihang","year":"2023","unstructured":"Zhihang Yuan, Lin Niu, Jia-Wen Liu, Wenyu Liu, Xinggang Wang, Yuzhang Shang, Guangyu Sun, Qiang Wu, Jiaxiang Wu, and Bingzhe Wu. 2023. RPTQ: Reorder-based Post-training Quantization for Large Language Models. ArXiv, Vol. abs\/2304.01089 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257913374"},{"key":"e_1_3_2_1_139_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"e_1_3_2_1_140_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"e_1_3_2_1_141_1","volume-title":"Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, et al.","author":"Zaheer Manzil","year":"2020","unstructured":"Manzil Zaheer, Guru Guruganesh, Kumar Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, et al. 2020. Big bird: Transformers for longer sequences. Advances in neural information processing systems, Vol. 33 (2020), 17283--17297."},{"key":"e_1_3_2_1_142_1","volume-title":"Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830","author":"Zellers Rowan","year":"2019","unstructured":"Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019. Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830 (2019)."},{"key":"e_1_3_2_1_143_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)."},{"key":"e_1_3_2_1_144_1","volume-title":"Pangu-\u03b1: Large-scale autoregressive pretrained Chinese language models with auto-parallel computation. arXiv preprint arXiv:2104.12369","author":"Zeng Wei","year":"2021","unstructured":"Wei Zeng, Xiaozhe Ren, Teng Su, Hui Wang, Yi Liao, Zhiwei Wang, Xin Jiang, ZhenZhang Yang, Kaisheng Wang, Xiaoda Zhang, et al. 2021. Pangu-\u03b1: Large-scale autoregressive pretrained Chinese language models with auto-parallel computation. arXiv preprint arXiv:2104.12369 (2021)."},{"key":"e_1_3_2_1_145_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022b. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_146_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00067"},{"key":"e_1_3_2_1_147_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446741"},{"key":"e_1_3_2_1_148_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00071"},{"key":"e_1_3_2_1_149_1","doi-asserted-by":"publisher","DOI":"10.1145\/3665314.3670813"},{"key":"e_1_3_2_1_150_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3175534"},{"key":"e_1_3_2_1_151_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhang Zhenyu","year":"2024","unstructured":"Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher R\u00e9, Clark Barrett, et al. 2024a. H2o: Heavy-hitter oracle for efficient generative inference of large language models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_152_1","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate llm serving","volume":"6","author":"Zhao Yilong","year":"2024","unstructured":"Yilong Zhao, Chien-Yu Lin, Kan Zhu, Zihao Ye, Lequn Chen, Size Zheng, Luis Ceze, Arvind Krishnamurthy, Tianqi Chen, and Baris Kasikci. 2024. Atom: Low-bit quantization for efficient and accurate llm serving. Proceedings of Machine Learning and Systems, Vol. 6 (2024), 196--209.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_153_1","doi-asserted-by":"publisher","DOI":"10.1109\/PRIME55000.2022.9816810"},{"key":"e_1_3_2_1_154_1","doi-asserted-by":"publisher","DOI":"10.23919\/EDHPC59100.2023.10396632"}],"event":{"name":"ASPLOS '25: 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Rotterdam Netherlands","acronym":"ASPLOS '25","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676641.3716013","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676641.3716013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T11:11:07Z","timestamp":1755774667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676641.3716013"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":154,"alternative-id":["10.1145\/3676641.3716013","10.1145\/3676641"],"URL":"https:\/\/doi.org\/10.1145\/3676641.3716013","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}