{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:14Z","timestamp":1750309514481,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3657374","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FastQuery: Communication-efficient Embedding Table Query for Private LLMs inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6575-2194","authenticated-orcid":false,"given":"Chenqi","family":"Lin","sequence":"first","affiliation":[{"name":"Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7832-828X","authenticated-orcid":false,"given":"Tianshi","family":"Xu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0672-6389","authenticated-orcid":false,"given":"Zebin","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7514-0767","authenticated-orcid":false,"given":"Runsheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8146-4821","authenticated-orcid":false,"given":"Ru","family":"Huang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7212-2264","authenticated-orcid":false,"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence and School of Integrated Circuits, Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"NeurIPs","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Mann, et al. Language models are few-shot learners. NeurIPs, 2020."},{"key":"e_1_3_2_1_2_1","volume-title":"et al. Ezpc: Programmable, efficient, and scalable secure two-party computation for machine learning. Cryptology ePrint Archive","author":"Chandran Nishanth","year":"2017","unstructured":"Nishanth Chandran, Divya Gupta, et al. Ezpc: Programmable, efficient, and scalable secure two-party computation for machine learning. Cryptology ePrint Archive, 2017."},{"key":"e_1_3_2_1_3_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. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323, 2022."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1145\/3582016.3582065"},{"key":"e_1_3_2_1_5_1","first-page":"15718","article-title":"Private inference on transformers","volume":"35","author":"Hao Meng","year":"2022","unstructured":"Meng Hao, Hongwei Li, Hanxiao Chen, Pengzhi Xing, Guowen Xu, and Tianwei Zhang. Iron: Private inference on transformers. NeurIPS, 35:15718--15731, 2022.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_6_1","volume-title":"Ciphergpt: Secure two-party gpt inference. Cryptology ePrint Archive","author":"Hou Xiaoyang","year":"2023","unstructured":"Xiaoyang Hou, Jian Liu, Jingyu Li, Yuhan Li, Wen-jie Lu, Cheng Hong, and Kui Ren. Ciphergpt: Secure two-party gpt inference. Cryptology ePrint Archive, 2023."},{"key":"e_1_3_2_1_7_1","first-page":"809","volume-title":"USENIX Security","author":"Huang Zhicong","year":"2022","unstructured":"Zhicong Huang, Wen-jie Lu, Cheng Hong, et al. Cheetah: Lean and fast secure two-party deep neural network inference. In USENIX Security, pages 809--826, 2022."},{"key":"e_1_3_2_1_8_1","volume-title":"Squeezellm: Dense-and-sparse quantization. arXiv preprint arXiv:2306.07629","author":"Kim Sehoon","year":"2023","unstructured":"Sehoon Kim, Coleman Hooper, Amir Gholami, Zhen Dong, Xiuyu Li, Sheng Shen, Michael W Mahoney, and Kurt Keutzer. Squeezellm: Dense-and-sparse quantization. arXiv preprint arXiv:2306.07629, 2023."},{"key":"e_1_3_2_1_9_1","volume-title":"Awq: Activation-aware weight quantization for llm compression and acceleration. arXiv preprint arXiv:2306.00978","author":"Lin Ji","year":"2023","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Xingyu Dang, and Song Han. Awq: Activation-aware weight quantization for llm compression and acceleration. arXiv preprint arXiv:2306.00978, 2023."},{"key":"e_1_3_2_1_10_1","volume-title":"et al. Llm-qat: Data-free quantization aware training for large language models. arXiv preprint arXiv:2305.17888","author":"Liu Zechun","year":"2023","unstructured":"Zechun Liu, Barlas Oguz, Changsheng Zhao, et al. Llm-qat: Data-free quantization aware training for large language models. arXiv preprint arXiv:2305.17888, 2023."},{"key":"e_1_3_2_1_11_1","volume-title":"et al. Bumblebee: Secure two-party inference framework for large transformers. Cryptology ePrint Archive","author":"Huang Zhicong","year":"2023","unstructured":"Wen-jie Lu, Zhicong Huang, Zhen Gu, et al. Bumblebee: Secure two-party inference framework for large transformers. Cryptology ePrint Archive, 2023."},{"key":"e_1_3_2_1_12_1","first-page":"17","volume-title":"USENIX ATC","author":"Ma Junming","year":"2023","unstructured":"Junming Ma, Yancheng Zheng, Jun Feng, et al. SecretFlow-SPU: A performant and User-Friendly framework for Privacy-Preserving machine learning. In USENIX ATC, pages 17--33, Boston, MA, July 2023. USENIX Association."},{"key":"e_1_3_2_1_13_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. Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843, 2016."},{"key":"e_1_3_2_1_14_1","volume-title":"Jan","author":"Mishra Pratyush","year":"2020","unstructured":"Pratyush Mishra, Ryan Lehmkuhl, Akshayaram Srinivasan, Wenting Zheng, and RalucaAda Popa. Delphi: A cryptographic inference service for neural networks, Jan 2020."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.5555\/3455716.3455856"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1109\/SP40001.2021.00086"},{"key":"e_1_3_2_1_17_1","volume-title":"ACM SIGSAC CCS","author":"Rathee Deevashwer","year":"2020","unstructured":"Deevashwer Rathee, Mayank Rathee, Nishant Kumar, et al. Cryptflow2: Practical 2-party secure inference. In ACM SIGSAC CCS, 2020."},{"key":"e_1_3_2_1_18_1","volume-title":"et al. Cham: A customized homomorphic encryption accelerator for fast matrix-vector product","author":"Ren Xuanle","year":"2023","unstructured":"Xuanle Ren, Zhaohui Chen, Zhen Gu, et al. Cham: A customized homomorphic encryption accelerator for fast matrix-vector product. In DAC. IEEE, 2023."},{"key":"e_1_3_2_1_19_1","volume-title":"November","author":"Microsoft SEAL","year":"2020","unstructured":"Microsoft SEAL (release 3.6). https:\/\/github.com\/Microsoft\/SEAL, November 2020. Microsoft Research, Redmond, WA."},{"key":"e_1_3_2_1_20_1","volume-title":"et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023."},{"key":"e_1_3_2_1_21_1","volume-title":"Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023."},{"key":"e_1_3_2_1_22_1","volume-title":"Hequant: Marrying homomorphic encryption and quantization for communication-efficient private inference. arXiv preprint arXiv:2401.15970","author":"Xu Tianshi","year":"2024","unstructured":"Tianshi Xu, Meng Li, and Runsheng Wang. Hequant: Marrying homomorphic encryption and quantization for communication-efficient private inference. arXiv preprint arXiv:2401.15970, 2024."},{"key":"e_1_3_2_1_23_1","volume-title":"Falcon: Accelerating homo-morphically encrypted convolutions for efficient private mobile network inference. arXiv preprint arXiv:2308.13189","author":"Xu Tianshi","year":"2023","unstructured":"Tianshi Xu, Meng Li, Runsheng Wang, and Ru Huang. Falcon: Accelerating homo-morphically encrypted convolutions for efficient private mobile network inference. arXiv preprint arXiv:2308.13189, 2023."},{"key":"e_1_3_2_1_24_1","first-page":"27168","article-title":"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. Zeroquant: Efficient and affordable post-training quantization for large-scale transformers. NeurIPS, 35:27168--27183, 2022.","journal-title":"NeurIPS"}],"event":{"sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"],"acronym":"DAC '24","name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","location":"San Francisco CA USA"},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3657374","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3657374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:01Z","timestamp":1750295881000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3657374"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":24,"alternative-id":["10.1145\/3649329.3657374","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3657374","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}