{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:09:18Z","timestamp":1780664958085,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:00:00Z","timestamp":1777161600000},"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":[[2026,4,27]]},"DOI":"10.1145\/3767295.3769351","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"1298-1313","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FlexiQ: Adaptive Mixed-Precision Quantization for Latency\/Accuracy Trade-Offs in Deep Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2505-8977","authenticated-orcid":false,"given":"Jaemin","family":"Kim","sequence":"first","affiliation":[{"name":"Seoul National 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\/0009-0008-8058-8161","authenticated-orcid":false,"given":"Sungkyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Hanyang 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\/0000-0002-4855-5609","authenticated-orcid":false,"given":"Jiwon","family":"Seo","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00144"},{"key":"e_1_3_2_1_3_1","first-page":"2294","volume-title":"International conference on machine learning","author":"Chen Wenlin","unstructured":"Wenlin Chen, James Wilson, Stephen Tyree, Kilian Weinberger, and Yixin Chen. Compressing neural networks with the hashing trick. In International conference on machine learning, pages 2285\u20132294. PMLR, 2015."},{"key":"e_1_3_2_1_4_1","volume-title":"Robust quantization: One model to rule them all. Advances in neural information processing systems, 33:5308\u20135317","author":"Chmiel Brian","year":"2020","unstructured":"Brian Chmiel, Ron Banner, Gil Shomron, Yury Nahshan, Alex Bronstein, Uri Weiser, et al. Robust quantization: One model to rule them all. Advances in neural information processing systems, 33:5308\u20135317, 2020."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","volume-title":"int8 (): 8-bit matrix multiplication for transformers at scale. Advances in neural information processing systems, 35:30318\u201330332","author":"Dettmers Tim","year":"2022","unstructured":"Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer. Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale. Advances in neural information processing systems, 35:30318\u201330332, 2022."},{"key":"e_1_3_2_1_7_1","volume-title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks. Advances in neural information processing systems, 33:18518\u201318529","author":"Dong Zhen","year":"2020","unstructured":"Zhen Dong, Zhewei Yao, Daiyaan Arfeen, Amir Gholami, Michael W Mahoney, and Kurt Keutzer. Hawq-v2: Hessian aware trace-weighted quantization of neural networks. Advances in neural information processing systems, 33:18518\u201318529, 2020."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"e_1_3_2_1_9_1","first-page":"26183","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","volume":"34","author":"Fang Yuxin","year":"2021","unstructured":"Yuxin Fang, Bencheng Liao, Xinggang Wang, Jiemin Fang, Jiyang Qi, Rui Wu, Jianwei Niu, and Wenyu Liu. You only look at one sequence: Rethinking transformer in vision through object detection. Advances in Neural Information Processing Systems, 34:26183\u201326197, 2021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Frankle Jonathan","year":"2019","unstructured":"Jonathan Frankle and Michael Carbin. The lottery ticket hypothesis: Finding sparse, trainable neural networks. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019. OpenReview.net, 2019."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00062"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"e_1_3_2_1_13_1","first-page":"463","volume-title":"Proceedings, Part XXVI 16","author":"Habi Hai Victor","unstructured":"Hai Victor Habi, Roy H Jennings, and Arnon Netzer. Hmq: Hardware friendly mixed precision quantization block for cnns. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXVI 16, pages 448\u2013463. Springer, 2020."},{"key":"e_1_3_2_1_14_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J Dally. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149, 2015."},{"key":"e_1_3_2_1_15_1","first-page":"778","volume-title":"Jian Sun. Deep Residual Learning for Image Recognition. In Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR '16","author":"He Kaiming","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep Residual Learning for Image Recognition. In Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR '16, pages 770\u2013778. IEEE, June 2016."},{"key":"e_1_3_2_1_16_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. CoRR, abs\/1704.04861","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. Mobilenets: Efficient convolutional neural networks for mobile vision applications. CoRR, abs\/1704.04861, 2017."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16950"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_20_1","volume-title":"A comprehensive evaluation of quantization strategies for large language models. arXiv preprint arXiv:2402.16775","author":"Jin Renren","year":"2024","unstructured":"Renren Jin, Jiangcun Du, Wuwei Huang, Wei Liu, Jian Luan, Bin Wang, and Deyi Xiong. A comprehensive evaluation of quantization strategies for large language models. arXiv preprint arXiv:2402.16775, 2024."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377555.3377900"},{"key":"e_1_3_2_1_22_1","first-page":"33","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky. Learning multiple layers of features from tiny images. pages 32\u201333, 2009."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586312"},{"key":"e_1_3_2_1_24_1","volume-title":"Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426","author":"Li Yuhang","year":"2021","unstructured":"Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, and Shi Gu. Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426, 2021."},{"key":"e_1_3_2_1_25_1","first-page":"679","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Li Zhuohan","year":"2023","unstructured":"Zhuohan Li, Lianmin Zheng, Yinmin Zhong, Vincent Liu, Ying Sheng, Xin Jin, Yanping Huang, Zhifeng Chen, Hao Zhang, Joseph E Gonzalez, et al. {AlpaServe}: Statistical multiplexing with model parallelism for deep learning serving. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23), pages 663\u2013679, 2023."},{"key":"e_1_3_2_1_26_1","first-page":"16205","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lin Chen","year":"2023","unstructured":"Chen Lin, Bo Peng, Zheyang Li, Wenming Tan, Ye Ren, Jun Xiao, and Shiliang Pu. Bit-shrinking: Limiting instantaneous sharpness for improving post-training quantization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pages 16196\u201316205, 2023."},{"key":"e_1_3_2_1_27_1","first-page":"87","article-title":"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. Awq: Activation-aware weight quantization for on-device llm compression and acceleration. Proceedings of Machine Learning and Systems, 6:87\u2013100, 2024.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17054"},{"key":"e_1_3_2_1_29_1","first-page":"10022","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pages 10012\u201310022, October 2021."},{"key":"e_1_3_2_1_30_1","volume-title":"Torchvision: Pytorch's computer vision library. https:\/\/github.com\/pytorch\/vision","author":"TorchVision","year":"2016","unstructured":"TorchVision maintainers and contributors. Torchvision: Pytorch's computer vision library. https:\/\/github.com\/pytorch\/vision, 2016."},{"key":"e_1_3_2_1_31_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_32_1","volume-title":"Azure public dataset. https:\/\/github.com\/Azure\/AzurePublicDataset","author":"Public Dataset Contributors Microsoft Azure","year":"2024","unstructured":"Microsoft Azure Public Dataset Contributors. Azure public dataset. https:\/\/github.com\/Azure\/AzurePublicDataset, 2024."},{"key":"e_1_3_2_1_33_1","volume-title":"Yelysei Bondarenko, Mart Van Baalen, and Tijmen Blankevoort. A white paper on neural network quantization. arXiv preprint arXiv:2106.08295","author":"Nagel Markus","year":"2021","unstructured":"Markus Nagel, Marios Fournarakis, Rana Ali Amjad, Yelysei Bondarenko, Mart Van Baalen, and Tijmen Blankevoort. A white paper on neural network quantization. arXiv preprint arXiv:2106.08295, 2021."},{"key":"e_1_3_2_1_34_1","unstructured":"NVIDIA. Parallel thread execution isa version 8.8. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640383"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519563"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00801"},{"key":"e_1_3_2_1_39_1","first-page":"411","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero, Qian Li, Neeraja J Yadwadkar, and Christos Kozyrakis. {INFaaS}: Automated model-less inference serving. In 2021 USENIX Annual Technical Conference (USENIX ATC 21), pages 397\u2013411, 2021."},{"issue":"1","key":"e_1_3_2_1_40_1","first-page":"3","article-title":"From tensors to fpgas","volume":"2","author":"Sharma Hardik","year":"2016","unstructured":"Hardik Sharma, Jongse Park, Balavinayagam Samynathan, Behnam Robatmili, Shahrzad Mirkhani, and Hadi Esmaeilzadeh. Dnnweaver v2. 0: From tensors to fpgas. Memory 2.1 (), page 3, 2016.","journal-title":"Memory"},{"key":"e_1_3_2_1_41_1","volume-title":"Megatron-lm: Training multibillion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. Megatron-lm: Training multibillion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053, 2019."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"e_1_3_2_1_43_1","unstructured":"Vijay Thakkar Pradeep Ramani Cris Cecka Aniket Shivam Honghao Lu Ethan Yan Jack Kosaian Mark Hoemmen Haicheng Wu Andrew Kerr Matt Nicely Duane Merrill Dustyn Blasig Fengqi Qiao Piotr Majcher Paul Springer Markus Hohnerbach Jin Wang and Manish Gupta. CUTLASS January 2023."},{"key":"e_1_3_2_1_44_1","first-page":"10357","volume-title":"International Conference on Machine Learning","volume":"139","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herve Jegou. Training data-efficient image transformers amp; distillation through attention. In International Conference on Machine Learning, volume 139, pages 10347\u201310357, July 2021."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"e_1_3_2_1_46_1","series-title":"Proceedings of Machine Learning Research","first-page":"9856","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Wang Peisong","unstructured":"Peisong Wang, Qiang Chen, Xiangyu He, and Jian Cheng. Towards accurate post-training network quantization via bit-split and stitching. In Hal Daum\u00e9 III and Aarti Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 9847\u20139856. PMLR, 13\u201318 Jul 2020."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3272341"},{"key":"e_1_3_2_1_48_1","volume-title":"timm: Pytorch image models. https:\/\/github.com\/huggingface\/pytorch-image-models","author":"Wightman Ross","year":"2021","unstructured":"Ross Wightman. timm: Pytorch image models. https:\/\/github.com\/huggingface\/pytorch-image-models, 2021. GitHub repository of Hugging Face's timm library."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"e_1_3_2_1_50_1","series-title":"Proceedings of Machine Learning Research","first-page":"38099","volume-title":"International Conference on Machine Learning, ICML","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Micka\u00ebl Seznec, Hao Wu, Julien Demouth, and Song Han. Smoothquant: Accurate and efficient post-training quantization for large language models. In Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett, editors, International Conference on Machine Learning, ICML 2023, 23\u201329 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of Machine Learning Research, pages 38087\u201338099. PMLR, 2023."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29553"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17269"},{"key":"e_1_3_2_1_53_1","first-page":"11886","volume-title":"International Conference on Machine Learning","author":"Yao Zhewei","unstructured":"Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael Mahoney, et al. Hawq-v3: Dyadic neural network quantization. In International Conference on Machine Learning, pages 11875\u201311886. PMLR, 2021."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17286"},{"key":"e_1_3_2_1_55_1","first-page":"1062","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Zhang Chengliang","year":"2019","unstructured":"Chengliang Zhang, Minchen Yu, Wei Wang, and Feng Yan. MArk: Exploiting cloud services for Cost-Effective, SLO-Aware machine learning inference serving. In 2019 USENIX Annual Technical Conference (USENIX ATC 19), pages 1049\u20131062, Renton, WA, July 2019. USENIX Association."},{"key":"e_1_3_2_1_56_1","first-page":"196","article-title":"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. Atom: Low-bit quantization for efficient and accurate llm serving. Proceedings of Machine Learning and Systems, 6:196\u2013209, 2024.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"e_1_3_2_1_58_1","first-page":"210","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong Yinmin","year":"2024","unstructured":"Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, and Hao Zhang. {DistServe}: Disaggregating prefill and decoding for goodput-optimized large language model serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pages 193\u2013210, 2024."}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767295.3769351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:23:32Z","timestamp":1780662212000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3769351"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":58,"alternative-id":["10.1145\/3767295.3769351","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3769351","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}