{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:31:37Z","timestamp":1773588697836,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","funder":[{"name":"Science and Technology Innovation Key R&amp;D Program of Chongqing","award":["CSTB2025TIAD-STX0016"],"award-info":[{"award-number":["CSTB2025TIAD-STX0016"]}]},{"name":"Science and Technology Innovation in Yongjiang 2035&#x5c;&quot; Key Technology Project","award":["2024Z283"],"award-info":[{"award-number":["2024Z283"]}]},{"name":"Ningbo Key R&amp;D Program","award":["2023Z214"],"award-info":[{"award-number":["2023Z214"]}]},{"name":"BTD Inc.","award":["20250X1"],"award-info":[{"award-number":["20250X1"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,22]]},"DOI":"10.1145\/3779212.3790153","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:55:26Z","timestamp":1773150926000},"page":"602-617","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DFVG: A Heterogeneous Architecture for Speculative Decoding with\n                    <u>D<\/u>\n                    raft-on-\n                    <u>F<\/u>\n                    PGA and\n                    <u>V<\/u>\n                    erify-on-\n                    <u>G<\/u>\n                    PU"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8624-8666","authenticated-orcid":false,"given":"Shaoqiang","family":"Lu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Eastern Institute of Technology, Ningbo, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3678-8942","authenticated-orcid":false,"given":"Yangbo","family":"Wei","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Eastern Institute of Technology, Ningbo, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1863-5690","authenticated-orcid":false,"given":"Junhong","family":"Qian","sequence":"additional","affiliation":[{"name":"Southest University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7679-0387","authenticated-orcid":false,"given":"Dongge","family":"Qin","sequence":"additional","affiliation":[{"name":"Southest University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4777-4777","authenticated-orcid":false,"given":"Shiji","family":"Gao","sequence":"additional","affiliation":[{"name":"Southest University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6376-3327","authenticated-orcid":false,"given":"Yizhi","family":"Ding","sequence":"additional","affiliation":[{"name":"Southest University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8390-5586","authenticated-orcid":false,"given":"Qifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Eastern Institute of Technology, Ningbo, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9939-8922","authenticated-orcid":false,"given":"Chen","family":"Wu","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin\uff0cEastern Institute of Technology, Ningbo, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1152-0055","authenticated-orcid":false,"given":"Xiao","family":"Shi","sequence":"additional","affiliation":[{"name":"Southest University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5266-3805","authenticated-orcid":false,"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology, Ningbo, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. GPT-4 Technical Report. In arXiv preprint arXiv:2303.08774. https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_2_1","volume-title":"PARD: Accelerating LLM Inference with Low-Cost Parallel Draft Model Adaptation. In arXiv preprint arXiv:2504.18583. https:\/\/arxiv.org\/abs\/2504.18583","author":"An Zihao","year":"2025","unstructured":"Zihao An, Huajun Bai, Ziqiong Liu, Dong Li, and Emad Barsoum. 2025. PARD: Accelerating LLM Inference with Low-Cost Parallel Draft Model Adaptation. In arXiv preprint arXiv:2504.18583. https:\/\/arxiv.org\/abs\/2504.18583"},{"key":"e_1_3_2_1_3_1","unstructured":"Anonymous. 2025. SpecBranch: Hybrid Drafting and Rollback-Aware Branch Parallelism. In arXiv preprint arXiv:2506.01979. https:\/\/arxiv.org\/abs\/2506.01979"},{"key":"e_1_3_2_1_4_1","unstructured":"Charlie Chen Sebastian Borgeaud Geoffrey Irving Jean-Baptiste Lespiau Laurent Sifre and John Jumper. 2023. Accelerating Large Language Model Decoding with Speculative Sampling. In arXiv preprint arXiv:2302.01318. https:\/\/arxiv.org\/abs\/2302.01318"},{"key":"e_1_3_2_1_5_1","volume-title":"SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models. In IEEE INFOCOM 2025-IEEE Conference on Computer Communications. IEEE, 1-10","author":"Chen Fahao","year":"2025","unstructured":"Fahao Chen, Peng Li, Tom H Luan, Zhou Su, and Jing Deng. 2025. SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models. In IEEE INFOCOM 2025-IEEE Conference on Computer Communications. IEEE, 1-10."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3692631"},{"key":"e_1_3_2_1_7_1","volume-title":"Georgi and contributors","author":"Gerganov","year":"2023","unstructured":"Gerganov, Georgi and contributors. 2023. llama.cpp: Inference of LLaMA Model in Pure C\/C. https:\/\/github.com\/ggml-org\/llama.cpp."},{"key":"e_1_3_2_1_8_1","unstructured":"Juyong Jiang Fan Wang Jiasi Shen Sungju Kim and Sunghun Kim. 2024. A Survey on Large Language Models for Code Generation. In arXiv preprint arXiv:2406.00515. https:\/\/arxiv.org\/abs\/2406.00515"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651352"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML).","author":"Li Yuhui","year":"2024","unstructured":"Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2024. EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty. In Proceedings of the 41st International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_12_1","unstructured":"Shaoqiang Lu Tiandong Zhao Ting-Jung Lin Rumin Zhang Chen Wu and Lei He. 2025. MCoreOPU: An FPGA-based Multi-Core Overlay Processor for Transformer-based Models. In ACM Transactions on Reconfigurable Technology and Systems (TRETS)."},{"key":"e_1_3_2_1_13_1","unstructured":"Kai Lv Honglin Guo Qipeng Guo and Xipeng Qiu. 2025. DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting. In arXiv preprint arXiv:2503.00784. https:\/\/arxiv.org\/abs\/2503.00784"},{"key":"e_1_3_2_1_14_1","volume-title":"AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration. In IEEE International Symposium on Circuits and Systems (ISCAS).","author":"McDanel Bradley","year":"2025","unstructured":"Bradley McDanel. 2025. AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration. In IEEE International Symposium on Circuits and Systems (ISCAS)."},{"key":"e_1_3_2_1_15_1","volume-title":"Alan Zhu, Lijie Yang, Xiaoxiang Shi, et al.","author":"Miao Xupeng","year":"2024","unstructured":"Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Zhengxin Zhang, Rae Ying Yee Wong, Alan Zhu, Lijie Yang, Xiaoxiang Shi, et al. 2024. SpecInfer: Accelerating Large Language Model Serving with Tree-Based Speculative Inference and Verification. In The 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)."},{"key":"e_1_3_2_1_16_1","unstructured":"Shervin Minaee Tomas Mikolov Narjes Nikzad Meysam Chenaghlu Richard Socher Xavier Amatriain and Jianfeng Gao. 2024. Large Language Models: A Survey. In arXiv preprint arXiv:2402.06196. https:\/\/arxiv.org\/abs\/2402.06196"},{"key":"e_1_3_2_1_17_1","unstructured":"PyTorch Foundation. 2023. Accelerating Generative AI with PyTorch II: GPT Fast. https:\/\/pytorch.org\/blog\/accelerating-generative-ai-2\/."},{"key":"e_1_3_2_1_18_1","volume-title":"Spector and Chris Re","author":"Benjamin","year":"2023","unstructured":"Benjamin S. Spector and Chris Re. 2023. Accelerating LLM Inference with Staged Speculative Decoding. In arXiv preprint arXiv:2308.04623. https:\/\/arxiv.org\/abs\/2308.04623"},{"key":"e_1_3_2_1_19_1","unstructured":"Qidong Su Christina Giannoula and Gennady Pekhimenko. 2023. The Synergy of Speculative Decoding and Batching in Serving Large Language Models. In arXiv preprint arXiv:2310.18813. https:\/\/arxiv.org\/abs\/2310.18813"},{"key":"e_1_3_2_1_20_1","unstructured":"Zhiqing Sun Zhuohan Li Haoqing Wang Di He Zi Lin and Zhihong Deng. 2019. Fast Structured Decoding for Sequence Models. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_21_1","volume-title":"Vicuna: An Open-source Chatbot Impressing GPT-4 with 90% ChatGPT Quality","author":"Team Vicuna","year":"2023","unstructured":"Vicuna Team. 2023. Vicuna: An Open-source Chatbot Impressing GPT-4 with 90% ChatGPT Quality. In Large Model Systems Organization."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of ICML 2025 (Poster).","author":"Tiwari Rishabh","year":"2025","unstructured":"Rishabh Tiwari, Haocheng Xi, Aditya Tomar, Coleman R. C. Hooper, Sehoon Kim, Maxwell Horton, Mahyar Najibi, Michael W. Mahoney, Kurt Keutzer, and Amir Gholami. 2025. QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache. In Proceedings of ICML 2025 (Poster)."},{"key":"e_1_3_2_1_23_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. In arXiv preprint arXiv:2307.09288. https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_1_24_1","volume-title":"Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism. In arXiv preprint arXiv:2505.23219. https:\/\/arxiv.org\/abs\/2505.23219","author":"Wei Jinhui","year":"2025","unstructured":"Jinhui Wei, Ye Huang, Yuhui Zhou, Jiazhi Jiang, Jiangsu Du, and Yutong Lu. 2025. Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism. In arXiv preprint arXiv:2505.23219. https:\/\/arxiv.org\/abs\/2505.23219"},{"key":"e_1_3_2_1_25_1","unstructured":"Zhuofan Wen Shangtong Gui and Yang Feng. 2024. Speculative Decoding with CTC-based Draft Model for LLM InferenceAcceleration. In NeurIPS 2024 Poster. https:\/\/arxiv.org\/abs\/2412.00061"},{"key":"e_1_3_2_1_26_1","volume-title":"Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding","author":"Xia Heming","unstructured":"Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, and Zhifang Sui. 2024. Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding. In Association for Computational Linguistics (ACL)."},{"key":"e_1_3_2_1_27_1","unstructured":"Minghao Yan Saurabh Agarwal and Shivaram Venkataraman. 2024. Decoding Speculative Decoding. In arXiv preprint arXiv:2402.01528. https:\/\/arxiv.org\/abs\/2402.01528"},{"key":"e_1_3_2_1_28_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 Technical Report. In arXiv preprint arXiv:2505.09388. https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_1_29_1","volume-title":"HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models. In arXiv preprint arXiv:2412.19925. https:\/\/arxiv.org\/abs\/2412.19925","author":"Yang Ze","year":"2024","unstructured":"Ze Yang, Yihong Jin, and Xinhe Xu. 2024. HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models. In arXiv preprint arXiv:2412.19925. https:\/\/arxiv.org\/abs\/2412.19925"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/AAI28260121"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375311"},{"key":"e_1_3_2_1_32_1","volume-title":"Yong Jae Lee, et al","author":"Yuan Zhihang","year":"2024","unstructured":"Zhihang Yuan, Yuzhang Shang, Yang Zhou, Zhen Dong, Zhe Zhou, Chenhao Xue, Bingzhe Wu, Zhikai Li, Qingyi Gu, Yong Jae Lee, et al. 2024. LLM Inference Unveiled: Survey and Roofline Model Insights. In arXiv preprint arXiv:2402.16363. https:\/\/arxiv.org\/abs\/2402.16363"},{"key":"e_1_3_2_1_33_1","volume-title":"Dovetail: A CPU\/GPU Heterogeneous Speculative Decoding for LLM Inference. In arXiv preprint arXiv:2412.18934. https:\/\/arxiv.org\/abs\/2412.18934","author":"Zhang Libo","year":"2024","unstructured":"Libo Zhang, Zhaoning Zhang, Baizhou Xu, Songzhu Mei, and Dongsheng Li. 2024. Dovetail: A CPU\/GPU Heterogeneous Speculative Decoding for LLM Inference. In arXiv preprint arXiv:2412.18934. https:\/\/arxiv.org\/abs\/2412.18934"},{"key":"e_1_3_2_1_34_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. 2022. OPT: Open Pre-Trained Transformer Language Models. In arXiv preprint arXiv:2205.01068. https:\/\/arxiv.org\/abs\/2205.01068"},{"key":"e_1_3_2_1_35_1","unstructured":"Ziyi Zhang Ziheng Jiang Chengquan Jiang Menghan Yu Size Zheng Haibin Lin Henry Hoffmann and Xin Liu. 2025. SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding. In arXiv preprint arXiv:2506.11309. https:\/\/arxiv.org\/abs\/2506.11309"},{"key":"e_1_3_2_1_36_1","volume-title":"ChatOPU: An FPGA-based Overlay Processor for Large Language Models with Unstructured Sparsity. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD).","author":"Zhao Tiandong","year":"2025","unstructured":"Tiandong Zhao, Shaoqiang Lu, Chen Wu, and Lei He. 2025. ChatOPU: An FPGA-based Overlay Processor for Large Language Models with Unstructured Sparsity. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)."},{"key":"e_1_3_2_1_37_1","unstructured":"Zixuan Zhou Xuefei Ning Ke Hong Tianyu Fu Jiaming Xu Shiyao Li Yuming Lou Luning Wang Zhihang Yuan Xiuhong Li et al. 2024. A Survey on Efficient Inference for Large Language Models. In arXiv preprint arXiv:2404.14294. https:\/\/arxiv.org\/abs\/2404.14294"},{"key":"e_1_3_2_1_38_1","unstructured":"Xiangwen Zhuge Xu Shen Zeyu Wang Fan Dang Xuan Ding Danyang Li Yahui Han Tianxiang Hao and Zheng Yang. 2025. SpecOffload: Unlocking Latent GPU Capacity for LLM Inference on Resource-Constrained Devices. In arXiv preprint arXiv:2505.10259. https:\/\/arxiv.org\/abs\/2505.10259"}],"event":{"name":"ASPLOS '26: 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Pittsburgh PA USA","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T14:07:12Z","timestamp":1773583632000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779212.3790153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":38,"alternative-id":["10.1145\/3779212.3790153","10.1145\/3779212"],"URL":"https:\/\/doi.org\/10.1145\/3779212.3790153","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}