{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:18:15Z","timestamp":1783153095065,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"name":"Hong Kong Research Grants Council, General Research Fund","award":["15225023"],"award-info":[{"award-number":["15225023"]}]},{"name":"National Natural Science Foundation of China","award":["62302184"],"award-info":[{"award-number":["62302184"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792218","type":"proceedings-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:28:36Z","timestamp":1777296516000},"page":"5155-5164","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-Speculative Decoding for On-device MoE Acceleration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2694-9451","authenticated-orcid":false,"given":"Peirong","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0983-387X","authenticated-orcid":false,"given":"Wenchao","family":"Xu","sequence":"additional","affiliation":[{"name":"Division of Integrative Systems and Design, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7591-5315","authenticated-orcid":false,"given":"Haozhao","family":"Wang","sequence":"additional","affiliation":[{"name":"The School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:2401.06066","author":"Dai Damai","year":"2024","unstructured":"Damai Dai, Chengqi Deng, Chenggang Zhao, RX Xu, Huazuo Gao, Deli Chen, Jiashi Li, Wangding Zeng, Xingkai Yu, Yu Wu, et al., 2024. Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:2401.06066 (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3580745"},{"key":"e_1_3_2_1_3_1","volume-title":"Fast inference of mixture-of-experts language models with offloading. arXiv preprint arXiv:2312.17238","author":"Eliseev Artyom","year":"2023","unstructured":"Artyom Eliseev and Denis Mazur. 2023. Fast inference of mixture-of-experts language models with offloading. arXiv preprint arXiv:2312.17238 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676741"},{"key":"e_1_3_2_1_5_1","volume-title":"Promoe: Fast moe-based llm serving using proactive caching. arXiv preprint arXiv:2410.22134","author":"Song Xiaoniu","year":"2024","unstructured":"Xiaoniu Song, Zihang Zhong, Rong Chen, and Haibo Chen. 2024. Promoe: Fast moe-based llm serving using proactive caching. arXiv preprint arXiv:2410.22134 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Automation and Test in Europe Conference (DATE). IEEE, 1-7.","author":"Zhang Yujie","year":"2025","unstructured":"Yujie Zhang, Shivam Aggarwal, and Tulika Mitra. 2025. DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference. In 2025 Design, Automation and Test in Europe Conference (DATE). IEEE, 1-7."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.363"},{"key":"e_1_3_2_1_8_1","volume-title":"Fast inference from transformers via speculative decoding","author":"Leviathan Yaniv","year":"2023","unstructured":"Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2022. Fast inference from transformers via speculative decoding, 2023. URL https:\/\/arxiv.org\/abs\/2211.17192 (2022)."},{"key":"e_1_3_2_1_9_1","volume-title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty. In International Conference on Machine Learning. PMLR, 28935-28948","author":"Li Yuhui","year":"2024","unstructured":"Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2024. EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty. In International Conference on Machine Learning. PMLR, 28935-28948."},{"key":"e_1_3_2_1_10_1","volume-title":"FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Wang Haozhao","year":"2024","unstructured":"Haozhao Wang, Haoran Xu, Yichen Li, Yuan Xu, Ruixuan Li, and Tianwei Zhang. [n.d.]. FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024."},{"key":"e_1_3_2_1_11_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al., 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_12_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv Chujie Zheng Dayiheng Liu Fan Zhou Fei Huang Feng Hu Hao Ge Haoran Wei Huan Lin Jialong Tang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jing Zhou Jingren Zhou Junyang Lin Kai Dang Keqin Bao Kexin Yang Le Yu Lianghao Deng Mei Li Mingfeng Xue Mingze Li Pei Zhang Peng Wang Qin Zhu Rui Men Ruize Gao Shixuan Liu Shuang Luo Tianhao Li Tianyi Tang Wenbiao Yin Xingzhang Ren Xinyu Wang Xinyu Zhang Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yinger Zhang Yu Wan Yuqiong Liu Zekun Wang Zeyu Cui Zhenru Zhang Zhipeng Zhou and Zihan Qiu. 2025. Qwen3 Technical Report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_13_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645416"},{"key":"e_1_3_2_1_15_1","unstructured":"Aixin Liu Bei Feng Bin Wang Bingxuan Wang Bo Liu Chenggang Zhao Chengqi Dengr Chong Ruan Damai Dai Daya Guo et al. 2024. Deepseek-v2: A strong economical and efficient mixture-of-experts language model. arXiv preprint arXiv:2405.04434 (2024)."},{"key":"e_1_3_2_1_16_1","unstructured":"Jingyuan Liu Jianlin Su Xingcheng Yao Zhejun Jiang Guokun Lai Yulun Du Yidao Qin Weixin Xu Enzhe Lu Junjie Yan Yanru Chen Huabin Zheng Yibo Liu Shaowei Liu Bohong Yin Weiran He Han Zhu Yuzhi Wang Jianzhou Wang Mengnan Dong Zheng Zhang Yongsheng Kang Hao Zhang Xinran Xu Yutao Zhang Yuxin Wu Xinyu Zhou and Zhilin Yang. 2025. Muon is Scalable for LLM Training. arXiv:2502.16982 [cs.LG] https:\/\/arxiv.org\/abs\/2502.16982"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.456"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3302"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_22_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_1_23_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 [cs.LG] https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.EMNLP-MAIN.550"},{"key":"e_1_3_2_1_25_1","volume-title":"Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958","author":"Lin Stephanie","year":"2021","unstructured":"Stephanie Lin, Jacob Hilton, and Owain Evans. 2021. Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958 (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models. arXiv preprint arXiv:2402.07033","author":"Keisuke Kamahori","year":"2024","unstructured":"Keisuke Kamahori et al., 2024. Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models. arXiv preprint arXiv:2402.07033 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of Machine Learning and Systems, P. Gibbons, G. Pekhimenko, and C. De Sa (Eds.)","volume":"6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. In Proceedings of Machine Learning and Systems, P. Gibbons, G. Pekhimenko, and C. De Sa (Eds.), Vol. 6. 87-100. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/42a452cbafa9dd64e9ba4aa95cc1ef21-Paper-Conference.pdf"},{"key":"e_1_3_2_1_28_1","volume-title":"Confidence in the reasoning of large language models. arXiv preprint arXiv:2412.15296","author":"Pawitan Yudi","year":"2024","unstructured":"Yudi Pawitan and Chris Holmes. 2024. Confidence in the reasoning of large language models. arXiv preprint arXiv:2412.15296 (2024)."},{"key":"e_1_3_2_1_29_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_30_1","volume-title":"OPTQ: Accurate Quantization for Generative Pre-trained Transformers. In The Eleventh International Conference on Learning Representations.","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2023. OPTQ: Accurate Quantization for Generative Pre-trained Transformers. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of Machine Learning and Systems, P. Gibbons, G. Pekhimenko, and C. De Sa (Eds.)","volume":"6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. In Proceedings of Machine Learning and Systems, P. Gibbons, G. Pekhimenko, and C. De Sa (Eds.), Vol. 6. 87-100. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/42a452cbafa9dd64e9ba4aa95cc1ef21-Paper-Conference.pdf"},{"key":"e_1_3_2_1_32_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=eFWG9Cy3WK","author":"Li Pingzhi","year":"2024","unstructured":"Pingzhi Li, Zhenyu Zhang, Prateek Yadav, Yi-Lin Sung, Yu Cheng, Mohit Bansal, and Tianlong Chen. 2024. Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=eFWG9Cy3WK"},{"key":"e_1_3_2_1_33_1","volume-title":"MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators. In Eighth Conference on Machine Learning and Systems. https:\/\/openreview.net\/forum?id=NXVXiJmhe1","author":"Huang Beichen","year":"2025","unstructured":"Beichen Huang, Yueming Yuan, ZELEI SHAO, and Minjia Zhang. 2025. MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators. In Eighth Conference on Machine Learning and Systems. https:\/\/openreview.net\/forum?id=NXVXiJmhe1"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Leviathan Yaniv","year":"2023","unstructured":"Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2023. Fast inference from transformers via speculative decoding. In International Conference on Machine Learning. PMLR, 19274-19286."},{"key":"e_1_3_2_1_35_1","volume-title":"Parallel speculative decoding with adaptive draft length. arXiv e-prints","author":"Liu Tianyu","year":"2024","unstructured":"Tianyu Liu, Yun Li, Qitan Lv, Kai Liu, Jianchen Zhu, and Winston Hu. 2024. Parallel speculative decoding with adaptive draft length. arXiv e-prints (2024), arXiv-2408."},{"key":"e_1_3_2_1_36_1","volume-title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. In International Conference on Machine Learning. PMLR, 5209-5235","author":"Cai Tianle","year":"2024","unstructured":"Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D Lee, Deming Chen, and Tri Dao. 2024. Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. In International Conference on Machine Learning. PMLR, 5209-5235."},{"key":"e_1_3_2_1_37_1","volume-title":"MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE. arXiv preprint arXiv:2505.19645","author":"Huang Zongle","year":"2025","unstructured":"Zongle Huang, Lei Zhu, Zongyuan Zhan, Ting Hu, Weikai Mao, Xianzhi Yu, Yongpan Liu, and Tianyu Zhang. 2025. MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE. arXiv preprint arXiv:2505.19645 (2025)."},{"key":"e_1_3_2_1_38_1","volume-title":"HALO: Semantic-Aware Distributed LLM Inference in Lossy Edge Network. arXiv:2601.11676 [cs.DC] https:\/\/arxiv.org\/abs\/2601.11676","author":"Zheng Peirong","year":"2026","unstructured":"Peirong Zheng, Wenchao Xu, Haozhao Wang, Jinyu Chen, and Xuemin Shen. 2026. HALO: Semantic-Aware Distributed LLM Inference in Lossy Edge Network. arXiv:2601.11676 [cs.DC] https:\/\/arxiv.org\/abs\/2601.11676"},{"key":"e_1_3_2_1_39_1","volume-title":"HetuMoE: An efficient trillion-scale mixture-of-expert distributed training system. arXiv preprint arXiv:2203.14685","author":"Nie Xiaonan","year":"2022","unstructured":"Xiaonan Nie, Pinxue Zhao, Xupeng Miao, Tong Zhao, and Bin Cui. 2022. HetuMoE: An efficient trillion-scale mixture-of-expert distributed training system. arXiv preprint arXiv:2203.14685 (2022)."},{"key":"e_1_3_2_1_40_1","volume-title":"Shortcut-connected expert parallelism for accelerating mixture-of-experts. arXiv preprint arXiv:2404.05019","author":"Cai Weilin","year":"2024","unstructured":"Weilin Cai, Juyong Jiang, Le Qin, Junwei Cui, Sunghun Kim, and Jiayi Huang. 2024. Shortcut-connected expert parallelism for accelerating mixture-of-experts. arXiv preprint arXiv:2404.05019 (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731025"},{"key":"e_1_3_2_1_42_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Liu Xinyi","year":"2025","unstructured":"Xinyi Liu, Yujie Wang, Fangcheng Fu, Xupeng Miao, Shenhan Zhu, Xiaonan Nie, and Bin Cui. 2025. Netmoe: Accelerating moe training through dynamic sample placement. In The Thirteenth International Conference on Learning Representations."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:45:36Z","timestamp":1783151136000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792218"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":42,"alternative-id":["10.1145\/3774904.3792218","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792218","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}