{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:31:12Z","timestamp":1773588672536,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"name":"Shanghai Rising-Star Program","award":["24QB270620"],"award-info":[{"award-number":["24QB270620"]}]},{"name":"National Natural Science Foundation of China","award":["U21B2031"],"award-info":[{"award-number":["U21B2031"]}]},{"name":"National Natural Science Foundation of China","award":["62325405"],"award-info":[{"award-number":["62325405"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,22]]},"DOI":"10.1145\/3779212.3790224","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:55:26Z","timestamp":1773150926000},"page":"1832-1847","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["<i>SpeContext:<\/i>\n                    Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7000-6537","authenticated-orcid":false,"given":"Jiaming","family":"Xu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University; SII;, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0468-4592","authenticated-orcid":false,"given":"Jiayi","family":"Pan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University; Infinigence-AI;, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1335-2855","authenticated-orcid":false,"given":"Hanzhen","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7732-6347","authenticated-orcid":false,"given":"Yongkang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University; SII;, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6189-3251","authenticated-orcid":false,"given":"Jiancai","family":"Ye","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0849-3252","authenticated-orcid":false,"given":"Guohao","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University; Infinigence-AI; SII;, Shanghai, 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":"Large language models for mathematical reasoning: Progresses and challenges. arXiv preprint arXiv:2402.00157","author":"Ahn Janice","year":"2024","unstructured":"Janice Ahn, Rishu Verma, Renze Lou, Di Liu, Rui Zhang, and Wenpeng Yin. 2024. Large language models for mathematical reasoning: Progresses and challenges. arXiv preprint arXiv:2402.00157 (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"e_1_3_2_1_3_1","volume-title":"Unleashing 10,000 Word Generation from Long Context LLMs. arXiv preprint arXiv:2408.07055","author":"Bai Yushi","year":"2024","unstructured":"Yushi Bai, Jiajie Zhang, Xin Lv, Linzhi Zheng, Siqi Zhu, Lei Hou, Yuxiao Dong, Jie Tang, and Juanzi Li. 2024b. LongWriter: Unleashing 10,000 Word Generation from Long Context LLMs. arXiv preprint arXiv:2408.07055 (2024)."},{"key":"e_1_3_2_1_4_1","volume-title":"An intuitive proof of the data processing inequality. arXiv preprint arXiv:1107.0740","author":"Beaudry Normand J","year":"2011","unstructured":"Normand J Beaudry and Renato Renner. 2011. An intuitive proof of the data processing inequality. arXiv preprint arXiv:1107.0740 (2011)."},{"key":"e_1_3_2_1_5_1","unstructured":"Kyle Bell. 2025. Estimating LLM Inference Memory Requirements. [Online]. https:\/\/tensorwave.com\/blog\/estimating-llm-inference-memory-requirements."},{"key":"e_1_3_2_1_6_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_1_7_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]"},{"key":"e_1_3_2_1_8_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_9_1","unstructured":"Guohao Dai Ke Hong Qiuli Mao Xiuhong Li Jiaming Xu Haofeng Huang Hongtu Xia Xuefei Ning Shengen Yan Yun Liang et al. 2025. FlashDecodingNext: High Throughput LLM Inference with Latency and Memory Optimization. IEEE Trans. Comput. (2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691","author":"Dao Tri","year":"2023","unstructured":"Tri Dao. 2023. Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations. arXiv preprint arXiv:2305.14233","author":"Ding Ning","year":"2023","unstructured":"Ning Ding, Yulin Chen, Bokai Xu, Yujia Qin, Zhi Zheng, Shengding Hu, Zhiyuan Liu, Maosong Sun, and Bowen Zhou. 2023. Enhancing Chat Language Models by Scaling High-quality Instructional Conversations. arXiv preprint arXiv:2305.14233 (2023)."},{"key":"e_1_3_2_1_12_1","unstructured":"EpistemeAI. 2025. Introducing Reasoning Llama 3.2 1B: The Next Evolution in Conversational AI. [Online]. https:\/\/huggingface.co\/EpistemeAI\/Reasoning-Llama-3.2-1B-Instruct-v1.2."},{"key":"e_1_3_2_1_13_1","volume-title":"From llm reasoning to autonomous ai agents: A comprehensive review. arXiv preprint arXiv:2504.19678","author":"Ferrag Mohamed Amine","year":"2025","unstructured":"Mohamed Amine Ferrag, Norbert Tihanyi, and Merouane Debbah. 2025. From llm reasoning to autonomous ai agents: A comprehensive review. arXiv preprint arXiv:2504.19678 (2025)."},{"key":"e_1_3_2_1_14_1","unstructured":"Yuankun Fu. 2024a. LLM Inference Sizing and Performance Guidance. [Online]. https:\/\/platform.openai.com\/docs\/models\/o3."},{"key":"e_1_3_2_1_15_1","unstructured":"Yuankun Fu. 2024b. LLM Inference Sizing and Performance Guidance. [Online]. https:\/\/blogs.vmware.com\/cloud-foundation\/2024\/09\/25\/llm-inference-sizing-and-performance-guidance\/."},{"key":"e_1_3_2_1_16_1","volume-title":"LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions. arXiv preprint arXiv:2505.17134","author":"Gao Chaochen","year":"2025","unstructured":"Chaochen Gao, Xing Wu, Zijia Lin, Debing Zhang, and Songlin Hu. 2025. LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions. arXiv preprint arXiv:2505.17134 (2025)."},{"key":"e_1_3_2_1_17_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680","author":"Guo Taicheng","year":"2024","unstructured":"Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680 (2024)."},{"key":"e_1_3_2_1_19_1","unstructured":"Shibo Hao Yi Gu Haotian Luo Tianyang Liu Xiyan Shao Xinyuan Wang Shuhua Xie Haodi Ma Adithya Samavedhi Qiyue Gao et al. 2024. Llm reasoners: New evaluation library and analysis of step-by-step reasoning with large language models. arXiv preprint arXiv:2404.05221 (2024)."},{"key":"e_1_3_2_1_20_1","first-page":"148","article-title":"Flashdecoding: Faster large language model inference with asynchronization, flat gemm optimization, and heuristics","volume":"6","author":"Hong Ke","year":"2024","unstructured":"Ke Hong, Guohao Dai, Jiaming Xu, Qiuli Mao, Xiuhong Li, Jun Liu, Kangdi Chen, Yuhan Dong, and Yu Wang. 2024. Flashdecoding: Faster large language model inference with asynchronization, flat gemm optimization, and heuristics. Proceedings of Machine Learning and Systems, Vol. 6 (2024), 148-161.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_21_1","volume-title":"Estimating mutual information. Physical Review E\u2014Statistical, Nonlinear, and Soft Matter Physics","author":"Kraskov Alexander","year":"2004","unstructured":"Alexander Kraskov, Harald St\u00f6gbauer, and Peter Grassberger. 2004. Estimating mutual information. Physical Review E\u2014Statistical, Nonlinear, and Soft Matter Physics, Vol. 69, 6 (2004), 066138."},{"key":"e_1_3_2_1_22_1","volume-title":"On information and sufficiency. The annals of mathematical statistics","author":"Kullback Solomon","year":"1951","unstructured":"Solomon Kullback and Richard A Leibler. 1951. On information and sufficiency. The annals of mathematical statistics, Vol. 22, 1 (1951), 79-86."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626869"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.422"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning. 28935-28948","author":"Li Yuhui","year":"2024","unstructured":"Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2024b. EAGLE: speculative sampling requires rethinking feature uncertainty. In Proceedings of the 41st International Conference on Machine Learning. 28935-28948."},{"key":"e_1_3_2_1_28_1","volume-title":"Eagle-3: Scaling up inference acceleration of large language models via training-time test. arXiv preprint arXiv:2503.01840","author":"Li Yuhui","year":"2025","unstructured":"Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. 2025. Eagle-3: Scaling up inference acceleration of large language models via training-time test. arXiv preprint arXiv:2503.01840 (2025)."},{"key":"e_1_3_2_1_29_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024a. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Clusterkv: Manipulating llm kv cache in semantic space for recallable compression. arXiv preprint arXiv:2412.03213","author":"Liu Guangda","year":"2024","unstructured":"Guangda Liu, Chengwei Li, Jieru Zhao, Chenqi Zhang, and Minyi Guo. 2024b. Clusterkv: Manipulating llm kv cache in semantic space for recallable compression. arXiv preprint arXiv:2412.03213 (2024)."},{"key":"e_1_3_2_1_31_1","unstructured":"Tianyang Liu Canwen Xu and Julian McAuley. 2023. RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems. arXiv:2306.03091 [cs.CL]"},{"key":"e_1_3_2_1_32_1","volume-title":"Rasprostranenie zakona bol'shih chisel na velichiny, zavisyaschie drug ot druga. Izvestiya Fiziko-matematicheskogo obschestva pri Kazanskom universitete","author":"Markov Andrei Andreevich","year":"1906","unstructured":"Andrei Andreevich Markov. 1906. Rasprostranenie zakona bol'shih chisel na velichiny, zavisyaschie drug ot druga. Izvestiya Fiziko-matematicheskogo obschestva pri Kazanskom universitete, Vol. 15, 135-156 (1906), 18."},{"key":"e_1_3_2_1_33_1","volume-title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models. In The Twelfth International Conference on Learning Representations.","author":"Mirzadeh Seyed Iman","unstructured":"Seyed Iman Mirzadeh, Keivan Alizadeh-Vahid, Sachin Mehta, Carlo C del Mundo, Oncel Tuzel, Golnoosh Samei, Mohammad Rastegari, and Mehrdad Farajtabar. [n.d.]. ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2024.102545"},{"key":"e_1_3_2_1_35_1","volume-title":"Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Cand\u00e8s, and Tatsunori Hashimoto.","author":"Muennighoff Niklas","year":"2025","unstructured":"Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Cand\u00e8s, and Tatsunori Hashimoto. 2025. s1: Simple test-time scaling. arXiv preprint arXiv:2501.19393 (2025)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1097\/JS9.0000000000000719"},{"key":"e_1_3_2_1_37_1","volume-title":"YaRN: Efficient Context Window Extension of Large Language Models. In The Twelfth International Conference on Learning Representations.","author":"Peng Bowen","unstructured":"Bowen Peng, Jeffrey Quesnelle, Honglu Fan, and Enrico Shippole. [n.d.]. YaRN: Efficient Context Window Extension of Large Language Models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_38_1","volume-title":"A mathematical theory of communication. The Bell system technical journal","author":"Shannon Claude E","year":"1948","unstructured":"Claude E Shannon. 1948. A mathematical theory of communication. The Bell system technical journal, Vol. 27, 3 (1948), 379-423."},{"key":"e_1_3_2_1_39_1","volume-title":"Shadowkv: Kv cache in shadows for high-throughput long-context llm inference. arXiv preprint arXiv:2410.21465","author":"Sun Hanshi","year":"2024","unstructured":"Hanshi Sun, Li-Wen Chang, Wenlei Bao, Size Zheng, Ningxin Zheng, Xin Liu, Harry Dong, Yuejie Chi, and Beidi Chen. 2024. Shadowkv: Kv cache in shadows for high-throughput long-context llm inference. arXiv preprint arXiv:2410.21465 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Quest: Query-aware sparsity for efficient long-context llm inference. arXiv preprint arXiv:2406.10774","author":"Tang Jiaming","year":"2024","unstructured":"Jiaming Tang, Yilong Zhao, Kan Zhu, Guangxuan Xiao, Baris Kasikci, and Song Han. 2024. Quest: Query-aware sparsity for efficient long-context llm inference. arXiv preprint arXiv:2406.10774 (2024)."},{"key":"e_1_3_2_1_41_1","unstructured":"Gemma Team Aishwarya Kamath Johan Ferret Shreya Pathak Nino Vieillard Ramona Merhej Sarah Perrin Tatiana Matejovicova Alexandre Ram\u00e9 Morgane Rivi\u00e8re et al. 2025b. Gemma 3 technical report. arXiv preprint arXiv:2503.19786 (2025)."},{"key":"e_1_3_2_1_42_1","unstructured":"Kimi Team Yifan Bai Yiping Bao Guanduo Chen Jiahao Chen Ningxin Chen Ruijue Chen Yanru Chen Yuankun Chen Yutian Chen et al. 2025a. Kimi k2: Open agentic intelligence. arXiv preprint arXiv:2507.20534 (2025)."},{"key":"e_1_3_2_1_43_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_46_1","volume-title":"Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3730996"},{"key":"e_1_3_2_1_48_1","volume-title":"A survey on knowledge distillation of large language models. arXiv preprint arXiv:2402.13116","author":"Xu Xiaohan","year":"2024","unstructured":"Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. 2024. A survey on knowledge distillation of large language models. arXiv preprint arXiv:2402.13116 (2024)."},{"key":"e_1_3_2_1_49_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. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_50_1","volume-title":"Explainable Multi-hop Question Answering. In Conference on Empirical Methods in Natural Language Processing (EMNLP).","author":"Yang Zhilin","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. In Conference on Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_2_1_51_1","volume-title":"FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving. In Eighth Conference on Machine Learning and Systems.","author":"Ye Zihao","unstructured":"Zihao Ye, Lequn Chen, Ruihang Lai, Wuwei Lin, Yineng Zhang, Stephanie Wang, Tianqi Chen, Baris Kasikci, Vinod Grover, Arvind Krishnamurthy, et al., [n.d.]. FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving. In Eighth Conference on Machine Learning and Systems."},{"key":"e_1_3_2_1_52_1","unstructured":"Weizhi Zhang Yangning Li Yuanchen Bei Junyu Luo Guancheng Wan Liangwei Yang Chenxuan Xie Yuyao Yang Wei-Chieh Huang Chunyu Miao et al. 2025. From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents. arXiv preprint arXiv:2506.18959 (2025)."},{"key":"e_1_3_2_1_53_1","first-page":"193","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. 2024. : Disaggregating prefill and decoding for goodput-optimized large language model serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 193-210."},{"key":"e_1_3_2_1_54_1","volume-title":"Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-Fran\u00e7ois Kagy, and Rishabh Agarwal.","author":"Zhou Yongchao","year":"2023","unstructured":"Yongchao Zhou, Kaifeng Lyu, Ankit Singh Rawat, Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-Fran\u00e7ois Kagy, and Rishabh Agarwal. 2023. Distillspec: Improving speculative decoding via knowledge distillation. arXiv preprint arXiv:2310.08461 (2023)."}],"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":"2026-03-15T14:04:31Z","timestamp":1773583471000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779212.3790224"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":54,"alternative-id":["10.1145\/3779212.3790224","10.1145\/3779212"],"URL":"https:\/\/doi.org\/10.1145\/3779212.3790224","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"}}]}}