{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:30:44Z","timestamp":1773588644361,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2027,3,22]],"date-time":"2027-03-22T00:00:00Z","timestamp":1805673600000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["CCF-2119184"],"award-info":[{"award-number":["CCF-2119184"]}]},{"name":"National Science Foundation","award":["CNS-2313190"],"award-info":[{"award-number":["CNS-2313190"]}]},{"name":"National Science Foundation","award":["CCF-1822949"],"award-info":[{"award-number":["CCF-1822949"]}]},{"name":"National Science Foundation","award":["CNS-1956180"],"award-info":[{"award-number":["CNS-1956180"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,22]]},"DOI":"10.1145\/3779212.3790246","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:55:26Z","timestamp":1773150926000},"page":"2197-2211","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SwiftSpec: Disaggregated Speculative Decoding and Fused Kernels for Low-Latency LLM Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4336-6341","authenticated-orcid":false,"given":"Ziyi","family":"Zhang","sequence":"first","affiliation":[{"name":"ByteDance Seed, Bellevue, WA, USA and University of Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7732-4391","authenticated-orcid":false,"given":"Ziheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9356-6034","authenticated-orcid":false,"given":"Chengquan","family":"Jiang","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8240-8144","authenticated-orcid":false,"given":"Menghan","family":"Yu","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9471-1780","authenticated-orcid":false,"given":"Size","family":"Zheng","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4879-5335","authenticated-orcid":false,"given":"Haibin","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8346-3323","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0816-8150","authenticated-orcid":false,"given":"Henry","family":"Hoffmann","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Branden Butler Sixing Yu Arya Mazaheri and Ali Jannesari. 2024. PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation. arXiv:2407.11798 [cs.CL] https:\/\/arxiv.org\/abs\/2407.11798","DOI":"10.1109\/SC41406.2024.00046"},{"key":"e_1_3_2_1_2_1","volume-title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. arXiv:2401.10774 [cs.LG] https:\/\/arxiv.org\/abs\/2401.10774","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. arXiv:2401.10774 [cs.LG] https:\/\/arxiv.org\/abs\/2401.10774"},{"key":"e_1_3_2_1_3_1","volume-title":"Large Language Models vs","author":"Caramancion Kevin Matthe","unstructured":"Kevin Matthe Caramancion. 2024. Large Language Models vs. Search Engines: Evaluating User Preferences Across Varied Information Retrieval Scenarios. arXiv:2401.05761 [cs.IR] https:\/\/arxiv.org\/abs\/2401.05761"},{"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. arXiv:2302.01318 [cs.CL] https:\/\/arxiv.org\/abs\/2302.01318"},{"key":"e_1_3_2_1_5_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_6_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_7_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arXiv:2110.14168 [cs.LG] https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Tri Dao Daniel Y. Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. arXiv:2205.14135 [cs.LG] https:\/\/arxiv.org\/abs\/2205.14135","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_2_1_9_1","unstructured":"DeepSeek-AI Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma PeiyiWang Xiao Bi Xiaokang Zhang Xingkai Yu Yu Wu Z. F. Wu Zhibin Gou Zhihong Shao Zhuoshu Li Ziyi Gao Aixin Liu Bing Xue Bingxuan Wang Bochao Wu Bei Feng Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fucong Dai Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Han Bao Hanwei Xu HaochengWang Honghui Ding Huajian Xin Huazuo Gao Hui Qu Hui Li Jianzhong Guo Jiashi Li Jiawei Wang Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li J. L. Cai Jiaqi Ni Jian Liang Jin Chen Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Liang Zhao Litong Wang Liyue Zhang Lei Xu Leyi Xia Mingchuan Zhang Minghua Zhang Minghui Tang Meng Li Miaojun Wang Mingming Li Ning Tian Panpan Huang Peng Zhang Qiancheng Wang Qinyu Chen Qiushi Du Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang R. J. Chen R. L. Jin Ruyi Chen Shanghao Lu Shangyan Zhou Shanhuang Chen Shengfeng Ye ShiyuWang Shuiping Yu Shunfeng Zhou Shuting Pan S. S. Li Shuang Zhou Shaoqing Wu Shengfeng Ye Tao Yun Tian Pei Tianyu Sun T. Wang Wangding Zeng Wanjia Zhao Wen Liu Wenfeng Liang Wenjun Gao Wenqin Yu Wentao Zhang W. L. Xiao Wei An Xiaodong Liu Xiaohan Wang Xiaokang Chen Xiaotao Nie Xin Cheng Xin Liu Xin Xie Xingchao Liu Xinyu Yang Xinyuan Li Xuecheng Su Xuheng Lin X. Q. Li Xiangyue Jin Xiaojin Shen Xiaosha Chen Xiaowen Sun Xiaoxiang Wang Xinnan Song Xinyi Zhou Xianzu Wang Xinxia Shan Y. K. Li Y. Q. Wang Y. X. Wei Yang Zhang Yanhong Xu Yao Li Yao Zhao Yaofeng Sun Yaohui Wang Yi Yu Yichao Zhang Yifan Shi Yiliang Xiong Ying He Yishi Piao Yisong Wang Yixuan Tan Yiyang Ma Yiyuan Liu Yongqiang Guo Yuan Ou Yuduan Wang Yue Gong Yuheng Zou Yujia He Yunfan Xiong Yuxiang Luo Yuxiang You Yuxuan Liu Yuyang Zhou Y. X. Zhu Yanhong Xu Yanping Huang Yaohui Li Yi Zheng Yuchen Zhu Yunxian Ma Ying Tang Yukun Zha Yuting Yan Z. Z. Ren Zehui Ren Zhangli Sha Zhe Fu Zhean Xu Zhenda Xie Zhengyan Zhang Zhewen Hao Zhicheng Ma Zhigang Yan Zhiyu Wu Zihui Gu Zijia Zhu Zijun Liu Zilin Li Ziwei Xie Ziyang Song Zizheng Pan Zhen Huang Zhipeng Xu Zhongyu Zhang and Zhen Zhang. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_1_10_1","volume-title":"GitHub Copilot - Latency Secrets and Lessons. https:\/\/www.youtube.com\/watch?v=zemBW3diXIs Talk cites sub-200 ms completion target","author":"Engineering GitHub","year":"2025","unstructured":"GitHub Engineering. 2025. GitHub Copilot - Latency Secrets and Lessons. https:\/\/www.youtube.com\/watch?v=zemBW3diXIs Talk cites sub-200 ms completion target; accessed 2025-07-11."},{"key":"e_1_3_2_1_11_1","volume-title":"DAPPLE: A Pipelined Data Parallel Approach for Training Large Models. arXiv:2007.01045 [cs.DC] https:\/\/arxiv.org\/abs\/2007.01045","author":"Fan Shiqing","year":"2020","unstructured":"Shiqing Fan, Yi Rong, Chen Meng, Zongyan Cao, Siyu Wang, Zhen Zheng, Chuan Wu, Guoping Long, Jun Yang, Lixue Xia, Lansong Diao, Xiaoyong Liu, and Wei Lin. 2020. DAPPLE: A Pipelined Data Parallel Approach for Training Large Models. arXiv:2007.01045 [cs.DC] https:\/\/arxiv.org\/abs\/2007.01045"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 18th USENIX Conference on Operating Systems Design and Implementation","author":"Fu Yao","year":"2024","unstructured":"Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian Brabete, Dmitrii Ustiugov, Yuvraj Patel, and Luo Mai. 2024. ServerlessLLM: low-latency serverless inference for large language models. In Proceedings of the 18th USENIX Conference on Operating Systems Design and Implementation (Santa Clara, CA, USA) (OSDI'24). USENIX Association, USA, Article 8, 19 pages."},{"key":"e_1_3_2_1_13_1","unstructured":"Daya Guo Canwen Xu Nan Duan Jian Yin and Julian McAuley. 2023. LongCoder: A Long-Range Pre-trained Language Model for Code Completion. arXiv:2306.14893 [cs.SE] https:\/\/arxiv.org\/abs\/2306.14893"},{"key":"e_1_3_2_1_14_1","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Y. Wu Y. K. Li Fuli Luo Yingfei Xiong and Wenfeng Liang. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence. arXiv:2401.14196 [cs.SE] https:\/\/arxiv.org\/abs\/2401.14196"},{"key":"e_1_3_2_1_15_1","unstructured":"Heyang Huang Cunchen Hu Jiaqi Zhu Ziyuan Gao Liangliang Xu Yizhou Shan Yungang Bao Sun Ninghui Tianwei Zhang and SaWang. 2025. DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving. arXiv:2506.13497 [cs.DC] https:\/\/arxiv.org\/abs\/2506.13497"},{"key":"e_1_3_2_1_16_1","volume-title":"Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen.","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism. arXiv:1811.06965 [cs.CV] https:\/\/arxiv.org\/abs\/1811.06965"},{"key":"e_1_3_2_1_17_1","volume-title":"Razvan Mihai Popescu, and Arie van Deursen","author":"Izadi Maliheh","year":"2024","unstructured":"Maliheh Izadi, Jonathan Katzy, Tim van Dam, Marc Otten, Razvan Mihai Popescu, and Arie van Deursen. 2024. Language Models for Code Completion: A Practical Evaluation. arXiv:2402.16197 [cs.SE] https:\/\/arxiv.org\/abs\/2402.16197"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_19_1","volume-title":"Joseph E. Gonzalez, Hao Zhang, and Ion Stoica.","author":"Kwon Woosuk","year":"2023","unstructured":"Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. arXiv:2309.06180 [cs.LG] https:\/\/arxiv.org\/abs\/2309.06180"},{"key":"e_1_3_2_1_20_1","unstructured":"Yaniv Leviathan Matan Kalman and Yossi Matias. 2023. Fast Inference from Transformers via Speculative Decoding. arXiv:2211.17192 [cs.LG] https:\/\/arxiv.org\/abs\/2211.17192"},{"key":"e_1_3_2_1_21_1","unstructured":"Yuhui Li Fangyun Wei Chao Zhang and Hongyang Zhang. 2024. EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees. arXiv:2406.16858 [cs.CL] https:\/\/arxiv.org\/abs\/2406.16858"},{"key":"e_1_3_2_1_22_1","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:2503.01840 [cs.CL] https:\/\/arxiv.org\/abs\/2503.01840"},{"key":"e_1_3_2_1_23_1","volume-title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration. arXiv:2306.00978 [cs.CL] https:\/\/arxiv.org\/abs\/2306.00978","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 LLM Compression and Acceleration. arXiv:2306.00978 [cs.CL] https:\/\/arxiv.org\/abs\/2306.00978"},{"key":"e_1_3_2_1_24_1","unstructured":"Tianyu Liu Yun Li Qitan Lv Kai Liu Jianchen Zhu and Winston Hu. 2024. Parallel Speculative Decoding with Adaptive Draft Length. arXiv:2408.11850 [cs.CL] https:\/\/arxiv.org\/abs\/2408.11850"},{"key":"e_1_3_2_1_25_1","unstructured":"Xiaoxuan Liu Cade Daniel Langxiang Hu Woosuk Kwon Zhuohan Li Xiangxi Mo Alvin Cheung Zhijie Deng Ion Stoica and Hao Zhang. 2024. Optimizing Speculative Decoding for Serving Large Language Models Using Goodput. arXiv:2406.14066 [cs.AI] https:\/\/arxiv.org\/abs\/2406.14066"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Yuhan Liu Hanchen Li Yihua Cheng Siddhant Ray Yuyang Huang Qizheng Zhang Kuntai Du Jiayi Yao Shan Lu Ganesh Ananthanarayanan Michael Maire Henry Hoffmann Ari Holtzman and Junchen Jiang. 2024. CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving. arXiv:2310.07240 [cs.NI] https:\/\/arxiv.org\/abs\/2310.07240","DOI":"10.1145\/3651890.3672274"},{"key":"e_1_3_2_1_27_1","volume-title":"AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration. arXiv:2410.17375 [cs.CL] https:\/\/arxiv.org\/abs\/2410.17375","author":"McDanel Bradley","year":"2024","unstructured":"Bradley McDanel. 2024. AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration. arXiv:2410.17375 [cs.CL] https:\/\/arxiv.org\/abs\/2410.17375"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"e_1_3_2_1_29_1","volume-title":"Caglar Gulcehre, and Bing Xiang.","author":"Nallapati Ramesh","year":"2016","unstructured":"Ramesh Nallapati, Bowen Zhou, Cicero Nogueira dos santos, Caglar Gulcehre, and Bing Xiang. 2016. Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond. arXiv:1602.06023 [cs.CL] https:\/\/arxiv.org\/abs\/1602.06023"},{"key":"e_1_3_2_1_30_1","unstructured":"Nvidia. [n.d.]. Nvidia\/TENSORRT-LLM: A TensorRT Toolbox for Optimized Large Language Model Inference. https:\/\/github.com\/NVIDIA\/TensorRT-LLM."},{"key":"e_1_3_2_1_31_1","unstructured":"NVIDIA. 2024. Low-Latency Inference Chapter 1: Up to 1.9\u00d7 Higher Llama-3-70B Performance with Medusa on NVIDIA HGX H200 with NVLink Switch. https:\/\/developer.nvidia.com\/blog\/low-latencyinference- chapter-1-up-to-1-9x-higher-llama-3-1-performancewith-medusa-on-nvidia-hgx-h200-with-nvlink-switch\/ Reports 268 tokens\/s in 1-request mode; accessed 2025-07-11."},{"key":"e_1_3_2_1_32_1","unstructured":"OpenAI. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_33_1","volume-title":"Splitwise: Efficient generative LLM inference using phase splitting. arXiv:2311.18677 [cs.AR] https:\/\/arxiv.org\/abs\/2311.18677","author":"Patel Pratyush","year":"2024","unstructured":"Pratyush Patel, Esha Choukse, Chaojie Zhang, Aashaka Shah, \u00cd\u00f1igo Goiri, Saeed Maleki, and Ricardo Bianchini. 2024. Splitwise: Efficient generative LLM inference using phase splitting. arXiv:2311.18677 [cs.AR] https:\/\/arxiv.org\/abs\/2311.18677"},{"key":"e_1_3_2_1_34_1","unstructured":"Noam Shazeer. 2020. GLU Variants Improve Transformer. arXiv:2002.05202 [cs.LG] https:\/\/arxiv.org\/abs\/2002.05202"},{"key":"e_1_3_2_1_35_1","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv:1909.08053 [cs.CL] https:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_2_1_36_1","unstructured":"Volker Strobel Marco Dorigo and Mario Fritz. 2024. LLM2Swarm: Robot Swarms that Responsively Reason Plan and Collaborate through LLMs. arXiv:2410.11387 [cs.RO] https:\/\/arxiv.org\/abs\/2410.11387"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems","author":"Svirschevski Ruslan","year":"2025","unstructured":"Ruslan Svirschevski, Avner May, Zhuoming Chen, Beidi Chen, Zhihao Jia, and Max Ryabinin. 2025. SpecExec: massively parallel speculative decoding for interactive LLM inference on consumer devices. In Proceedings of the 38th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS '24). Curran Associates Inc., Red Hook, NY, USA, Article 522, 27 pages."},{"key":"e_1_3_2_1_38_1","unstructured":"Tatsu-Lab. [n.d.]. Tatsu-Lab\/STANFORD-ALPACA: Code and documentation to train Stanford's alpaca models and generate the data. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_1_39_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. 2023. CUTLASS. https:\/\/github.com\/NVIDIA\/cutlass"},{"key":"e_1_3_2_1_40_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971 [cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_1_41_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arXiv:1706.03762 [cs.CL] https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_2_1_42_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arXiv:1706.03762 [cs.CL] https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_2_1_43_1","unstructured":"Guangxuan Xiao Ji Lin Mickael Seznec HaoWu Julien Demouth and Song Han. 2024. SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models. arXiv:2211.10438 [cs.CL] https:\/\/arxiv.org\/abs\/2211.10438"},{"key":"e_1_3_2_1_44_1","volume-title":"When Search Engine Services meet Large Language Models: Visions and Challenges. arXiv:2407","author":"Xiong Haoyi","year":"2024","unstructured":"Haoyi Xiong, Jiang Bian, Yuchen Li, Xuhong Li, Mengnan Du, Shuaiqiang Wang, Dawei Yin, and Sumi Helal. 2024. When Search Engine Services meet Large Language Models: Visions and Challenges. arXiv:2407.00128 [cs.IR] https:\/\/arxiv.org\/abs\/2407.00128"},{"key":"e_1_3_2_1_45_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang Guanting Dong Haoran Wei Huan Lin Jialong Tang Jialin Wang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Ma Jianxin Yang Jin Xu Jingren Zhou Jinze Bai Jinzheng He Junyang Lin Kai Dang Keming Lu Keqin Chen Kexin Yang Mei Li Mingfeng Xue Na Ni Pei Zhang Peng Wang Ru Peng Rui Men Ruize Gao Runji Lin Shijie Wang Shuai Bai Sinan Tan Tianhang Zhu Tianhao Li Tianyu Liu Wenbin Ge Xiaodong Deng Xiaohuan Zhou Xingzhang Ren Xinyu Zhang Xipin Wei Xuancheng Ren Xuejing Liu Yang Fan Yang Yao Yichang Zhang Yu Wan Yunfei Chu Yuqiong Liu Zeyu Cui Zhenru Zhang Zhifang Guo and Zhihao Fan. 2024. Qwen2 Technical Report. arXiv:2407.10671 [cs.CL] https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_2_1_46_1","volume-title":"FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving. In Eighth Conference on Machine Learning and Systems. https:\/\/openreview.net\/forum?id=RXPofAsL8F","author":"Ye Zihao","year":"2025","unstructured":"Zihao Ye, Lequn Chen, Ruihang Lai, Wuwei Lin, Yineng Zhang, Stephanie Wang, Tianqi Chen, Baris Kasikci, Vinod Grover, Arvind Krishnamurthy, and Luis Ceze. 2025. FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving. In Eighth Conference on Machine Learning and Systems. https:\/\/openreview.net\/forum?id=RXPofAsL8F"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611663"},{"key":"e_1_3_2_1_48_1","volume-title":"Guy Van den Broeck, and Aditya Grover","author":"Zhao Siyan","year":"2024","unstructured":"Siyan Zhao, Daniel Israel, Guy Van den Broeck, and Aditya Grover. 2024. Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models. arXiv:2404.09529 [cs.LG] https:\/\/arxiv.org\/abs\/2404.09529"},{"key":"e_1_3_2_1_49_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang ZhanghaoWu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric P. Xing Hao Zhang Joseph E. Gonzalez and Ion Stoica. 2023. Judging LLM-asa-Judge with MT-Bench and Chatbot Arena. arXiv:2306.05685 [cs.CL] https:\/\/arxiv.org\/abs\/2306.05685"},{"key":"e_1_3_2_1_50_1","volume-title":"Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng.","author":"Zheng Lianmin","year":"2024","unstructured":"Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng. 2024. SGLang: Efficient Execution of Structured Language Model Programs. arXiv:2312.07104 [cs.AI] https:\/\/arxiv.org\/abs\/2312.07104"},{"key":"e_1_3_2_1_51_1","first-page":"193","volume-title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving. In 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. DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 193-210. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/zhongyinmin"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Enshen Zhou Qi Su Cheng Chi Zhizheng Zhang Zhongyuan Wang Tiejun Huang Lu Sheng and He Wang. 2025. Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection. arXiv:2412.04455 [cs.RO] https:\/\/arxiv.org\/abs\/2412.04455","DOI":"10.1109\/CVPR52734.2025.00649"},{"key":"e_1_3_2_1_53_1","unstructured":"Ruidong Zhu Ziheng Jiang Chao Jin Peng Wu Cesar A. Stuardo Dongyang Wang Xinlei Zhang Huaping Zhou Haoran Wei Yang Cheng Jianzhe Xiao Xinyi Zhang Lingjun Liu Haibin Lin Li-Wen Chang Jianxi Ye Xiao Yu Xuanzhe Liu Xin Jin and Xin Liu. 2025. MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism. arXiv:2504.02263 [cs.DC] https:\/\/arxiv.org\/abs\/2504.02263"}],"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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3779212.3790246","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T14:00:31Z","timestamp":1773583231000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779212.3790246"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":53,"alternative-id":["10.1145\/3779212.3790246","10.1145\/3779212"],"URL":"https:\/\/doi.org\/10.1145\/3779212.3790246","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"}}]}}