{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:08:06Z","timestamp":1780664886406,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":68,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402050"],"award-info":[{"award-number":["62402050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3769346","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"1144-1159","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TailorLLM: Collaborative End-Cloud Inference of Large and Small Language Models Based on Low-Rank Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6605-0920","authenticated-orcid":false,"given":"Zian","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8174-0593","authenticated-orcid":false,"given":"Ziyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6607-5154","authenticated-orcid":false,"given":"Haonan","family":"Jin","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9747-8539","authenticated-orcid":false,"given":"Jie","family":"Xing","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0674-7864","authenticated-orcid":false,"given":"Lanshan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Machine Learning. PMLR, 265\u2013279","author":"Aghajanyan Armen","year":"2023","unstructured":"Armen Aghajanyan, Lili Yu, Alexis Conneau, Wei-Ning Hsu, Karen Hambardzumyan, Susan Zhang, Stephen Roller, Naman Goyal, Omer Levy, and Luke Zettlemoyer. 2023. Scaling laws for generative mixed-modal language models. In International Conference on Machine Learning. PMLR, 265\u2013279."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1620"},{"key":"e_1_3_2_1_3_1","first-page":"12312","article-title":"Distributed Inference and Fine-tuning of Large Language Models Over The Internet","volume":"36","author":"Borzunov Alexander","year":"2023","unstructured":"Alexander Borzunov, Max Ryabinin, Artem Chumachenko, Dmitry Baranchuk, Tim Dettmers, Younes Belkada, Pavel Samygin, and Colin A Raffel. 2023. Distributed Inference and Fine-tuning of Large Language Models Over The Internet. In Advances in Neural Information Processing Systems, Vol. 36. 12312\u201312331.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00099"},{"key":"e_1_3_2_1_6_1","volume-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices. arXiv preprint arXiv:2312.16886 2, 6","author":"Chu Xiangxiang","year":"2023","unstructured":"Xiangxiang Chu, Limeng Qiao, Xinyang Lin, Shuang Xu, Yang Yang, Yiming Hu, Fei Wei, Xinyu Zhang, Bo Zhang, Xiaolin Wei, et al. 2023. Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices. arXiv preprint arXiv:2312.16886 2, 6 (2023), 7."},{"key":"e_1_3_2_1_7_1","volume-title":"International conference on machine learning. PMLR, 4057\u20134086","author":"Clark Aidan","year":"2022","unstructured":"Aidan Clark, Diego de Las Casas, Aurelia Guy, Arthur Mensch, Michela Paganini, Jordan Hoffmann, Bogdan Damoc, Blake Hechtman, Trevor Cai, Sebastian Borgeaud, et al. 2022. Unified scaling laws for routed language models. In International conference on machine learning. PMLR, 4057\u20134086."},{"key":"e_1_3_2_1_8_1","unstructured":"Christopher Clark Kenton Lee Ming-Wei Chang Tom Kwiatkowski Michael Collins and Kristina Toutanova. 2019. BoolQ: Exploring the Surprising Difficulty of Natural Yes\/No Questions. arXiv:1905.10044 [cs.CL] https:\/\/arxiv.org\/abs\/1905.10044"},{"key":"e_1_3_2_1_9_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_10_1","volume-title":"QLoRA: Efficient Finetuning of Quantized LLMs. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=OUIFPHEgJU","author":"Dettmers Tim","year":"2023","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=OUIFPHEgJU"},{"key":"e_1_3_2_1_11_1","volume-title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=02f3mUtqnM","author":"Ding Dujian","year":"2024","unstructured":"Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor R\u00fchle, Laks V. S. Lakshmanan, and Ahmed Hassan Awadallah. 2024. Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=02f3mUtqnM"},{"key":"e_1_3_2_1_12_1","volume-title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling. arXiv:2103.10360 [cs.CL] https:\/\/arxiv.org\/abs\/2103.10360","author":"Du Zhengxiao","year":"2022","unstructured":"Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, and Jie Tang. 2022. GLM: General Language Model Pretraining with Autoregressive Blank Infilling. arXiv:2103.10360 [cs.CL] https:\/\/arxiv.org\/abs\/2103.10360"},{"key":"e_1_3_2_1_13_1","unstructured":"Amir Efrati and Aaron Holmes. [n. d.]. Why OpenAI Could Lose 5 Billion This Year. https:\/\/www.theinformation.com\/articles\/why-openai-could-lose-5-billion-this-year"},{"key":"e_1_3_2_1_14_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Frantar Elias","year":"2022","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2022. OPTQ: Accurate quantization for generative pre-trained transformers. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","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 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 135\u2013153."},{"key":"e_1_3_2_1_16_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri and et al. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_17_1","volume-title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces. arXiv:2312.00752 [cs.LG] https:\/\/arxiv.org\/abs\/2312.00752","author":"Gu Albert","year":"2024","unstructured":"Albert Gu and Tri Dao. 2024. Mamba: Linear-Time Sequence Modeling with Selective State Spaces. arXiv:2312.00752 [cs.LG] https:\/\/arxiv.org\/abs\/2312.00752"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350890"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3662006.3662067"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3662006.3662067"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"e_1_3_2_1_23_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSD57027.2022.00048"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Zhengxiang Huang Chaoyue Niu Zhaode Wang Jiarui Xue Hanming Zhang Yugang Wang Zewei Xin Xiaotang Jiang Chengfei Lv Fan Wu and Guihai Chen. 2025. MNN-AECS: Energy Optimization for LLM Decoding on Mobile Devices via Adaptive Core Selection. arXiv:2506.19884 [cs.OS] https:\/\/arxiv.org\/abs\/2506.19884","DOI":"10.1021\/acs.energyfuels.5c03402"},{"key":"e_1_3_2_1_26_1","unstructured":"Gautier Izacard Mathilde Caron Lucas Hosseini Sebastian Riedel Piotr Bojanowski Armand Joulin and Edouard Grave. 2022. Unsupervised Dense Information Retrieval with Contrastive Learning. arXiv:2112.09118 [cs.IR] https:\/\/arxiv.org\/abs\/2112.09118"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29197"},{"key":"e_1_3_2_1_28_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3357874"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3125949"},{"key":"e_1_3_2_1_31_1","volume-title":"Suriya Gunasekar, and Yin Tat Lee.","author":"Li Yuanzhi","year":"2023","unstructured":"Yuanzhi Li, S\u00e9bastien Bubeck, Ronen Eldan, Allie Del Giorno, Suriya Gunasekar, and Yin Tat Lee. 2023. Textbooks are all you need ii: phi-1.5 technical report. arXiv preprint arXiv:2309.05463 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3430103"},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Machine Learning. 20852\u201320867","author":"Liang Chen","year":"2023","unstructured":"Chen Liang, Simiao Zuo, Qingru Zhang, Pengcheng He, Weizhu Chen, and Tuo Zhao. 2023. Less is more: Task-aware layer-wise distillation for language model compression. In International Conference on Machine Learning. 20852\u201320867."},{"key":"e_1_3_2_1_34_1","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Lin Chaofan","year":"2024","unstructured":"Chaofan Lin, Zhenhua Han, Chengruidong Zhang, Yuqing Yang, Fan Yang, Chen Chen, and Lili Qiu. 2024. Parrot: Efficient serving of {LLM-based} applications with semantic variable. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 929\u2013945."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525517"},{"key":"e_1_3_2_1_36_1","volume-title":"QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models. In The Twelfth International Conference on Learning Representations(ICLR).","author":"Liu Jing","year":"2024","unstructured":"Jing Liu, Ruihao Gong, Xiuying Wei, Zhiwei Dong, Jianfei Cai, and Bohan Zhuang. 2024. QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models. In The Twelfth International Conference on Learning Representations(ICLR)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3366186"},{"key":"e_1_3_2_1_38_1","volume-title":"Llm-pruner: On the structural pruning of large language models. Advances in neural information processing systems 36","author":"Ma Xinyin","year":"2023","unstructured":"Xinyin Ma, Gongfan Fang, and Xinchao Wang. 2023. Llm-pruner: On the structural pruning of large language models. Advances in neural information processing systems 36 (2023), 21702\u201321720."},{"key":"e_1_3_2_1_39_1","volume-title":"Evaluating very long-term conversational memory of llm agents. arXiv preprint arXiv:2402.17753","author":"Maharana Adyasha","year":"2024","unstructured":"Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, and Yuwei Fang. 2024. Evaluating very long-term conversational memory of llm agents. arXiv preprint arXiv:2402.17753 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/mfi49285.2020.9235263"},{"key":"e_1_3_2_1_41_1","volume-title":"DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution. arXiv preprint arXiv:2405.17357","author":"Mao Yulong","year":"2024","unstructured":"Yulong Mao, Kaiyu Huang, Changhao Guan, Ganglin Bao, Fengran Mo, and Jinan Xu. 2024. DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution. arXiv preprint arXiv:2405.17357 (2024)."},{"key":"e_1_3_2_1_42_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya and et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_43_1","volume-title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models. In The Twelfth International Conference on Learning Representations (ICLR).","author":"Shao Wenqi","year":"2024","unstructured":"Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao, Yu Qiao, and Ping Luo. 2024. OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models. In The Twelfth International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_44_1","first-page":"296","article-title":"Slora: Scalable serving of thousands of lora adapters","volume":"6","author":"Sheng Ying","year":"2024","unstructured":"Ying Sheng, Shiyi Cao, Dacheng Li, Coleman Hooper, Nicholas Lee, Shuo Yang, Christopher Chou, Banghua Zhu, Lianmin Zheng, Kurt Keutzer, et al. 2024. Slora: Scalable serving of thousands of lora adapters. Proceedings of Machine Learning and Systems 6 (2024), 296\u2013311.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3388242.3388281"},{"key":"e_1_3_2_1_46_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, and et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, and et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530 [cs.CL] https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"e_1_3_2_1_47_1","first-page":"9565","article-title":"Hydralora: An asymmetric lora architecture for efficient fine-tuning","volume":"37","author":"Tian Chunlin","year":"2024","unstructured":"Chunlin Tian, Zhan Shi, Zhijiang Guo, Li Li, and Cheng-Zhong Xu. 2024. Hydralora: An asymmetric lora architecture for efficient fine-tuning. Advances in Neural Information Processing Systems 37 (2024), 9565\u20139584.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.conll-babylm.24"},{"key":"e_1_3_2_1_49_1","volume-title":"A short proof of optimality for the MIN cache replacement algorithm. Information processing letters 102, 2\u20133","author":"Roy Benjamin Van","year":"2007","unstructured":"Benjamin Van Roy. 2007. A short proof of optimality for the MIN cache replacement algorithm. Information processing letters 102, 2\u20133 (2007), 72\u201373."},{"key":"e_1_3_2_1_50_1","volume-title":"Knowledge-tuning large language models with structured medical knowledge bases for trustworthy response generation in Chinese. ACM Transactions on Knowledge Discovery from Data 19, 2","author":"Wang Haochun","year":"2025","unstructured":"Haochun Wang, Sendong Zhao, Zewen Qiang, Zijian Li, Chi Liu, Nuwa Xi, Yanrui Du, Bing Qin, and Ting Liu. 2025. Knowledge-tuning large language models with structured medical knowledge bases for trustworthy response generation in Chinese. ACM Transactions on Knowledge Discovery from Data 19, 2 (2025), 1\u201317."},{"key":"e_1_3_2_1_51_1","volume-title":"Understanding User Experience in Large Language Model Interactions. arXiv preprint arXiv:2401.08329","author":"Wang Jiayin","year":"2024","unstructured":"Jiayin Wang, Weizhi Ma, Peijie Sun, Min Zhang, and Jian-Yun Nie. 2024. Understanding User Experience in Large Language Model Interactions. arXiv preprint arXiv:2401.08329 (2024)."},{"key":"e_1_3_2_1_52_1","volume-title":"Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022. Emergent Abilities of Large Language Models. arXiv:2206.07682 [cs.CL] https:\/\/arxiv.org\/abs\/2206.07682"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Wei Jason","year":"2024","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2024. Chain-of-thought prompting elicits reasoning in large language models. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 1800, 14 pages."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645494"},{"key":"e_1_3_2_1_55_1","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Xia Haojun","year":"2024","unstructured":"Haojun Xia, Zhen Zheng, Xiaoxia Wu, Shiyang Chen, Zhewei Yao, Stephen Youn, Arash Bakhtiari, Michael Wyatt, Donglin Zhuang, Zhongzhu Zhou, Olatunji Ruwase, Yuxiong He, and Shuaiwen Leon Song. 2024. Quant-LLM: Accelerating the Serving of Large Language Models via FP6-Centric Algorithm-System Co-Design on Modern GPUs. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA, 699\u2013713. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/xia"},{"key":"e_1_3_2_1_56_1","volume-title":"The Twelfth International Conference on Learning Representations(ICLR).","author":"Xia Mengzhou","year":"2024","unstructured":"Mengzhou Xia, Tianyu Gao, Zhiyuan Zeng, and Danqi Chen. 2024. Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning. In The Twelfth International Conference on Learning Representations(ICLR)."},{"key":"e_1_3_2_1_57_1","volume-title":"International Conference on Machine Learning(ICML). 38087\u201338099","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(ICML). 38087\u201338099."},{"key":"e_1_3_2_1_58_1","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Xiong Yifan","year":"2024","unstructured":"Yifan Xiong, Yuting Jiang, Ziyue Yang, Lei Qu, Guoshuai Zhao, Shuguang Liu, Dong Zhong, Boris Pinzur, Jie Zhang, Yang Wang, et al. 2024. {SuperBench}: Improving Cloud {AI} Infrastructure Reliability with Proactive Validation. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). 835\u2013850."},{"key":"e_1_3_2_1_59_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng and et al. 2025. Qwen3 Technical Report. arXiv:2505.09388 [cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","unstructured":"Linyi Yang Shuibai Zhang Libo Qin Yafu Li Yidong Wang Hanmeng Liu Jindong Wang Xing Xie and Yue Zhang. 2023. GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective. arXiv:2211.08073 [cs.CL] https:\/\/arxiv.org\/abs\/2211.08073","DOI":"10.18653\/v1\/2023.findings-acl.806"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.204"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488694"},{"key":"e_1_3_2_1_63_1","volume-title":"Root mean square layer normalization. Advances in neural information processing systems 32","author":"Zhang Biao","year":"2019","unstructured":"Biao Zhang and Rico Sennrich. 2019. Root mean square layer normalization. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_64_1","volume-title":"Tinyllama: An open-source small language model. arXiv preprint arXiv:2401.02385","author":"Zhang Peiyuan","year":"2024","unstructured":"Peiyuan Zhang, Guangtao Zeng, Tianduo Wang, and Wei Lu. 2024. Tinyllama: An open-source small language model. arXiv preprint arXiv:2401.02385 (2024)."},{"key":"e_1_3_2_1_65_1","unstructured":"Qingru Zhang Minshuo Chen Alexander Bukharin Nikos Karampatziakis Pengcheng He Yu Cheng Weizhu Chen and Tuo Zhao. 2023. AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning. arXiv:2303.10512 [cs.CL] https:\/\/arxiv.org\/abs\/2303.10512"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.20944\/preprints202310.1487.v2"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638480"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS61880.2024.10620716"}],"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\/3767295.3769346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:23:10Z","timestamp":1780662190000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3769346"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":68,"alternative-id":["10.1145\/3767295.3769346","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3769346","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"}}]}}