{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:23:17Z","timestamp":1781281397886,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["CCF 2107470,CCF 2316233"],"award-info":[{"award-number":["CCF 2107470,CCF 2316233"]}]},{"name":"ACE, one of the seven centers in JUMP 2.0, a Semiconductor Research Corporation (SRC) program sponsored by DARPA","award":[""],"award-info":[{"award-number":[""]}]},{"name":"IBM-Illinois Discovery Accelerator Institute","award":[""],"award-info":[{"award-number":[""]}]},{"name":"Amazon ML Systems Fellowship funded by the UIUC AICE Center","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756083","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"217-231","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0519-8683","authenticated-orcid":false,"given":"Nikoleta","family":"Iliakopoulou","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4914-336X","authenticated-orcid":false,"given":"Jovan","family":"Stojkovic","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7965-0510","authenticated-orcid":false,"given":"Chloe","family":"Alverti","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4443-8170","authenticated-orcid":false,"given":"Tianyin","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0150-1055","authenticated-orcid":false,"given":"Hubertus","family":"Franke","sequence":"additional","affiliation":[{"name":"IBM Research, Yorktown Heights, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2595-5228","authenticated-orcid":false,"given":"Josep","family":"Torrellas","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"117","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Agrawal Amey","year":"2024","unstructured":"Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, and Ramachandran Ramjee. 2024. Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 117\u2013134. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/agrawal"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Keivan Alizadeh Iman Mirzadeh Dmitry Belenko Karen Khatamifard Minsik Cho Carlo C\u00a0Del Mundo Mohammad Rastegari and Mehrdad Farajtabar. 2024. LLM in a flash: Efficient Large Language Model Inference with Limited Memory. arxiv:https:\/\/arXiv.org\/abs\/2312.11514\u00a0[cs.CL]","DOI":"10.18653\/v1\/2024.acl-long.678"},{"key":"e_1_3_3_1_4_2","unstructured":"Jairus Bowne. 2024. Using Large Language Models in Learning and Teaching. https:\/\/biomedicalsciences.unimelb.edu.au\/study\/dlh\/assets\/documents\/large-language-models-in-education\/llms-in-education."},{"key":"e_1_3_3_1_5_2","first-page":"1","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Chen Lequn","year":"2024","unstructured":"Lequn Chen, Zihao Ye, Yongji Wu, Danyang Zhuo, Luis Ceze, and Arvind Krishnamurthy. 2024. Punica: Multi-Tenant LoRA Serving. In Proceedings of Machine Learning and Systems , P.\u00a0Gibbons, G.\u00a0Pekhimenko, and C.\u00a0De Sa (Eds.), Vol.\u00a06. 1\u201313. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/054de805fcceb78a201f5e9d53c85908-Paper-Conference.pdf"},{"key":"e_1_3_3_1_6_2","volume-title":"Improving WWW Proxies Performance with Greedy-Dual-Size-Frequency Caching Policy","author":"Cherkasova Ludmila","year":"1998","unstructured":"Ludmila Cherkasova. 1998. Improving WWW Proxies Performance with Greedy-Dual-Size-Frequency Caching Policy. Technical Report 98-69 (R.1). HP Labs."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00052"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/277851.277942"},{"key":"e_1_3_3_1_9_2","unstructured":"Tri Dao Daniel\u00a0Y. Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. arxiv:https:\/\/arXiv.org\/abs\/2205.14135\u00a0[cs.LG]"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071081"},{"key":"e_1_3_3_1_11_2","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)."},{"key":"e_1_3_3_1_12_2","unstructured":"Yichao Fu Siqi Zhu Runlong Su Aurick Qiao Ion Stoica and Hao Zhang. 2024. Efficient LLM Scheduling by Learning to Rank. arxiv:https:\/\/arXiv.org\/abs\/2408.15792\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2408.15792"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446757"},{"key":"e_1_3_3_1_14_2","unstructured":"GitHub. 2024. The world\u2019s most widely adopted AI developer tool. https:\/\/github.com\/features\/copilot."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Mor Harchol-Balter Mark\u00a0E. Crovella and Cristina\u00a0D. Murta. 1999. On Choosing a Task Assignment Policy for a Distributed Server System. J. Parallel and Distrib. Comput. 59 2 (1999) 204\u2013228. 10.1006\/jpdc.1999.1577","DOI":"10.1006\/jpdc.1999.1577"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"e_1_3_3_1_18_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hu Edward\u00a0J","year":"2022","unstructured":"Edward\u00a0J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations (ICLR). https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00078"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00034"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_3_1_22_2","unstructured":"Marina Lammertyn. 2024. 60+ ChatGPT Statistics And Facts You Need to Know in 2024. https:\/\/blog.invgate.com\/chatgpt-statistics."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00080"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00106"},{"key":"e_1_3_3_1_25_2","unstructured":"Brian Lester Rami Al-Rfou and Noah Constant. 2021. The Power of Scale for Parameter-Efficient Prompt Tuning. arxiv:https:\/\/arXiv.org\/abs\/2104.08691\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2104.08691"},{"key":"e_1_3_3_1_26_2","unstructured":"Suyi Li Hanfeng Lu Tianyuan Wu Minchen Yu Qizhen Weng Xusheng Chen Yizhou Shan Binhang Yuan and Wei Wang. 2024. CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference. arxiv:https:\/\/arXiv.org\/abs\/2401.11240\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2401.11240"},{"key":"e_1_3_3_1_27_2","volume-title":"Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201923)","author":"Li Zhuohan","year":"2023","unstructured":"Zhuohan Li, Lianmin Zheng, Yinmin Zhong, Vincent Liu, Ying Sheng, Xin Jin, Yanping Huang, Zhifeng Chen, Hao Zhang, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2023. AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving. In Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201923)."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Xiao Liu Kaixuan Ji Yicheng Fu Weng\u00a0Lam Tam Zhengxiao Du Zhilin Yang and Jie Tang. 2022. P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks. arxiv:https:\/\/arXiv.org\/abs\/2110.07602\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2110.07602","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_3_3_1_29_2","unstructured":"Sourab Mangrulkar Sylvain Gugger Lysandre Debut Younes Belkada Sayak Paul and Benjamin Bossan. 2022. PEFT: State-of-the-art Parameter-Efficient Fine-Tuning Methods. https:\/\/github.com\/huggingface\/peft."},{"key":"e_1_3_3_1_30_2","unstructured":"Meta. 2024. Llama3-70B. https:\/\/huggingface.co\/meta-llama\/Meta-Llama-3-70B-Instruct."},{"key":"e_1_3_3_1_31_2","unstructured":"Meta AI. 2024. Open Pre-trained Transformer Language Models. https:\/\/huggingface.co\/docs\/transformers\/model_doc\/opt."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640411"},{"key":"e_1_3_3_1_34_2","unstructured":"Microsoft Copilot. 2025. Microsoft Copilot \u2014 Wikipedia The Free Encyclopedia. https:\/\/en.wikipedia.org\/wiki\/Microsoft_Copilot [Online; accessed 22-August-2025]."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3463529"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00026"},{"key":"e_1_3_3_1_37_2","unstructured":"Mistral AI. 2024. The Mixtral-8x22B Large Language Model. https:\/\/huggingface.co\/mistralai\/Mixtral-8x22B-Instruct-v0.1."},{"key":"e_1_3_3_1_38_2","unstructured":"NVIDIA. 2024. Introduction to the NVIDIA DGX A100 System. https:\/\/docs.nvidia.com\/dgx\/dgxa100-user-guide\/introduction-to-dgxa100.html."},{"key":"e_1_3_3_1_39_2","unstructured":"NVIDIA. 2024. NVIDIA A40 Data Center GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/a40\/."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640383"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651329"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Cheng Peng Xi Yang Aokun Chen Kaleb Smith Nima PourNejatian Anthony Costa Cheryl Martin Mona Flores Ying Zhang Tanja Magoc Gloria Lipori Mitchell Duane Naykky Ospina Mustafa Ahmed William Hogan Elizabeth Shenkman Yi Guo Jiang Bian and Yonghui Wu. 2023. A study of generative large language model for medical research and healthcare. npj Digital Medicine (2023).","DOI":"10.1038\/s41746-023-00958-w"},{"key":"e_1_3_3_1_44_2","unstructured":"Jonas Pfeiffer Aishwarya Kamath Andreas R\u00fcckl\u00e9 Kyunghyun Cho and Iryna Gurevych. 2020. AdapterHub: A Framework for Adapting Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2007.07779 (2020). https:\/\/arxiv.org\/abs\/2007.07779"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00079"},{"key":"e_1_3_3_1_47_2","first-page":"75","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Qiu Haoran","year":"2024","unstructured":"Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Saurabh Jha, Chen Wang, Hubertus Franke, Zbigniew Kalbarczyk, Tamer Ba\u015far, and Ravishankar\u00a0K. Iyer. 2024. Power-aware Deep Learning Model Serving with \u03bc-Serve. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA, 75\u201393. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/qiu"},{"key":"e_1_3_3_1_48_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_1_49_2","volume-title":"Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC \u201920)","author":"Shahrad Mohammad","year":"2020","unstructured":"Mohammad Shahrad, Rodrigo Fonseca, Inigo Goiri, Gohar Chaudhry, Paul Batum, Jason Cooke, Eduardo Laureano, Colby Tresness, Mark Russinovich, and Ricardo Bianchini. 2020. Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Provider. In Proceedings of the 2020 USENIX Annual Technical Conference (USENIX ATC \u201920)."},{"key":"e_1_3_3_1_50_2","first-page":"296","volume-title":"Proceedings of Machine Learning and Systems","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, Joseph Gonzalez, and Ion Stoica. 2024. S-LoRA: Scalable Serving of Thousands of LoRA Adapters. In Proceedings of Machine Learning and Systems , P.\u00a0Gibbons, G.\u00a0Pekhimenko, and C.\u00a0De Sa (Eds.), Vol.\u00a06. 296\u2013311. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/906419cd502575b617cc489a1a696a67-Paper-Conference.pdf"},{"key":"e_1_3_3_1_51_2","first-page":"965","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Sheng Ying","year":"2024","unstructured":"Ying Sheng, Shiyi Cao, Dacheng Li, Banghua Zhu, Zhuohan Li, Danyang Zhuo, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2024. Fairness in Serving Large Language Models. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 965\u2013988. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/sheng"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","unstructured":"Jovan Stojkovic Esha Choukse Chaojie Zhang Inigo Goiri and Josep Torrellas. 2024. Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference. arXiv e-prints Article arXiv:2403.20306 (March 2024) arXiv:2403.20306\u00a0pages. 10.48550\/arXiv.2403.20306 arxiv:https:\/\/arXiv.org\/abs\/2403.20306\u00a0[cs.AI]","DOI":"10.48550\/arXiv.2403.20306"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716025"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"e_1_3_3_1_55_2","volume-title":"Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201924)","author":"Sun Biao","year":"2024","unstructured":"Biao Sun, Ziming Huang, Hanyu Zhao, Wencong Xiao, Xinyi Zhang, Yong Li, and Wei Lin. 2024. Llumnix: Dynamic Scheduling for Large Language Model Serving. In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201924)."},{"key":"e_1_3_3_1_56_2","unstructured":"Technology Innovation Institute (TII). 2024. Falcon-180B. https:\/\/huggingface.co\/tiiuae\/falcon-180B. (2024)."},{"key":"e_1_3_3_1_57_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_1_58_2","unstructured":"Tanay Varshney. 2024. Build an LLM-Powered Data Agent for Data Analysis. https:\/\/developer.nvidia.com\/blog\/build-an-llm-powered-data-agent-for-data-analysis\/."},{"key":"e_1_3_3_1_59_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang Zhengbo","year":"2025","unstructured":"Zhengbo Wang, Jian Liang, Ran He, Zilei Wang, and Tieniu Tan. 2025. LoRA-Pro: Are Low-Rank Adapters Properly Optimized?. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=gTwRMU3lJ5"},{"key":"e_1_3_3_1_60_2","unstructured":"Bingyang Wu Yinmin Zhong Zili Zhang Gang Huang Xuanzhe Liu and Xin Jin. 2023. Fast Distributed Inference Serving for Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2305.05920\u00a0[cs.LG]"},{"key":"e_1_3_3_1_61_2","first-page":"911","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Wu Bingyang","year":"2024","unstructured":"Bingyang Wu, Ruidong Zhu, Zili Zhang, Peng Sun, Xuanzhe Liu, and Xin Jin. 2024. dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 911\u2013927. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/wu-bingyang"},{"key":"e_1_3_3_1_62_2","first-page":"521","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo\u00a0Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A Distributed Serving System for Transformer-Based Generative Models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 521\u2013538. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu"},{"key":"e_1_3_3_1_63_2","volume-title":"Proceedings of the International Symposium on Microarchitecture (MICRO \u201924)","author":"Yu Zhongkai","year":"2024","unstructured":"Zhongkai Yu, Shengwen Liang, Tianyun Ma, Yunke Cai, Ziyuan Nan, Di Huang, Xinkai Song, Yifan Hao, Jie Zhang, Tian Zhi, Yongwei Zhao, Zidong Du, Xing Hu, Qi Guo, and Tianshi Chen. 2024. FlashLLM: A Chiplet-Based In-Flash Computing Architecture to Enable On-Device Inference of 70B LLM. In Proceedings of the International Symposium on Microarchitecture (MICRO \u201924)."},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00105"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00082"},{"key":"e_1_3_3_1_66_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhao Wenting","year":"2024","unstructured":"Wenting Zhao, Xiang Ren, Jack Hessel, Claire Cardie, Yejin Choi, and Yuntian Deng. 2024. WildChat: 1M ChatGPT Interaction Logs in the Wild. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Bl8u7ZRlbM"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00077"},{"key":"e_1_3_3_1_68_2","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Tianle Li Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zhuohan Li Zi Lin Eric\u00a0P. Xing Joseph\u00a0E. Gonzalez Ion Stoica and Hao Zhang. 2024. LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset. arxiv:https:\/\/arXiv.org\/abs\/2309.11998\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2309.11998"},{"key":"e_1_3_3_1_69_2","volume-title":"Proceedings of the USENIX Annual Technical Conference (USENIX ATC \u201922)","author":"Zhou Zhe","year":"2022","unstructured":"Zhe Zhou, Xuechao Wei, Jiejing Zhang, and Guangyu Sun. 2022. PetS: A Unified Framework for Parameter-Efficient Transformers Serving. In Proceedings of the USENIX Annual Technical Conference (USENIX ATC \u201922)."},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00059"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756083","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:46:18Z","timestamp":1769463978000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":69,"alternative-id":["10.1145\/3725843.3756083","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756083","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}