{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T19:10:03Z","timestamp":1755976203792,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2238431;2316176;2335881"],"award-info":[{"award-number":["2238431;2316176;2335881"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1145\/3735654.3735937","type":"proceedings-article","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T21:36:31Z","timestamp":1750628191000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Buffer Management for Out-of-GPU LLM Execution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0079-2146","authenticated-orcid":false,"given":"Jiashen","family":"Cao","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7706-6978","authenticated-orcid":false,"given":"Joy","family":"Arulraj","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6061-7825","authenticated-orcid":false,"given":"Hyesoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. NVIDIA H100 Tensor Core GPU Architecture Overview. https:\/\/resources.nvidia.com\/en-us-tensor-core"},{"key":"e_1_3_2_1_2_1","volume-title":"Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He.","author":"Aminabadi Reza Yazdani","year":"2022","unstructured":"Reza Yazdani Aminabadi, Samyam Rajbhandari, Minjia Zhang, Ammar Ahmad Awan, Cheng Li, Du Li, Elton Zheng, Jeff Rasley, Shaden Smith, Olatunji Ruwase, and Yuxiong He. 2022. DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale."},{"key":"e_1_3_2_1_3_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan and et al. 2023. Qwen Technical Report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Li","author":"Daya Guo AI","year":"2025","unstructured":"DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, 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, and Erhang et al. Li. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning."},{"key":"e_1_3_2_1_5_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, L\u00e9lio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, and Pierre et al. Stock.","author":"Jiang Albert","year":"2024","unstructured":"Albert Q.Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, L\u00e9lio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, and Pierre et al. Stock. 2024. Mixtral of Experts. http:\/\/arxiv.org\/abs\/2401.04088"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Song Jiang and Xiaodong Zhang. 2002. LIRS: an efficient low inter-reference recency set replacement policy to improve buffer cache performance. In SIGMETRICS. 31--42.","DOI":"10.1145\/511334.511340"},{"key":"e_1_3_2_1_7_1","volume-title":"Natural Questions: A Benchmark for Question Answering Research. Transactions of the ACL","author":"Kwiatkowski Tom","year":"2019","unstructured":"Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natural Questions: A Benchmark for Question Answering Research. Transactions of the ACL (2019), 453--466."},{"key":"e_1_3_2_1_8_1","volume-title":"Joseph 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 Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. In SOSP. 611--626."},{"key":"e_1_3_2_1_9_1","volume-title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU. ICLR","author":"Sheng Ying","year":"2023","unstructured":"Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher R\u00e9, Ion Stoica, and Ce Zhang. 2023. FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU. ICLR (2023)."},{"key":"e_1_3_2_1_10_1","unstructured":"Hugo Touvron Louis Martin and Kevin Stone. [n. d.]. Llama 2: Open Foundation and Fine-Tuned Chat Models. ([n. d.])."},{"key":"e_1_3_2_1_11_1","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. In NeurIPS. 6000--6010."},{"key":"e_1_3_2_1_12_1","volume-title":"Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun.","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. ORCA: A Distributed Serving System for Transformer-Based Generative Models. OSDI (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. arXiv:2205.01068 [cs.CL]"}],"event":{"name":"SIGMOD\/PODS '25: International Conference on Management of Data","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"],"location":"Berlin Germany","acronym":"SIGMOD\/PODS '25"},"container-title":["Proceedings of the Workshop on Data Management for End-to-End Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3735654.3735937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:28:37Z","timestamp":1755973717000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3735654.3735937"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":13,"alternative-id":["10.1145\/3735654.3735937","10.1145\/3735654"],"URL":"https:\/\/doi.org\/10.1145\/3735654.3735937","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]},"assertion":[{"value":"2025-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}