{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:44:51Z","timestamp":1782999891711,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3807846","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"766-779","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CXL-CCL: Inter-Node Collective GPU-Communication Using a CXL Shared Memory Pool"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4093-628X","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"first","affiliation":[{"name":"University of California, Merced, Merced, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2532-4721","authenticated-orcid":false,"given":"Han","family":"Meng","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8774-1617","authenticated-orcid":false,"given":"Xinyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5809-4578","authenticated-orcid":false,"given":"Dengcheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Bytedance, San Jose, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5441-5503","authenticated-orcid":false,"given":"Wei","family":"Tang","sequence":"additional","affiliation":[{"name":"Bytedance, San Jose, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9533-3446","authenticated-orcid":false,"given":"Fei","family":"Liu","sequence":"additional","affiliation":[{"name":"Bytedance, San Jose, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3764-9888","authenticated-orcid":false,"given":"Liguang","family":"Xie","sequence":"additional","affiliation":[{"name":"Bytedance technology company Limited, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6733-0947","authenticated-orcid":false,"given":"Wu","family":"Xiang","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9122-4703","authenticated-orcid":false,"given":"Rui","family":"Shi","sequence":"additional","affiliation":[{"name":"Bytedance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1169-7389","authenticated-orcid":false,"given":"Yue","family":"Li","sequence":"additional","affiliation":[{"name":"Bytedance, San Jose, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1505-2907","authenticated-orcid":false,"given":"Henry","family":"Hu","sequence":"additional","affiliation":[{"name":"Bytedance, San Jose, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2358-7946","authenticated-orcid":false,"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance, San Jose, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1750-660X","authenticated-orcid":false,"given":"Jianping","family":"Jiang","sequence":"additional","affiliation":[{"name":"Xconn-Tech, San Jose, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9336-0694","authenticated-orcid":false,"given":"Dong","family":"Li","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2020. Buddy and Slab Allocators. https:\/\/students.mimuw.edu.pl\/ZSO\/Wyklady\/06_memory2\/BuddySlabAllocator.pdf."},{"key":"e_1_3_3_1_3_2","unstructured":"2026. Compute Express Link (CXL). https:\/\/computeexpresslink.org\/."},{"key":"e_1_3_3_1_4_2","unstructured":"2026. PyTorch. https:\/\/pytorch.org\/."},{"key":"e_1_3_3_1_5_2","unstructured":"2026. TensorFlow. https:\/\/www.tensorflow.org\/."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Neha Agarwal and Thomas\u00a0F. Wenisch. 2017. Thermostat: Application-transparent Page Management for Two-tiered Main Memory. Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems (2017). https:\/\/api.semanticscholar.org\/CorpusID:8753499","DOI":"10.1145\/3037697.3037706"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3533737.3535090"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545054"},{"key":"e_1_3_3_1_9_2","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et\u00a0al. 2023. Qwen technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.16609 (2023)."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716006"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707267"},{"key":"e_1_3_3_1_12_2","unstructured":"Jonathan Corbet. 2023. Weighted interleaving for memory tiering. https:\/\/lwn.net\/Articles\/948037\/."},{"key":"e_1_3_3_1_13_2","volume-title":"Wikimedia Downloads","author":"Foundation Wikimedia","unstructured":"Wikimedia Foundation. [n. d.]. Wikimedia Downloads. https:\/\/dumps.wikimedia.org"},{"key":"e_1_3_3_1_14_2","first-page":"287","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Gouk Donghyun","year":"2022","unstructured":"Donghyun Gouk, Sangwon Lee, Miryeong Kwon, and Myoungsoo Jung. 2022. Direct access,{ High-Performance} memory disaggregation with { DirectCXL}. In 2022 USENIX Annual Technical Conference (USENIX ATC 22). 287\u2013294."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00447"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Taekyung Heo Yang Wang Wei Cui Jaehyuk Huh and Lintao Zhang. 2022. Adaptive Page Migration Policy With Huge Pages in Tiered Memory Systems. IEEE Trans. Comput. 71 1 (2022) 53\u201368. 10.1109\/TC.2020.3036686","DOI":"10.1109\/TC.2020.3036686"},{"key":"e_1_3_3_1_17_2","volume-title":"19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25), Boston, MA","author":"Huang Yibo","year":"2025","unstructured":"Yibo Huang, Haowei Chen, Newton Ni, Vijay Chidambaram, Dixin Tang, Emmett Witchel, Zhiting Zhu, and Zhipeng Jia. 2025. Tigon: A distributed database for a CXL pod. In 19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25), Boston, MA."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.42"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613167"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"e_1_3_3_1_21_2","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et\u00a0al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.19437 (2024)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00036"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715987"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545090"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441581"},{"key":"e_1_3_3_1_26_2","unstructured":"LWN.net. [n. d.]. AutoNUMA Balancing. \"https:\/\/access.redhat.com\/documentation\/en-us\/red_hat_enterprise_linux\/7\/html\/virtualization_tuning_and_optimization_guide\/sect-virtualization_tuning_optimization_guide-numa-auto_numa_balancing\"."},{"key":"e_1_3_3_1_27_2","unstructured":"Bin Ma Xingjian Ding Tekin Bicer Pengfei Su and Dong Li. 2026. CoCoDiff: Optimizing Collective Communications for Distributed Diffusion Transformer Inference Under Ulysses Sequence Parallelism. arxiv:https:\/\/arXiv.org\/abs\/2604.14561\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2604.14561"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Adnan Maruf Ashikee Ghosh Janki Bhimani Daniela Campello Andy Rudoff and Raju Rangaswami. 2022. MULTI-CLOCK: Dynamic Tiering for Hybrid Memory Systems. 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA) (2022) 925\u2013937. https:\/\/api.semanticscholar.org\/CorpusID:248865268","DOI":"10.1109\/HPCA53966.2022.00072"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582063"},{"key":"e_1_3_3_1_30_2","unstructured":"Siyuan Mu and Sen Lin. 2026. A Comprehensive Survey of Mixture-of-Experts: Algorithms Theory and Applications. arxiv:https:\/\/arXiv.org\/abs\/2503.07137\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2503.07137"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_3_1_32_2","unstructured":"NVIDIA. [n. d.]. NVIDIA Collective Communications Library (NCCL).https:\/\/developer.nvidia.com\/nccl"},{"key":"e_1_3_3_1_33_2","volume-title":"Introduction to InfiniBand","author":"Corporation NVIDIA","year":"2021","unstructured":"NVIDIA Corporation. 2021. Introduction to InfiniBand. White Paper. NVIDIA. https:\/\/network.nvidia.com\/pdf\/whitepapers\/IB_Intro_WP_190.pdf"},{"key":"e_1_3_3_1_34_2","unstructured":"Pytorch. 2022. Fully sharded data parallelism.https:\/\/pytorch.org\/blog\/introducing-pytorch-fully-sharded-data-parallel-api\/"},{"key":"e_1_3_3_1_35_2","unstructured":"Amanda Raybuck Tim Stamler Wei Zhang Mattan Erez and Simon Peter. 2021. HeMem: Scalable Tiered Memory Management for Big Data Applications and Real NVM. Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles (2021). https:\/\/api.semanticscholar.org\/CorpusID:239029009"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460356"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00057"},{"key":"e_1_3_3_1_38_2","unstructured":"Jie Ren Bin Ma Shuangyan Yang Benjamin Francis Ehsan\u00a0K. Ardestani Min Si and Dong Li. 2025. Machine Learning-Guided Memory Optimization for DLRM Inference on Tiered Memory. arxiv:https:\/\/arXiv.org\/abs\/2511.08568\u00a0[cs.PF] https:\/\/arxiv.org\/abs\/2511.08568"},{"key":"e_1_3_3_1_39_2","first-page":"551","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza\u00a0Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. { ZeRO-Offload} : Democratizing { Billion-Scale} model training. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). 551\u2013564."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650075"},{"key":"e_1_3_3_1_41_2","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ren Jie","year":"2020","unstructured":"Jie Ren, Minjia Zhang, and Dong Li. 2020. HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_42_2","unstructured":"Andre Rodriguez and William Osborn. 2025. Distributed Locking: Performance Analysis and Optimization Strategies. arxiv:https:\/\/arXiv.org\/abs\/2504.03073\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2504.03073"},{"key":"e_1_3_3_1_43_2","first-page":"1027","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Romero Joshua","year":"2022","unstructured":"Joshua Romero, Junqi Yin, Nouamane Laanait, Bing Xie, M.\u00a0Todd Young, Sean Treichler, Vitalii Starchenko, Albina Borisevich, Alex Sergeev, and Michael Matheson. 2022. Accelerating Collective Communication in Data Parallel Training across Deep Learning Frameworks. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, 1027\u20131040. https:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/romero"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3208064"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624173"},{"key":"e_1_3_3_1_46_2","unstructured":"Min Si Pavan Balaji Yongzhou Chen Ching-Hsiang Chu Adi Gangidi Saif Hasan Subodh Iyengar Dan Johnson Bingzhe Liu Regina Ren Deep Shah Ashmitha\u00a0Jeevaraj Shetty Greg Steinbrecher Yulun Wang Bruce Wu Xinfeng Xie Jingyi Yang Mingran Yang Kenny Yu Minlan Yu Cen Zhao Wes Bland Denis Boyda Suman Gumudavelli Prashanth Kannan Cristian Lumezanu Rui Miao Zhe Qu Venkat Ramesh Maxim Samoylov Jan Seidel Srikanth Sundaresan Feng Tian Qiye Tan Shuqiang Zhang Yimeng Zhao Shengbao Zheng Art Zhu and Hongyi Zeng. 2026. Collective Communication for 100k+ GPUs. arxiv:https:\/\/arXiv.org\/abs\/2510.20171\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2510.20171"},{"key":"e_1_3_3_1_47_2","unstructured":"Dinghong Song Yuan Feng Yiwei Wang Shangye Chen Cyril Guyot Filip Blagojevic Hyeran Jeon Pengfei Su and Dong Li. 2025. AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache. arxiv:https:\/\/arXiv.org\/abs\/2510.25979\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2510.25979"},{"key":"e_1_3_3_1_48_2","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew\u00a0M Dai Anja Hauth Katie Millican et\u00a0al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.11805 (2023)."},{"key":"e_1_3_3_1_49_2","unstructured":"Vishal Verma.2022. Tiering-0.8.https:\/\/git.kernel.org\/pub\/scm\/linux\/ kernel\/git\/vishal\/tiering.git\/log\/?h=tiering-0.8."},{"key":"e_1_3_3_1_50_2","unstructured":"Xi Wang Jie Liu Jianbo Wu Shuangyan Yang Jie Ren Bhanu Shankar and Dong Li. 2024. Exploring and evaluating real-world cxl: use cases and system adoption. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.14209 (2024)."},{"key":"e_1_3_3_1_51_2","unstructured":"Xi Wang Jie Liu Shuangyan Yang Jongryool Kim Pengfei Su and Dong Li. 2026. Hybrid Adaptive Tuning for Tiered Memory Systems. arxiv:https:\/\/arXiv.org\/abs\/2604.12165\u00a0[cs.OS] https:\/\/arxiv.org\/abs\/2604.12165"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759816"},{"key":"e_1_3_3_1_53_2","unstructured":"Xi Wang Tal Zussman Yuang Xu Bin Ma Asaf Cidon and Dong Li. 2026. TierBPF: Page Migration Admission Control for Tiered Memory via eBPF. arxiv:https:\/\/arXiv.org\/abs\/2604.12300\u00a0[cs.OS] https:\/\/arxiv.org\/abs\/2604.12300"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Zhonghua Wang Yixing Guo Kai Lu Jiguang Wan Daohui Wang Ting Yao and Huatao Wu. 2024. Rcmp: Reconstructing rdma-based memory disaggregation via cxl. ACM Transactions on Architecture and Code Optimization 21 1 (2024) 1\u201326.","DOI":"10.1145\/3634916"},{"key":"e_1_3_3_1_55_2","unstructured":"Xingda Wei Haotian Wang Tianxia Wang Rong Chen Jinyu Gu Pengfei Zuo and Haibo Chen. 2023. Transactional indexes on (RDMA or cxl-based) disaggregated memory with repairable transaction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.02501 (2023)."},{"key":"e_1_3_3_1_56_2","unstructured":"Bryan Woolley. 2015. NCCL: Multi-GPU Collective Communication Library. https:\/\/images.nvidia.com\/events\/sc15\/pdfs\/NCCL-Woolley.pdf."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126923"},{"key":"e_1_3_3_1_58_2","volume-title":"USENIX Conference on File and Storage Technologies","author":"Wu Kai","year":"2021","unstructured":"Kai Wu, Jie Ren\u00a0Ivy Peng, and Dong Li. 2021. ArchTM: Architecture-Aware, High Performance Transaction for Persistent Memory. In USENIX Conference on File and Storage Technologies."},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00034"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/2907294.2907321"},{"key":"e_1_3_3_1_61_2","unstructured":"Xconn. 2025. Xconn Technologies. https:\/\/www.xconn-tech.com\/."},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460365"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577497"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00100"},{"key":"e_1_3_3_1_65_2","series-title":"(USENIX ATC\u201924)","volume-title":"Proceedings of the 2024 USENIX Conference on Usenix Annual Technical Conference","author":"Xu Dong","year":"2024","unstructured":"Dong Xu, Junhee Ryu, Jinho Baek, Kwangsik Shin, Pengfei Su, and Dong Li. 2024. FlexMem: adaptive page profiling and migration for tiered memory. In Proceedings of the 2024 USENIX Conference on Usenix Annual Technical Conference (Santa Clara, CA, USA) (USENIX ATC\u201924). USENIX Association, USA, Article 50, 17\u00a0pages."},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"crossref","unstructured":"Zi Yan Daniel Lustig David\u00a0W. Nellans and Abhishek Bhattacharjee. 2019. Nimble Page Management for Tiered Memory Systems. Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems (2019). https:\/\/api.semanticscholar.org\/CorpusID:102348046","DOI":"10.1145\/3297858.3304024"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.61"},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575725"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00083"},{"key":"e_1_3_3_1_70_2","unstructured":"Xinjun Yang Qingda Hu Junru Li Feifei Li Yicong Zhu Yuqi Zhou Qiuru Lin Jian Dai Yang Kong Jiayu Zhang et\u00a0al. 2025. Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.20172 (2025)."},{"key":"e_1_3_3_1_71_2","unstructured":"Xinjun Yang Qingda Hu Junru Li Feifei Li Yicong Zhu Yuqi Zhou Qiuru Lin Jian Dai Yang Kong Jiayu Zhang Guoqiang Xu and Qiang Liu. 2025. Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management. arxiv:https:\/\/arXiv.org\/abs\/2511.20172\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2511.20172"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3722212.3724460"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3722212.3724460"},{"key":"e_1_3_3_1_74_2","unstructured":"Dongha Yoon Younghoon Min Hoshik Kim Sam\u00a0H. Noh and Jongryool Kim. 2025. TraCT: Disaggregated LLM Serving with CXL Shared Memory KV Cache at Rack-Scale. arxiv:https:\/\/arXiv.org\/abs\/2512.18194\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2512.18194"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196890"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405857"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613135"}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:12:49Z","timestamp":1782997969000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3807846"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":76,"alternative-id":["10.1145\/3797905.3807846","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3807846","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}