{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T19:02:13Z","timestamp":1789585333022,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"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":["62402070"],"award-info":[{"award-number":["62402070"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024CDJGF-003"],"award-info":[{"award-number":["2024CDJGF-003"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024CDJGF-019"],"award-info":[{"award-number":["2024CDJGF-019"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Graduate Supervisor Team","award":["0225005401117"],"award-info":[{"award-number":["0225005401117"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"DOI":"10.1145\/3832810.3832869","type":"proceedings-article","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T00:19:06Z","timestamp":1789258746000},"page":"12-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CARE-MoE: Correlation-Aware Expert Placement and Semantic Equivalence Routing for MoE LLM Inference on Edge Devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1550-5258","authenticated-orcid":false,"given":"Zhenyu","family":"Wang","sequence":"first","affiliation":[{"name":"Chongqing University, Chongqing, China and Jialingjiang Laboratory, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3298-4716","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2322-8038","authenticated-orcid":false,"given":"Ao","family":"Ren","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3040-2065","authenticated-orcid":false,"given":"Duo","family":"Liu","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China and Jialingjiang Laboratory, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5129-0102","authenticated-orcid":false,"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5278-0406","authenticated-orcid":false,"given":"Kan","family":"Zhong","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China and Jialingjiang Laboratory, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7193-9993","authenticated-orcid":false,"given":"Chaoxia","family":"Qin","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China and Jialingjiang Laboratory, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8728-5294","authenticated-orcid":false,"given":"Haoyang","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing University, Chongqing, China and Jialingjiang Laboratory, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,9,27]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Alexander Borzunov Max Ryabinin Artem Chumachenko Dmitry Baranchuk Tim Dettmers Younes Belkada Pavel Samygin and Colin\u00a0A Raffel. 2023. Distributed inference and fine-tuning of large language models over the internet. Advances in neural information processing systems 36 (2023) 12312\u201312331.","DOI":"10.52202\/075280-0540"},{"key":"e_1_3_3_1_3_2","first-page":"797","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Cui Weihao","year":"2023","unstructured":"Weihao Cui, Zhenhua Han, Lingji Ouyang, Yichuan Wang, Ningxin Zheng, Lingxiao Ma, Yuqing Yang, Fan Yang, Jilong Xue, Lili Qiu, et\u00a0al. 2023. Optimizing dynamic neural networks with brainstorm. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 797\u2013815."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"e_1_3_3_1_5_2","unstructured":"deepseek ai. [n. d.]. Expert Parallelism Load Balancer (EPLB). https:\/\/github.com\/deepseek-ai\/EPLB. Accessed 2026-04-30."},{"key":"e_1_3_3_1_6_2","unstructured":"domeccleston. [n. d.]. ShareGPT: Share your wildest ChatGPT conversations with one click. https:\/\/github.com\/domeccleston\/sharegpt. Accessed 2026-04-30."},{"key":"e_1_3_3_1_7_2","unstructured":"William Fedus Barret Zoph and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research 23 120 (2022) 1\u201339."},{"key":"e_1_3_3_1_8_2","unstructured":"Dan Hendrycks Collin Burns Steven Basart Andy Zou Mantas Mazeika Dawn Song and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.03300 (2020)."},{"key":"e_1_3_3_1_9_2","volume-title":"AAAI 2025 Workshop on Artificial Intelligence for Wireless Communications and Networking (AI4WCN)","author":"Hu Xinyi","year":"2025","unstructured":"Xinyi Hu, Zihan Chen, Kun Guo, Meng Zhang, and Howard\u00a0Hao Yang. 2025. Adaptlink: A heterogeneity-aware adaptive framework for distributed mllm inference. In AAAI 2025 Workshop on Artificial Intelligence for Wireless Communications and Networking (AI4WCN)."},{"key":"e_1_3_3_1_10_2","unstructured":"Haiyang Huang Newsha Ardalani Anna Sun Liu Ke Hsien-Hsin\u00a0S Lee Anjali Sridhar Shruti Bhosale Carole-Jean Wu and Benjamin Lee. 2023. Towards moe deployment: Mitigating inefficiencies in mixture-of-expert (moe) inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.06182 (2023)."},{"key":"e_1_3_3_1_11_2","unstructured":"Albert\u00a0Q Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Emma\u00a0Bou Hanna Florian Bressand et\u00a0al. 2024. Mixtral of experts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.04088 (2024)."},{"key":"e_1_3_3_1_12_2","unstructured":"Youhe Jiang Ran Yan and Binhang Yuan. 2025. Hexgen-2: Disaggregated generative inference of llms in heterogeneous environment. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.07903 (2025)."},{"key":"e_1_3_3_1_13_2","unstructured":"Ning Li Song Guo Tuo Zhang Muqing Li Zicong Hong Qihua Zhou Xin Yuan and Haijun Zhang. 2025. The moe-empowered edge llms deployment: Architecture challenges and opportunities. IEEE Communications Magazine (2025)."},{"key":"e_1_3_3_1_14_2","unstructured":"Zonghang Li Wenjiao Feng Mohsen Guizani and Hongfang Yu. 2025. TPI-LLM: Serving 70B-scale LLMs efficiently on low-resource mobile devices. IEEE Transactions on Services Computing (2025)."},{"key":"e_1_3_3_1_15_2","unstructured":"Zonghang Li Tao Li Wenjiao Feng Mohsen Guizani and Hongfang Yu. 2025. Prima. Cpp: Speeding up 70b-scale LLM inference on low-resource everyday home clusters. arXiv e-prints (2025) arXiv\u20132504."},{"key":"e_1_3_3_1_16_2","unstructured":"Yixuan Mei Yonghao Zhuang Xupeng Miao Juncheng Yang Zhihao Jia and Rashmi Vinayak. 2024. Helix: Distributed serving of large language models via max-flow on heterogeneous gpus. Parameters 4 A100s (2024) H100s."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Xiaonan Nie Xupeng Miao Zilong Wang Zichao Yang Jilong Xue Lingxiao Ma Gang Cao and Bin Cui. 2023. Flexmoe: Scaling large-scale sparse pre-trained model training via dynamic device placement. Proceedings of the ACM on Management of Data 1 1 (2023) 1\u201319.","DOI":"10.1145\/3588964"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER52292.2023.00015"},{"key":"e_1_3_3_1_19_2","unstructured":"Yongji Wu Wenjie Qu Tianyang Tao Zhuang Wang Wei Bai Zhuohao Li Yuan Tian Jiaheng Zhang Matthew Lentz and Danyang Zhuo. 2024. Lazarus: Resilient and elastic training of mixture-of-experts models with adaptive expert placement. arXiv e-prints (2024) arXiv\u20132407."},{"key":"e_1_3_3_1_20_2","unstructured":"Fuzhao Xue Zian Zheng Yao Fu Jinjie Ni Zangwei Zheng Wangchunshu Zhou and Yang You. 2024. Openmoe: An early effort on open mixture-of-experts language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.01739 (2024)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Nan Xue Yaping Sun Zhiyong Chen Meixia Tao Xiaodong Xu Liang Qian Shuguang Cui Wenjun Zhang and Ping Zhang. 2025. WDMoE: Wireless distributed mixture of experts for large language models. IEEE Transactions on Wireless Communications (2025).","DOI":"10.1109\/TWC.2025.3585163"},{"key":"e_1_3_3_1_22_2","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et\u00a0al. 2025. Qwen3 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.09388 (2025)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621342"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044734"},{"key":"e_1_3_3_1_25_2","unstructured":"Aohan Zeng Xin Lv Qinkai Zheng Zhenyu Hou Bin Chen Chengxing Xie Cunxiang Wang Da Yin Hao Zeng Jiajie Zhang et\u00a0al. 2025. Glm-4.5: Agentic reasoning and coding (arc) foundation models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.06471 (2025)."},{"key":"e_1_3_3_1_26_2","first-page":"961","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Zhai Mingshu","year":"2023","unstructured":"Mingshu Zhai, Jiaao He, Zixuan Ma, Zan Zong, Runqing Zhang, and Jidong Zhai. 2023. { SmartMoE} : Efficiently training { Sparsely-Activated} models through combining offline and online parallelization. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 961\u2013975."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044447"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Mingjin Zhang Xiaoming Shen Jiannong Cao Zeyang Cui and Shan Jiang. 2024. Edgeshard: Efficient llm inference via collaborative edge computing. IEEE Internet of Things Journal 12 10 (2024) 13119\u201313131.","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Zheng Zhang Yaqi Xia Hulin Wang Donglin Yang Chuang Hu Xiaobo Zhou and Dazhao Cheng. 2024. Mpmoe: Memory efficient moe for pre-trained models with adaptive pipeline parallelism. IEEE Transactions on Parallel and Distributed Systems 35 6 (2024) 998\u20131011.","DOI":"10.1109\/TPDS.2024.3385639"},{"key":"e_1_3_3_1_30_2","unstructured":"Junchen Zhao Yurun Song Simeng Liu Ian\u00a0G Harris and Sangeetha\u00a0Abdu Jyothi. 2023. LinguaLinked: A distributed large language model inference system for mobile devices. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.00388 (2023)."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Lianmin Zheng Liangsheng Yin Zhiqiang Xie Chuyue Sun Jeff Huang Cody\u00a0H Yu Shiyi Cao Christos Kozyrakis Ion Stoica Joseph\u00a0E Gonzalez et\u00a0al. 2024. Sglang: Efficient execution of structured language model programs. Advances in neural information processing systems 37 (2024) 62557\u201362583.","DOI":"10.52202\/079017-2000"}],"event":{"name":"ICPP '26: Proceedings of the 55th International Conference on Parallel Processing","location":"Singapore , Singapore","acronym":"ICPP '26"},"container-title":["Proceedings of the 55th International Conference on Parallel Processing"],"original-title":[],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T18:07:32Z","timestamp":1789582052000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3832810.3832869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,27]]},"references-count":30,"alternative-id":["10.1145\/3832810.3832869","10.1145\/3832810"],"URL":"https:\/\/doi.org\/10.1145\/3832810.3832869","relation":{},"subject":[],"published":{"date-parts":[[2026,9,27]]},"assertion":[{"value":"2026-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}