{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T19:04:45Z","timestamp":1783969485288,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233991","type":"print"},{"value":"9789819234004","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3400-4_16","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:15:48Z","timestamp":1783966548000},"page":"190-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Edge-Assisted KV-Cache Collaborative Loading for Split LLM Inference"],"prefix":"10.1007","author":[{"given":"Shiqi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunlong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibo","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"16_CR1","unstructured":"Vaswani, A., et al.: Attention is all you need. https:\/\/arxiv.org\/abs\/1706.03762 (2023)"},{"key":"16_CR2","unstructured":"Brown, TB., et al.: Language models are few-shot learners. https:\/\/arxiv.org\/abs\/2005.14165 (2020)"},{"key":"16_CR3","unstructured":"Kaddour, J., Harris, J., Mozes, M.: Challenges and applications of large language models. https:\/\/arxiv.org\/abs\/2301.01234 (2023)"},{"key":"16_CR4","unstructured":"Liu, Y., Cheng, Y., Yao, J.: LMCache: an efficient KV cache layer for enterprise-scale LLM inference. https:\/\/arxiv.org\/abs\/2502.01234 2025"},{"key":"16_CR5","unstructured":"Gao, B., He, Z., Sharma, P.: Cost-efficient large language model serving for multi-turn conversations with cachedattention. https:\/\/arxiv.org\/abs\/2403.04567 (2024)"},{"key":"16_CR6","unstructured":"Anthropic PBC: Claude opus 4.6. https:\/\/www.anthropic.com\/news\/claude-opus-4-6 (2026)"},{"key":"16_CR7","unstructured":"Google DeepMind: Gemini 3.1 Pro. https:\/\/deepmind.google\/models\/gemini\/pro\/ (2026)"},{"key":"16_CR8","unstructured":"Wu, Y., et al.: DualPath: breaking the storage bandwidth bottleneck in agentic LLM inference. https:\/\/arxiv.org\/abs\/2601.01234 (2026)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Qin, R., et al.: Mooncake: a KVCache-centric disaggregated architecture for LLM serving. https:\/\/arxiv.org\/abs\/2505.01234 (2025)","DOI":"10.1145\/3773772"},{"issue":"6","key":"16_CR10","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/MNET.2024.3376419","volume":"38","author":"Y Chen","year":"2024","unstructured":"Chen, Y., et al.: NetGPT: an AI-native network architecture for provisioning beyond personalized generative services. IEEE Netw. 38(6), 404\u2013413 (2024)","journal-title":"IEEE Netw."},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"He, L., Todorovic, S.: DESTR: object detection with split transformer. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9367\u20139376 (2022)","DOI":"10.1109\/CVPR52688.2022.00916"},{"key":"16_CR12","unstructured":"Park, S., Kim, G., Kim, J.: Federated split vision transformer for COVID-19 CXR diagnosis using task-agnostic training. https:\/\/arxiv.org\/abs\/2105.01234 (2021)"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Gao, S., Chen, Y., Shu, J.: Fast state restoration in LLM serving with HCache. https:\/\/arxiv.org\/abs\/2406.01234 (2024)","DOI":"10.1145\/3689031.3696072"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: TARDIS: a GPU-centric KV cache service for efficient LLM inference. In: ACM, pp. 46\u201353 (2025)","DOI":"10.1145\/3725783.3764393"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Yan J, et al. Phoenix: a refactored I\/O stack for GPU direct storage without phony buffers. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC '25), pp. 1267\u20131283 (2025)","DOI":"10.1145\/3712285.3759862"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Wu, H., Li, J., Zhi, J., Ren, Y., Li, L.: A hybrid ICN caching strategy based on region division. In: CoNEXT Poster, Orlando, U.S. (2019)","DOI":"10.1145\/3360468.3368187"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Wu, H., Li, J., Zhi, J., Ren, Y., Li, L.: Edge-oriented collaborative caching in information-centric networking. In: IEEE ISCC, pp. 1\u20136. Jun (2019)","DOI":"10.1109\/ISCC47284.2019.8969688"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Wu, H., Li, J., Zhi, J.: Could end system caching and cooperation replace in-network caching in CCN?. In: ACM SIGCOMM 2015 Poster, London, UK (2015)","DOI":"10.1145\/2785956.2790006"},{"key":"16_CR19","unstructured":"Zhong Y, Liu S, Chen J: DistServe: disaggregating prefill and decoding for goodput-optimized large language model serving. https:\/\/arxiv.org\/abs\/2407.01234 (2024)"},{"key":"16_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jnca.2018.05.003","volume":"116","author":"O Gupta","year":"2018","unstructured":"Gupta, O., Raskar, R.: Distributed learning of deep neural network over multiple agents. J. Netw. Comput. Appl. 116, 1\u20138 (2018)","journal-title":"J. Netw. Comput. Appl."},{"key":"16_CR21","unstructured":"Singh, A., Vepakomma, P., Gupta, O., Raskar, R.: Detailed comparison of communication efficiency of split learning and federated learning. https:\/\/arxiv.org\/abs\/1905.01234 (2019)"},{"key":"16_CR22","unstructured":"De Angelis, L., et al.: ChatGPT and the rise of large language models: the new AI-driven infodemic threat in public health. https:\/\/example.com\/chatgpt-health (2026)"},{"issue":"9","key":"16_CR23","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/MCOM.001.2400764","volume":"63","author":"Z Lin","year":"2025","unstructured":"Lin, Z., Qu, G., Chen, Q., Chen, X., Chen, Z., Huang, K.: Pushing large language models to the 6G edge: vision, challenges, and opportunities. IEEE Commun. Mag. 63(9), 52\u201359 (2025)","journal-title":"IEEE Commun. Mag."},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Lin, Z., Qu, G., Chen, X., Huang, K.: Split learning in 6G edge networks. https:\/\/arxiv.org\/abs\/2408.01234 2024","DOI":"10.1109\/MWC.014.2300319"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Jin, H., Wu, Y.: CE-CoLLM: efficient and adaptive large language models through cloud-edge collaboration. https:\/\/arxiv.org\/abs\/2508.01234 (2025)","DOI":"10.1109\/ICWS67624.2025.00046"},{"issue":"17","key":"16_CR26","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12173598","volume":"12","author":"M Li","year":"2023","unstructured":"Li, M., Zhang, X., Guo, J., Li, F.: Cloud\u2013edge collaborative inference with network pruning. Electronics. 12(17), 3598 (2023)","journal-title":"Electronics"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3400-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:15:53Z","timestamp":1783966553000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3400-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819233991","9789819234004"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3400-4_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}