{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:03:12Z","timestamp":1779944592453,"version":"3.53.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032273574","type":"print"},{"value":"9783032273581","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-27358-1_2","type":"book-chapter","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T04:15:56Z","timestamp":1779941756000},"page":"21-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HyperCluster: Decentralized Large Language Model Inference over\u00a0Peer-to-Peer Wireless Networks"],"prefix":"10.1007","author":[{"given":"P.","family":"Samarth","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vyoman","family":"Jain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjiv","family":"Raghunandan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akepati Ramya","family":"Sri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richa","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","unstructured":"Borzunov, A., et al.: Petals: collaborative inference and fine-tuning of large models. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 558\u2013568 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-demo.54","DOI":"10.18653\/v1\/2023.acl-demo.54"},{"key":"2_CR2","unstructured":"ExoLabs: EXO: run your own ai cluster at home with everyday devices (2024). https:\/\/github.com\/exo-explore\/exo"},{"key":"2_CR3","unstructured":"Ford, B., Srisuresh, P., Kegel, D.: Peer-to-peer communication across network address translators. In: Proceedings of the 2005 USENIX Annual Technical Conference (USENIX ATC 2005), p. 13 (2005)"},{"key":"2_CR4","unstructured":"Grattafiori, A., et\u00a0al.: The LLaMA 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"2_CR5","unstructured":"HuggingFace: Safetensors: a simple, safe way to store and distribute tensors (2022). https:\/\/github.com\/huggingface\/safetensors"},{"key":"2_CR6","unstructured":"HyperSpace: Hyperspace: Peer-to-peer AI network (2024). https:\/\/hyperspace.computer\/bittorrent-for-ai.pdf"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Iyengar, J., Thomson, M.: QUIC: a UDP-based multiplexed and secure transport. RFC\u00a09000, IETF (2021). https:\/\/doi.org\/10.17487\/RFC9000","DOI":"10.17487\/RFC9000"},{"key":"2_CR8","unstructured":"Jaghouar, S., et\u00a0al.: Intellect-1 technical report. arXiv preprint arXiv:2412.01152 (2024)"},{"key":"2_CR9","unstructured":"Li, Z., et\u00a0al.: Prima.cpp: Fast 30-70b LLM inference on heterogeneous and low-resource home clusters. arXiv preprint arXiv:2504.08791 (2025)"},{"key":"2_CR10","unstructured":"n0, Inc.: Iroh: P2P for everyone (2024). https:\/\/www.iroh.computer"},{"issue":"2","key":"2_CR11","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.jpdc.2008.09.002","volume":"69","author":"P Patarasuk","year":"2009","unstructured":"Patarasuk, P., Yuan, X.: Bandwidth-optimal all-reduce algorithms for clusters of workstations. J. Parallel Distrib. Comput. 69(2), 117\u2013124 (2009). https:\/\/doi.org\/10.1016\/j.jpdc.2008.09.002","journal-title":"J. Parallel Distrib. Comput."},{"key":"2_CR12","doi-asserted-by":"publisher","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: DeepSpeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 3505\u20133506 (2020). https:\/\/doi.org\/10.1145\/3394486.3406703","DOI":"10.1145\/3394486.3406703"},{"key":"2_CR13","unstructured":"Shoeybi, M., et\u00a0al.: Megatron-LM: training multi-billion parameter language models using model parallelism (2019)"},{"key":"2_CR14","unstructured":"Tadych, B.: Distributed-LLaMA: connect home devices into a powerful cluster to accelerate LLM inference (2024). https:\/\/github.com\/b4rtaz\/distributed-llama"},{"key":"2_CR15","unstructured":"Tong, C., et\u00a0al.: Parallax: efficient LLM inference service over decentralized environment (2025)"},{"key":"2_CR16","unstructured":"Tong, J., et\u00a0al.: JARVIS: disjoint large language models on radio VLANs for inference serving (2024)"},{"key":"2_CR17","unstructured":"Wang, Z., et\u00a0al.: Tokenring: an efficient parallelism framework for infinite-context LLMs via bidirectional communication (2024)"},{"key":"2_CR18","doi-asserted-by":"publisher","unstructured":"Wolf, T., et\u00a0al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"2_CR19","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report (2025)"},{"key":"2_CR20","unstructured":"Yang, W., et\u00a0al.: Lattica: a decentralized cross-NAT communication framework for scalable ai inference and training. arXiv preprint arXiv:2510.00183 (2025)"},{"key":"2_CR21","unstructured":"Zheng, L., et\u00a0al.: Alpa: automating inter-and $$\\{$$Intra-Operator$$\\}$$ parallelism for distributed deep learning. In: 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2022), pp. 559\u2013578 (2022)"}],"container-title":["Lecture Notes in Computer Science","Distributed Applications and Interoperable Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-27358-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T04:16:06Z","timestamp":1779941766000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-27358-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032273574","9783032273581"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-27358-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"29 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"DAIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Distributed Applications and Interoperable Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urbino","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"8 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dais2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.discotec.org\/2026\/dais","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}