{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:50:10Z","timestamp":1757609410627,"version":"3.44.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031998539"},{"type":"electronic","value":"9783031998546"}],"license":[{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"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\/978-3-031-99854-6_20","type":"book-chapter","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T15:07:15Z","timestamp":1756307235000},"page":"292-306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DynoInfer: Adaptive Resource Orchestration for\u00a0LLM Inference on\u00a0Resource-Constrained PCs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1690-4223","authenticated-orcid":false,"given":"Yunling","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3692-4761","authenticated-orcid":false,"given":"Qingyin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0385-8416","authenticated-orcid":false,"given":"Zhitao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5609-3571","authenticated-orcid":false,"given":"Yang","family":"Ou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-5715","authenticated-orcid":false,"given":"Zhiguang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"20_CR1","unstructured":"llama.cpp. https:\/\/github.com\/ggml-org\/llama.cpp"},{"key":"20_CR2","unstructured":"philschmid. https:\/\/huggingface.co\/datasets\/philschmid\/sharegpt-raw"},{"key":"20_CR3","first-page":"114","volume":"6","author":"M Adnan","year":"2024","unstructured":"Adnan, M., et al.: Keyformer: Kv cache reduction through key tokens selection for efficient generative inference. Proc. Mach. Learn. Syst. 6, 114\u2013127 (2024)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Alizadeh, K., et\u00a0al.: Llm in a flash: efficient large language model inference with limited memory. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12562\u201312584 (2024)","DOI":"10.18653\/v1\/2024.acl-long.678"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Chevalier, A., et\u00a0al.: Adapting language models to compress contexts. arXiv preprint arXiv:2305.14788 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.232"},{"key":"20_CR6","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing gpt-4 with 90%* chatgpt quality, march 2023. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna3(5) (2023)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Chuang, Y.N., et\u00a0al.: Learning to compress prompt in natural language formats. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 7749\u20137760 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.429"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Guo, L., et\u00a0al.: Sti: Turbocharge nlp inference at the edge via elastic pipelining. In: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (2023)","DOI":"10.1145\/3575693.3575698"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Hwang, R., et\u00a0al.: Pre-gated moe: an algorithm-system co-design for fast and scalable mixture-of-expert inference. In: 2024 ACM\/IEEE 51st Annual International Symposium on Computer Architecture (ISCA), pp. 1018\u20131031. IEEE (2024)","DOI":"10.1109\/ISCA59077.2024.00078"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, H., et\u00a0al.: Longllmlingua: accelerating and enhancing llms in long context scenarios via prompt compression. arXiv preprint arXiv:2310.06839 (2023)","DOI":"10.18653\/v1\/2024.acl-long.91"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., et\u00a0al.: Compressing context to enhance inference efficiency of large language models. arXiv preprint arXiv:2310.06201 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.391"},{"key":"20_CR12","unstructured":"Liu, Z., et\u00a0al.: Deja vu: contextual sparsity for efficient llms at inference time. In: Proceedings of the 40th International Conference on Machine Learning, pp. 22137\u201322176 (2023)"},{"key":"20_CR13","first-page":"52342","volume":"36","author":"Z Liu","year":"2023","unstructured":"Liu, Z., et al.: Scissorhands: exploiting the persistence of importance hypothesis for llm kv cache compression at test time. Adv. Neural. Inf. Process. Syst. 36, 52342\u201352364 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR14","first-page":"19327","volume":"36","author":"J Mu","year":"2023","unstructured":"Mu, J., et al.: Learning to compress prompts with gist tokens. Adv. Neural. Inf. Process. Syst. 36, 19327\u201319352 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR15","unstructured":"Sun, M., et\u00a0al.: A simple and effective pruning approach for large language models. arXiv preprint arXiv:2306.11695 (2023)"},{"key":"20_CR16","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Wingate, D., et\u00a0al.: Prompt compression and contrastive conditioning for controllability and toxicity reduction in language models. In: Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 5621\u20135634 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.412"},{"key":"20_CR18","unstructured":"Xiao, G., et\u00a0al.: Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453 (2023)"},{"key":"20_CR19","unstructured":"Yi, R., et\u00a0al.: Edgemoe: fast on-device inference of moe-based large language models. arXiv preprint arXiv:2308.14352 (2023)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2025: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-99854-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T09:43:42Z","timestamp":1756892622000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-99854-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"ISBN":["9783031998539","9783031998546"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-99854-6_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"27 August 2025","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":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dresden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}