{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T16:36:09Z","timestamp":1786725369063,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032352507","type":"print"},{"value":"9783032352514","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T00:00:00Z","timestamp":1786752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T00:00:00Z","timestamp":1786752000000},"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\/978-3-032-35251-4_21","type":"book-chapter","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T16:03:18Z","timestamp":1786723398000},"page":"301-315","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Layer-Wise CPU-GPU Scheduling for\u00a0LLM Inference on\u00a0Memory-Limited Consumer GPUs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5970-9422","authenticated-orcid":false,"given":"Naoto","family":"Sugiura","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuta","family":"Tokusashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-3842","authenticated-orcid":false,"given":"Hiroki","family":"Matsutani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,15]]},"reference":[{"key":"21_CR1","unstructured":"Generative AI 2025: Assessing opportunities and disruptions in an evolving trillion-dollar-plus market (2024). https:\/\/assets.bbhub.io\/professional\/sites\/41\/Generative-AI-Outlook.pdf. Accessed 04 Mar 2026"},{"key":"21_CR2","unstructured":"Gartner says AI PCs will represent 31% of worldwide PC market by the end of 2025 (2025). https:\/\/www.gartner.com\/en\/newsroom\/press-releases\/2025-08-28-gartner-says-artificial-intelligence-pcs-will-represent-31-percent-of-worldwide-pc-market-by-the-end-of-2025. Accessed 04 Mar 2026"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Aminabadi, R.Y., et al.: Deepspeed-inference: enabling efficient inference of transformer models at unprecedented scale. In: SC22: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315. IEEE (2022)","DOI":"10.1109\/SC41404.2022.00051"},{"key":"21_CR4","unstructured":"Hugging Face: Hugging Face Accelerate (2022). https:\/\/github.com\/huggingface\/accelerate. Accessed 16 Feb 2026"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Jiang, C., Gao, L., Zarch, H.E., Annavaram, M.: KVPR: Efficient LLM inference with I\/O-aware KV cache partial recomputation. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 19474\u201319488 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.997"},{"key":"21_CR6","unstructured":"Na, S., et al.: Flexinfer: Flexible LLM inference with CPU computations. Proc. Mach. Learn. Syst. 7 (2025)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Park, D., Egger, B.: Improving throughput-oriented LLM inference with CPU computations. In: Proceedings of the 2024 International Conference on Parallel Architectures and Compilation Techniques, pp. 233\u2013245 (2024)","DOI":"10.1145\/3656019.3676949"},{"key":"21_CR8","unstructured":"Sheng, Y., et al.: Flexgen: high-throughput generative inference of large language models with a single GPU. In: International Conference on Machine Learning, pp. 31094\u201331116. PMLR (2023)"},{"key":"21_CR9","unstructured":"Sun, H., et al.: Shadowkv: KV cache in shadows for high-throughput long-context LLM inference. arXiv preprint arXiv:2410.21465 (2024)"},{"key":"21_CR10","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"21_CR11","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"21_CR12","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"21_CR13","unstructured":"Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., Han, S.: Smoothquant: accurate and efficient post-training quantization for large language models. In: International Conference on Machine Learning, pp. 38087\u201338099. PMLR (2023)"},{"key":"21_CR14","unstructured":"Xu, J., et al.: On-device language models: a comprehensive review. arXiv preprint arXiv:2409.00088 (2024)"},{"key":"21_CR15","unstructured":"Yang, Z., Jia, X., Li, H., Yan, J.: Llm4drive: a survey of large language models for autonomous driving. arXiv preprint arXiv:2311.01043 (2023)"},{"key":"21_CR16","unstructured":"Zeng, F., Gan, W., Wang, Y., Liu, N., Yu, P.S.: Large language models for robotics: a survey. arXiv preprint arXiv:2311.07226 (2023)"},{"key":"21_CR17","unstructured":"Zhang, S., et al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"21_CR18","first-page":"162","volume":"6","author":"X Zhao","year":"2024","unstructured":"Zhao, X., Jia, B., Zhou, H., Liu, Z., Cheng, S., You, Y.: Hetegen: efficient heterogeneous parallel inference for large language models on resource-constrained devices. Proc. Mach. Learn. Syst. 6, 162\u2013172 (2024)","journal-title":"Proc. Mach. Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2026: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-35251-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T16:03:21Z","timestamp":1786723401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-35251-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,15]]},"ISBN":["9783032352507","9783032352514"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-35251-4_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,15]]},"assertion":[{"value":"15 August 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","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"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":"Pisa","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":"24 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2026.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}