{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T23:03:19Z","timestamp":1784329399554,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233939","type":"print"},{"value":"9789819233946","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"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\/978-981-92-3394-6_26","type":"book-chapter","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T22:21:08Z","timestamp":1784326868000},"page":"306-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient 4-bit Quantized Inference for LLMs on RISC-V via RVV-Based GGUF Weight Layout Reconfiguration"],"prefix":"10.1007","author":[{"given":"Zhilong","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,18]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/978-3-031-85747-8_3","volume-title":"Enhancing LLM Performance: Efficacy, Fine-Tuning, and Inference Techniques","author":"H Shen","year":"2025","unstructured":"Shen, H., Chang, H., Dong, B., Luo, Y., Meng, H.: Efficient LLM inference on CPUs. In: Enhancing LLM Performance: Efficacy, Fine-Tuning, and Inference Techniques, pp. 33\u201346. Springer (2025)"},{"key":"26_CR2","doi-asserted-by":"publisher","first-page":"1690","DOI":"10.1109\/SCW63240.2024.00211","volume-title":"SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"N Brown","year":"2024","unstructured":"Brown, N., Barton, R.: Accelerating stencils on the Tenstorrent Grayskull RISC-V accelerator. In: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1690\u20131700. IEEE (2024)"},{"issue":"5","key":"26_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3772277","volume":"58","author":"G Agosta","year":"2025","unstructured":"Agosta, G., Galimberti, A., Zoni, D.: Deep learning on RISC-V platforms at the edge: a perspective on the hardware and software support. ACM Comput. Surv. 58(5), 1\u201337 (2025)","journal-title":"ACM Comput. Surv."},{"key":"26_CR4","unstructured":"Assir, I.A., Iskandarani, M.E., Sandid, H.R.A., Saghir, M.A.: Arrow: A RISC-V Vector Accelerator for Machine Learning Inference. arXiv preprint https:\/\/arxiv.org\/abs\/2107.07169 (2021)."},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Peccia, F.N., Haxel, F., Bringmann, O.: Tensor Program Optimization for the RISC-V Vector Extension Using Probabilistic Programs. arXiv preprint https:\/\/arxiv.org\/abs\/2507.01457 (2025).","DOI":"10.1109\/ICCAD66269.2025.11241007"},{"key":"26_CR6","unstructured":"Georgi, G., et al.: 2026 (ed.): Llama.cpp. https:\/\/github.com\/ggml-org\/llama.cpp. Accessed 26 Jan 2026"},{"key":"26_CR7","first-page":"1","volume-title":"2023 21st IEEE Interregional NEWCAS Conference (NEWCAS)","author":"T Dupuis","year":"2023","unstructured":"Dupuis, T., et al.: Sparq: a custom RISC-V vector processor for efficient sub-byte quantized inference. In: 2023 21st IEEE Interregional NEWCAS Conference (NEWCAS), pp. 1\u20135. IEEE (2023)"},{"key":"26_CR8","first-page":"1","volume-title":"2023 IEEE International Symposium on Circuits and Systems (ISCAS)","author":"M Askari Hemmat","year":"2023","unstructured":"Askari Hemmat, M., et al.: Quark: an integer RISC-V vector processor for sub-byte quantized DNN inference. In: 2023 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1\u20135. IEEE (2023)"},{"issue":"13","key":"26_CR9","doi-asserted-by":"publisher","first-page":"25676","DOI":"10.1109\/JIOT.2025.3560382","volume":"12","author":"H Mart\u00ednez","year":"2025","unstructured":"Mart\u00ednez, H., Catal\u00e1n, S., Castell\u00f3, A., Mestre, J.I., Quintana-Ort\u00ed, E.S.: Latency-critical quantized inference with transformer decoders on ARM and RISC-V CPUs. IEEE Internet Things J. 12(13), 25676\u201325690 (2025)","journal-title":"IEEE Internet Things J."},{"key":"26_CR10","first-page":"1","volume-title":"Proceedings of the 29th Annual International Conference on Mobile Computing and Networking","author":"X Tang","year":"2023","unstructured":"Tang, X., et al.: Lut-NN: empower efficient neural network inference with centroid learning and table lookup. In: Proceedings of the 29th Annual International Conference on Mobile Computing and Networking, pp. 1\u201315 (2023)"},{"key":"26_CR11","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/IPDPS54959.2023.00024","volume-title":"2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","author":"SR Gupta","year":"2023","unstructured":"Gupta, S.R., Papadopoulou, N., Pericas, M.: Accelerating CNN inference on long vector architectures via co-design. In: 2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 145\u2013155. IEEE (2023)"},{"key":"26_CR12","first-page":"1","volume-title":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","author":"C Wang","year":"2024","unstructured":"Wang, C., Fang, C., Wu, X., Wang, Z., Lin, J.: A scalable RISC-V vector processor enabling efficient multi-precision DNN inference. In: 2024 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1\u20135. IEEE (2024)"},{"key":"26_CR13","first-page":"635","volume-title":"International Conference on Machine Learning and Computing","author":"W Wang","year":"2025","unstructured":"Wang, W., et al.: Design and implementation of a high-performance operator library for RISC-V vector extension. In: International Conference on Machine Learning and Computing, pp. 635\u2013646. Springer (2025)"},{"key":"26_CR14","first-page":"515","volume-title":"International Conference on Intelligent Computing","author":"Z Liu","year":"2025","unstructured":"Liu, Z., et al.: Accelerating LLM inference on RISC-V edge devices via vector extension optimization. In: International Conference on Intelligent Computing, pp. 515\u2013526. Springer (2025)"},{"issue":"2164","key":"26_CR15","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0155","volume":"378","author":"A Garofalo","year":"2020","unstructured":"Garofalo, A., Rusci, M., Conti, F., Rossi, D., Benini, L.: PULP-NN: accelerating quantized neural networks on parallel ultra-low-power RISC-V processors. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 378(2164), 20190155 (2020)","journal-title":"Philos. Trans. R. Soc. A Math. Phys. Eng. Sci."},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Matsui, Y., Imaizumi, Y., Miyamoto, N., Yoshifuji, N.: Arm 4-bit PQ: SIMD-based acceleration for approximate nearest neighbor search on ARM. In: ICASSP 2022--2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2080\u20132084. IEEE (2022).","DOI":"10.1109\/ICASSP43922.2022.9746589"},{"key":"26_CR17","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1145\/3689031.3696099","volume-title":"Proceedings of the Twentieth European Conference on Computer Systems","author":"J Wei","year":"2025","unstructured":"Wei, J., et al.: T-MAC: CPU renaissance via table lookup for low-bit LLM deployment on edge. In: Proceedings of the Twentieth European Conference on Computer Systems, pp. 278\u2013292 (2025)"},{"key":"26_CR18","doi-asserted-by":"publisher","first-page":"112706","DOI":"10.52202\/079017-3581","volume":"37","author":"T Zhang","year":"2024","unstructured":"Zhang, T., Yi, J., Yao, B., Xu, Z., Shrivastava, A.: Nomad-attention: efficient LLM inference on CPUs through multiply-add-free attention. Adv. Neural Inf. Process. Syst. 37, 112706\u2013112730 (2024)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"26_CR19","unstructured":"Radford, C.: Design and optimization of low-power RISC-V processors for edge AI applications. J. Comput. Technol. Softw. 4(7) (2025)"},{"issue":"4","key":"26_CR20","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1007\/s11390-023-1266-6","volume":"38","author":"R-S Li","year":"2023","unstructured":"Li, R.-S., Peng, P., Shao, Z.-Y., Jin, H., Zheng, R.: Evaluating RISC-V vector instruction set architecture extension with computer vision workloads. J. Comput. Sci. Technol. 38(4), 807\u2013820 (2023)","journal-title":"J. Comput. Sci. Technol."}],"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\/978-981-92-3394-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T22:21:10Z","timestamp":1784326870000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3394-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,18]]},"ISBN":["9789819233939","9789819233946"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3394-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,18]]},"assertion":[{"value":"18 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"}}]}}