{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:39:58Z","timestamp":1757619598767,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819500130"},{"type":"electronic","value":"9789819500147"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-95-0014-7_13","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T10:06:05Z","timestamp":1753351565000},"page":"149-160","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ALMP: Automatic Layer-By-Layer Mixed-Precision Quantization for Large Language Models"],"prefix":"10.1007","author":[{"given":"Jie","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanxi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"13_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., et al.: Gpt-4 technical report (2023). arXiv preprint arXiv:2303.08774"},{"key":"13_CR2","unstructured":"Liu, A., Feng, B., Xue, B., et al.: Deepseek-v3 technical report (2024). arXiv preprint arXiv:2412.19437"},{"key":"13_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR4","unstructured":"Yao, Z., Li, C., Wu, X., et al.: A comprehensive study on post-training quantization for large language models (2023). arXiv preprint arXiv:2303.08302"},{"key":"13_CR5","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., et al.: Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale. Adv. Neural Inf. Process. Syst. 35, 30318\u201330332 (2022)"},{"key":"13_CR6","unstructured":"Xiao, G., Lin, J., Seznec, M., et al.: Smoothquant: accurate and efficient post-training quantization for large language models. International Conference on Machine Learning. PMLR, pp. 38087\u201338099 (2023)"},{"key":"13_CR7","unstructured":"Shao, W., Chen, M., Zhang, Z., et al.: Omniquant: omnidirectionally calibrated quantization for large language models (2023). arXiv preprint arXiv:2308.13137"},{"key":"13_CR8","unstructured":"Touvron, H., Lavril, T., Izacard, G., et al.: Llama: open and efficient foundation language models (2023). arXiv preprint arXiv:2302.13971"},{"key":"13_CR9","unstructured":"Bai, J., Bai, S., Chu, Y., et al.: Qwen technical report (2023). arXiv preprint arXiv:2309.16609"},{"key":"13_CR10","unstructured":"Merity, S., Xiong, C., Bradbury, J., et al.: Pointer sentinel mixture models (2016). arXiv preprint arXiv:1609.07843"},{"key":"13_CR11","first-page":"17402","volume":"35","author":"X Wei","year":"2022","unstructured":"Wei, X., Zhang, Y., Zhang, X., et al.: Outlier suppression: pushing the limit of low-bit transformer language models. Adv. Neural. Inf. Process. Syst. 35, 17402\u201317414 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR12","unstructured":"Liu, J., Gong, R., Wei, X., et al.: Qllm: accurate and efficient low-bitwidth quantization for large language models (2023). arXiv preprint arXiv:2310.08041"},{"key":"13_CR13","first-page":"87766","volume":"37","author":"H Lin","year":"2024","unstructured":"Lin, H., Xu, H., Wu, Y., et al.: Duquant: distributing outliers via dual transformation makes stronger quantized LLMs. Adv. Neural. Inf. Process. Syst. 37, 87766\u201387800 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR14","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273\u2013297 (1995)","journal-title":"Mach. Learn."},{"issue":"1","key":"13_CR15","doi-asserted-by":"publisher","first-page":"31","DOI":"10.17849\/insm-47-01-31-39.1","volume":"47","author":"SJ Rigatti","year":"2017","unstructured":"Rigatti, S.J.: Random forest. J. Insur. Med. 47(1), 31\u201339 (2017)","journal-title":"J. Insur. Med."},{"issue":"4","key":"13_CR16","doi-asserted-by":"publisher","first-page":"327","DOI":"10.2307\/3001655","volume":"7","author":"J Berkson","year":"1951","unstructured":"Berkson, J.: Why i prefer logits to probits. Biometrics 7(4), 327\u2013339 (1951)","journal-title":"Biometrics"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining. Pp. 785\u2013794 (2016)","DOI":"10.1145\/2939672.2939785"}],"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\/978-981-95-0014-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T21:29:30Z","timestamp":1757280570000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0014-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500130","9789819500147"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0014-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","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":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}