{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:08:59Z","timestamp":1763190539328,"version":"3.45.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032104588","type":"print"},{"value":"9783032104595","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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\/978-3-032-10459-5_33","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:06:45Z","timestamp":1763190405000},"page":"423-435","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learnable Cloud-Guided LLM Quantization for\u00a0Resource-Constrained Edge Devices"],"prefix":"10.1007","author":[{"given":"Qinxiao","family":"Deng","sequence":"first","affiliation":[]},{"given":"Tianfu","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Benteng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Bingbing","family":"Nie","sequence":"additional","affiliation":[]},{"given":"Xiaoming","family":"He","sequence":"additional","affiliation":[]},{"given":"Yingchi","family":"Mao","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"key":"33_CR1","unstructured":"Zhang, S., Roller, S., Goyal, N., et al.: OPT: Open Pre-trained Transformer Language Models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"33_CR2","unstructured":"Le Scao, T., Fan, A., Akiki, C., et al.: BLOOM: A 176B-Parameter Open-Access Multilingual Language Model. arXiv preprint arXiv:2211.05100 (2022)"},{"key":"33_CR3","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.comcom.2018.01.007","volume":"118","author":"K Abas","year":"2018","unstructured":"Abas, K., Obraczka, K., Miller, L.: Solar-powered, wireless smart camera network: an IoT solution for outdoor video monitoring. Comput. Commun. 118, 217\u2013233 (2018)","journal-title":"Comput. Commun."},{"key":"33_CR4","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"33_CR5","unstructured":"Brown, T., Mann, B., Ryder, N., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"33_CR6","unstructured":"Xiao, G., Lin, J., Seznec, M., et al.: Smoothquant: accurate and efficient post-training quantization for large language models. In: PMLR, pp. 38087\u201338099 (2023)"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhang, Y., Li, Y., et al.: Outlier suppression+: accurate quantization of large language models by equivalent and effective shifting and scaling. In: Empirical Methods in Natural Language Processing, pp. 1648\u20131665 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.102"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Hooper, C., Kim, S., et al.: KVQuant: towards 10 million context length LLM inference with KV cache quantization. In: Advances in Neural Information Processing Systems, vol. 37, pp. 1270\u20131303 (2024)","DOI":"10.52202\/079017-0040"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Liu, R., et al.: IntactKV: improving large language model quantization by keeping pivot tokens intact. In: ACL, pp. 7716\u20137741 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.460"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Luo, Z., Kulmizev, A., Mao, X.: Positional artefacts propagate through masked language model embeddings. In: ACL-IJCNLP, vol. 1, pp. 5312\u20135327 (2021)","DOI":"10.18653\/v1\/2021.acl-long.413"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Bondarenko, Y., Nagel, M., Blankevoort, T.: Understanding and overcoming the challenges of efficient transformer quantization. In: EMNLP, pp. 7947\u20137969 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.627"},{"key":"33_CR12","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"33_CR13","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: LLM.int8(): 8-bit matrix multiplication for transformers at scale. arXiv preprint arXiv:2208.07339 (2022)"},{"key":"33_CR14","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. In: ICLR (2017)"},{"key":"33_CR15","unstructured":"Colin, R., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. Mach. Learn. Res. 21 (2020)"},{"key":"33_CR16","unstructured":"Clark, P., et al.: Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge. arXiv preprint arXiv:1803.05457 (2018)"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Zellers, R., Holtzman, A., Bisk, Y., et al.: HellaSwag: can a machine really finish your sentence? In: ACL, pp. 4791\u20134800 (2020)","DOI":"10.18653\/v1\/P19-1472"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Bisk, Y., Zellers, R., Le Bras, R., et al.: PIQA: reasoning about physical commonsense in natural language. In: AAAI, pp. 7432\u20137439 (2020)","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Sakaguchi, K., et al.: WinoGrande: an adversarial winograd schema challenge at scale. In: AAAI, pp. 8732\u20138740 (2020)","DOI":"10.1609\/aaai.v34i05.6399"},{"key":"33_CR20","unstructured":"Shao, W., Chen, M., Zhang, Z., et al.: OmniQuant: omnidirectionally calibrated quantization for large language models. In: ICLR (2024)"},{"key":"33_CR21","unstructured":"Li, S., Ning, X., Wang, L., et al.: Evaluating Quantized Large Language Models. arXiv preprint arXiv:2402.18158 (2024)"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10459-5_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:06:49Z","timestamp":1763190409000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10459-5_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9783032104588","9783032104595"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10459-5_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nha Trang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"14 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 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":"npc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.npc-conference.com\/#\/npc2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}