{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T19:35:53Z","timestamp":1793820953852,"version":"4.6.1"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819670291","type":"print"},{"value":"9789819670307","type":"electronic"}],"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\/978-981-96-7030-7_23","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T12:39:29Z","timestamp":1750682369000},"page":"327-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for\u00a0LLaMA-Based Language Models"],"prefix":"10.1007","author":[{"given":"Lucas","family":"Maisonnave","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cyril","family":"Moineau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Bichler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabrice","family":"Rastello","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"23_CR1","first-page":"34278","volume":"36","author":"A Ahmadian","year":"2023","unstructured":"Ahmadian, A., et al.: Intriguing properties of quantization at scale. Adv. Neural. Inf. Process. Syst. 36, 34278\u201334294 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Bondarenko, Y., Nagel, M., Blankevoort, T.: Understanding and overcoming the challenges of efficient transformer quantization. arXiv preprint arXiv:2109.12948 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.627"},{"key":"23_CR3","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale. In: Advances in Neural Information Processing Systems, vol. 35, pp. 30318\u201330332 (2022)"},{"key":"23_CR4","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLoRA: efficient finetuning of quantized LLMs. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"23_CR5","unstructured":"Du, N., et\u00a0al.: GLaM: efficient scaling of language models with mixture-of-experts. In: International Conference on Machine Learning, pp. 5547\u20135569. PMLR (2022)"},{"key":"23_CR6","unstructured":"Frantar, E., Ashkboos, S., Hoefler, T., Alistarh, D.: GPTQ: accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323 (2022)"},{"key":"23_CR7","unstructured":"He, B., Noci, L., Paliotta, D., Schlag, I., Hofmann, T.: Understanding and minimising outlier features in neural network training. arXiv preprint arXiv:2405.19279 (2024)"},{"key":"23_CR8","unstructured":"HuggingFace: Meta-Llama-3-8B (2024). https:\/\/huggingface.co\/meta-llama\/Meta-Llama-3-8B"},{"key":"23_CR9","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"23_CR10","unstructured":"Le\u00a0Scao, T., et\u00a0al.: Bloom: a 176b-parameter open-access multilingual language model (2023)"},{"key":"23_CR11","unstructured":"Ma, S., et al.: The era of 1-bit LLMs: all large language models are in 1.58 bits. arXiv preprint arXiv:2402.17764 (2024)"},{"key":"23_CR12","unstructured":"Micikevicius, P., et\u00a0al.: FP8 formats for deep learning. arXiv preprint arXiv:2209.05433 (2022)"},{"key":"23_CR13","unstructured":"Paglieri, D., Dash, S., Rockt\u00e4schel, T., Parker-Holder, J.: Outliers and calibration sets have diminishing effect on quantization of modern LLMs. arXiv preprint arXiv:2405.20835 (2024)"},{"key":"23_CR14","first-page":"483","volume":"6","author":"H Shen","year":"2024","unstructured":"Shen, H., Mellempudi, N., He, X., Gao, Q., Wang, C., Wang, M.: Efficient post-training quantization with FP8 formats. Proc. Mach. Learn. Syst. 6, 483\u2013498 (2024)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Son, S., Park, W., Han, W., Kim, K., Lee, J.: Prefixing attention sinks can mitigate activation outliers for large language model quantization. arXiv preprint arXiv:2406.12016 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.134"},{"key":"23_CR16","unstructured":"Sun, M., Chen, X., Kolter, J.Z., Liu, Z.: Massive activations in large language models. arXiv preprint arXiv:2402.17762 (2024)"},{"key":"23_CR17","doi-asserted-by":"publisher","unstructured":"Sutawika, L., et al.: Eleutherai\/lm-evaluation-harness: major refactor (2023). https:\/\/doi.org\/10.5281\/zenodo.10256836, https:\/\/doi.org\/10.5281\/zenodo.10256836","DOI":"10.5281\/zenodo.10256836"},{"key":"23_CR18","unstructured":"Touvron, H., et\u00a0al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"23_CR19","unstructured":"Wang, H., et al.: BitNet: scaling 1-bit transformers for large language models. arXiv preprint arXiv:2310.11453 (2023)"},{"key":"23_CR20","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":"23_CR21","doi-asserted-by":"crossref","unstructured":"Yang, J., Kim, H., Kim, Y.: Mitigating quantization errors due to activation spikes in GLU-based LLMs. arXiv preprint arXiv:2405.14428 (2024)","DOI":"10.3390\/fi17040185"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-7030-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T12:39:33Z","timestamp":1750682373000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-7030-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819670291","9789819670307"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-7030-7_23","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","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":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}