{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T08:04:07Z","timestamp":1784189047802,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234165","type":"print"},{"value":"9789819234172","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"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\/978-981-92-3417-2_44","type":"book-chapter","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:10:31Z","timestamp":1784185831000},"page":"518-528","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SDFP: Speculative Decoding with FIT-Pruned Models for Training-Free and Plug-and-Play LLM Acceleration"],"prefix":"10.1007","author":[{"given":"Hanyu","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunhai","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Spandan","family":"Tiwari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashish","family":"Sirasao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhan","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"44_CR1","unstructured":"OpenAI: Gpt-4 technical report. arXiv preprint https:\/\/arxiv.org\/abs\/2303.08774 (2023)."},{"key":"44_CR2","unstructured":"Dubey, A., et al.: The LLaMA 3 herd of models. arXiv preprint https:\/\/arxiv.org\/abs\/2407.21783 (2024)."},{"key":"44_CR3","doi-asserted-by":"publisher","first-page":"3909","DOI":"10.18653\/v1\/2023.findings-emnlp.257","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","author":"H Xia","year":"2023","unstructured":"Xia, H., Ge, T., Wang, P., Chen, S.-Q., Wei, F., Sui, Z.: Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 3909\u20133925 (2023)"},{"key":"44_CR4","first-page":"19274","volume-title":"International Conference on Machine Learning","author":"Y Leviathan","year":"2023","unstructured":"Leviathan, Y., Kalman, M., Matias, Y.: Fast inference from transformers via speculative decoding. In: International Conference on Machine Learning, pp. 19274\u201319286. PMLR (2023)"},{"key":"44_CR5","unstructured":"Cai, T. et al.: Medusa: Simple llm inference acceleration framework with multiple decoding heads. arXiv preprint. https:\/\/arxiv.org\/abs\/2401.10774. (2024)"},{"key":"44_CR6","unstructured":"Li, Y., Wei, F., Zhang, C., Zhang, H.: Eagle: speculative sampling requires rethinking feature uncertainty. arXiv preprint. https:\/\/arxiv.org\/abs\/2401.15077. (2024)"},{"key":"44_CR7","doi-asserted-by":"publisher","first-page":"12622","DOI":"10.18653\/v1\/2024.acl-long.681","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"M Elhoushi","year":"2024","unstructured":"Elhoushi, M., et al.: Layerskip: enabling early exit inference and self-speculative decoding. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12622\u201312642 (2024)"},{"key":"44_CR8","unstructured":"Zhou, Y. et al.: Distillspec: improving speculative decoding via knowledge distillation. arXiv preprint. https:\/\/arxiv.org\/abs\/2310.08461. (2023)"},{"key":"44_CR9","unstructured":"Xia, H., Li, Y., Zhang, J., Du, C., Li, W.: Swift: on-the-fly self-speculative decoding for llm inference acceleration. arXiv preprint. https:\/\/arxiv.org\/abs\/2410.06916. (2024)"},{"key":"44_CR10","unstructured":"Zandonati, B., Pol, A.A., Pierini, M., Sirkin, O., Kopetz, T.: Fit: a metric for model sensitivity. arXiv preprint. https:\/\/arxiv.org\/abs\/2210.08502. (2022)"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Su, Z. et al.: Akvq-vl: attention-aware kv cache adaptive 2-bit quantization for vision-language models. arXiv preprint. https:\/\/arxiv.org\/abs\/2501.15021. (2025)","DOI":"10.1109\/ICME59968.2025.11209367"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Su, Z. et al.: Rotatekv: accurate and robust 2-bit kv cache quantization for llms via outlier-aware adaptive rotations. arXiv preprint. https:\/\/arxiv.org\/abs\/2501.16383. (2025)","DOI":"10.24963\/ijcai.2025\/690"},{"key":"44_CR13","doi-asserted-by":"publisher","first-page":"280","DOI":"10.18653\/v1\/K16-1028","volume-title":"Proceedings of the 20th SIGNLL conference on computational natural language learning","author":"R Nallapati","year":"2016","unstructured":"R. Nallapati, B. Zhou, C. Dos Santos, C Gulc\u00b8 Ehre, and B. Xiang, \u201cAbstractive text summarization using sequence-to-sequence rnns and beyond,\u201d in Proceedings of the 20th SIGNLL conference on computational natural language learning, 2016, pp. 280\u2013290."},{"key":"44_CR14","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. arXiv preprint. https:\/\/arxiv.org\/abs\/2110.14168. (2021)"},{"key":"44_CR15","unstructured":"Eldan, R., Li, Y.: Tinystories: how small can language models be and still speak coherent English? arXiv preprint. https:\/\/arxiv.org\/abs\/2305.07759. (2023)"},{"key":"44_CR16","unstructured":"Santilli, A., et al.: Accelerating transformer inference for translation via parallel decoding. arXiv preprint. https:\/\/arxiv.org\/abs\/2305.10427. (2023)"},{"key":"44_CR17","unstructured":"Fu, Y., Bailis, P., Stoica, I., Zhang, H.: Break the sequential dependency of llm inference using lookahead decoding. arXiv preprint. https:\/\/arxiv.org\/abs\/2402.02057. (2024)"}],"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\/978-981-92-3417-2_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:10:33Z","timestamp":1784185833000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3417-2_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"ISBN":["9789819234165","9789819234172"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3417-2_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"assertion":[{"value":"17 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"}}]}}