{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:19:36Z","timestamp":1757456376297,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794362"},{"type":"electronic","value":"9789819794379"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-9437-9_13","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:27:22Z","timestamp":1730392042000},"page":"158-169","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["FIRP: Faster LLM Inference via\u00a0Future Intermediate Representation Prediction"],"prefix":"10.1007","author":[{"given":"Pengfei","family":"Wu","sequence":"first","affiliation":[]},{"given":"Jiahao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhuocheng","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Qifan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jinpeng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jingang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xunliang","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Dongyan","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"13_CR1","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models (2023)"},{"key":"13_CR2","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models (2023)"},{"key":"13_CR3","unstructured":"Roziere, B., et\u00a0al.: Code llama: open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)"},{"key":"13_CR4","unstructured":"Shazeer, N.: Fast transformer decoding: one write-head is all you need. arXiv preprint arXiv:1911.02150 (2019)"},{"key":"13_CR5","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":"13_CR6","unstructured":"Chen, C., Borgeaud, S., Irving, G., Lespiau, J.B., Sifre, L., Jumper, J.: Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318 (2023)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Draft & verify: lossless large language model acceleration via self-speculative decoding. arXiv preprint arXiv:2309.08168 (2023)","DOI":"10.18653\/v1\/2024.acl-long.607"},{"key":"13_CR8","unstructured":"Cai, T., Li, Y., Geng, Z., Peng, H., Dao, T.: Medusa: simple framework for accelerating llm generation with multiple decoding heads (2023). https:\/\/github.com\/FasterDecoding\/Medusa"},{"key":"13_CR9","unstructured":"Miao, X., et al.: Specinfer: accelerating generative llm serving with speculative inference and token tree verification. arXiv preprint arXiv:2305.09781 (2023)"},{"key":"13_CR10","unstructured":"Spector, B., Re, C.: Accelerating llm inference with staged speculative decoding. arXiv preprint arXiv:2308.04623 (2023)"},{"key":"13_CR11","unstructured":"Fu, Y., Bailis, P., Stoica, I., Zhang, H.: Break the sequential dependency of llm inference using lookahead decoding (2024)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, Q., Wang, J., Cai, X.: Speculative decoding via early-exiting for faster llm inference with thompson sampling control mechanism. ArXiv arxiv:2406.03853 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.179"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Gong, Z., et al.: Graph-structured speculative decoding (2024)","DOI":"10.18653\/v1\/2024.findings-acl.677"},{"key":"13_CR14","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing gpt-4 with 90%* chatgpt quality (2023)"},{"key":"13_CR15","unstructured":"Wolf, T., et\u00a0al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)"},{"key":"13_CR16","unstructured":"Lhoest, Q., et\u00a0al.: Datasets: a community library for natural language processing. arXiv preprint arXiv:2109.02846 (2021)"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cohen, S.B., Lapata, M.: Don\u2019t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization. arXiv preprint arXiv:1808.08745 (2018)","DOI":"10.18653\/v1\/D18-1206"},{"key":"13_CR18","unstructured":"Cobbe, K., et\u00a0al.: Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9437-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:29:19Z","timestamp":1730392159000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9437-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794362","9789819794379"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9437-9_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}