{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:02:01Z","timestamp":1780639321750,"version":"3.54.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539704","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Boosting the Performance of Tree-Based Speculative Decoding of LLMs on FPGAs"],"prefix":"10.23919","author":[{"given":"Tielong","family":"Liu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,C2DL, Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,C2DL, Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zitao","family":"Mo","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,C2DL, Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,C2DL, Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minnan","family":"Pei","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,C2DL, Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Cheng","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,C2DL, Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Fast Inference from Transformers via Speculative Decoding","author":"Leviathan","year":"2022"},{"key":"ref2","article-title":"Accelerating Large Language Model Decoding with Speculative Sampling","author":"Chen","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref4","article-title":"LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification","volume-title":"International Conference on Machine Learning (ICML)","author":"Yang"},{"key":"ref5","article-title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","author":"Li","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"ref7","article-title":"MEDUSA: Simple LLMInference Acceleration Framework with Multiple Decoding Heads","volume-title":"International Conference on Machine Learning (ICML)","author":"Cai"},{"key":"ref8","article-title":"EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty","volume-title":"International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.422"},{"key":"ref10","article-title":"MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding","volume-title":"International Conference on Learning Representations (ICLR)","author":"Sadhukhan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref12","article-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref13","article-title":"How Long Can Open-Source LLMs Truly Promise on Context Length?","author":"Li","year":"2023"},{"key":"ref14","article-title":"The Llama 3 Herd of Models","author":"Grattafiori","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.112"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.472"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1102"},{"key":"ref18","article-title":"Longcoder: A long-range pre-trained language model for code completion","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Guo"},{"key":"ref19","article-title":"RepoBench: Benchmarking repository-level code auto-completion systems","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Liu"}],"event":{"name":"2026 Design, Automation & Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539704.pdf?arnumber=11539704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:14:46Z","timestamp":1780636486000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539704\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":19,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539704","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}