ResDecode: Accelerating Large Language Models Inference via Residual Decoding Heads
Big Data Mining and Analytics · 2025-08 · 8 (4) · 779-793
DOI: 10.26599/bdma.2024.9020074 ↗Kurz gefasst
Fachartikel in der Zeitschrift Big Data Mining and Analytics, 2025-08. Verfasst von Ziqian Zeng und 7 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Zeng, Z., Yu, J., Pang, Q., Wang, Z., Zhuang, H., Yu, F., Shao, H., & Zou, X. (2025). ResDecode: Accelerating Large Language Models Inference via Residual Decoding Heads. Big Data Mining and Analytics, 8(4), 779-793. https://doi.org/10.26599/bdma.2024.9020074
Vancouver
Zeng Z, Yu J, Pang Q, Wang Z, Zhuang H, Yu F, et al. ResDecode: Accelerating Large Language Models Inference via Residual Decoding Heads. Big Data Mining and Analytics. 2025;8(4):779-793. doi:10.26599/bdma.2024.9020074
BibTeX
@article{Zeng2025,
author = {Zeng, Ziqian and Yu, Jiahong and Pang, Qianshi and Wang, Zihao and Zhuang, Huiping and Yu, Fan and Shao, Hongen and Zou, Xiaofeng},
title = {ResDecode: Accelerating Large Language Models Inference via Residual Decoding Heads},
journal = {Big Data Mining and Analytics},
year = {2025},
volume = {8},
number = {4},
pages = {779--793},
doi = {10.26599/bdma.2024.9020074}
}
EUVIMED