CLLMs: Consistency Large Language Models

Parallel decoding methods such as Jacobi decoding show promise for more efficient LLM inference as it breaks the sequential nature of the LLM decoding process and transforms it into parallelizable computation. However, in practice, it achieves little speedup compared to traditional autoregressive (A...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-06
Hauptverfasser:	Kou, Siqi, Hu, Lanxiang, He, Zhezhi, Deng, Zhijie, Zhang, Hao
Format:	Artikel
Sprache:	eng
Schlagworte:	Autoregressive processes Iterative methods Large language models Parallel processing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!