Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models

Recent large language models (LLMs) employ billions of parameters to enable broad problem-solving capabilities. Such language models also tend to be memory-bound because of the dominance of matrix-vector and matrix-matrix multiplications with low arithmetic intensity. Therefore, optimizing the memor...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Moar, Chakshu, Tahmasebi, Faraz, Pellauer, Michael, Kwon, Hyoukjun
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!