Language Modeling on a SpiNNaker 2 Neuromorphic Chip

As large language models continue to scale in size rapidly, so too does the computational power required to run them. Event-based networks on neuromorphic devices offer a potential way to reduce energy consumption for inference significantly. However, to date, most event-based networks that can run...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-01
Hauptverfasser:	Khaleelulla Khan Nazeer, Schöne, Mark, Mukherji, Rishav, Vogginger, Bernhard, Mayr, Christian, Kappel, David, Subramoney, Anand
Format:	Artikel
Sprache:	eng
Schlagworte:	Energy consumption Gesture recognition Hardware Inference Language Large language models Modelling Neural networks Neuromorphic computing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!