Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression
Jan 1, 2025·,,,,,·
1 min read
Jacob Sander
David Moe
Achraf Cohen
Brent Venable
Venkat Dasari
Brian Jalaian
Abstract
This paper investigates LLM compression techniques for edge deployment, comparing fine-tuning and knowledge distillation approaches for resource-constrained environments.
Type
Publication
arXiv preprint arXiv:2505.18166
Add the full text or supplementary notes for the publication here using Markdown formatting.