Numerical Error Analysis of Large Language Models

MaRDI QIDQ7170085arXivFDO

Authors Stanislav S. Budzinskiy, Wenyi Fang, Longbin Zeng, Philipp Petersen

Publication date 2025

Published in arXiv

arXiv classification

math.NA

Cited in

(2)

• Automated Numerical Stability Analysis of Deep Learning Operators
• LampAttention: Look-Ahead Mixed-Precision FlashAttention for Dedicated Accelerators

This page was built for publication: Numerical Error Analysis of Large Language Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7170085)