PISA: Efficient Precision-Slice Framework for LLMs with Adaptive Numerical Type

Large language models (LLMs) have transformed numerous AI applications, with on-device deployment becoming increasingly important for reducing cloud computing costs and protecting user privacy. However, the astronomical model size and limited hardware resources pose significant deployment challenges...

Full description

Bibliographic Details

Published in:	2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 7
Main Authors:	Yang, Ning, Wang, Zongwu, Sun, Qingxiao, Lu, Liqiang, Liu, Fangxin
Format:	Conference Proceeding
Language:	English
Published:	IEEE 22.06.2025
Subjects:	Accuracy Adaptation models Computational efficiency Computational modeling Logic Numerical models Performance gain Privacy Quantization (signal) Systolic arrays
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!