ITQ3_S: High-Fidelity 3-bit LLM Inference via Interleaved Ternary Quantization with Rotation-Domain Smoothing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Yoon, Edward J.
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing 68T50, 65T50, 94A29 I.2.7; C.1.4; B.3.2
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.27914