SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization

Runsheng Bai; Bo Liu; Qiang Liu

2025 ICML ICML 2025

SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Runsheng Bai, Bo Liu, Qiang Liu

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Application Areas > Efficient Computing Artificial Intelligence > Core AI > Large Language Models

Keywords

quantization k-means clustering mixed precision perplexity llama scaled

Download PDF