arXiv Machine Learning By Xueying Wu, Baijun Zhou, Zhihui Gao, Yuzhe Fu, Qilin Zheng, Yintao He, Hai Li

OASIS: Outlier-Aware LUT-Based GEMM with Dual-Side Quantization for LLM Inference Acceleration

Read the original on arXiv Machine Learning →

arXiv:2507. 23035v4 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated impressive capabilities across a wide range of applications, but demand substantial memory and compute resources during inference.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
1d ago

CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts

arXiv:2604. 10496v2 Announce Type: replace Abstract: Outliers have emerged as a fundamental bottleneck in preserving accuracy for low-precision large models, particularly within Mixture-of-Experts (MoE) architectures that are increasingly central to large-scale language modeling.

By Xiangyang Yin, Xingyu Liu, Tianhua Xia, Bo Bao, Vithursan Thangarasa, Valavan Manohararajah, Eric Sather, Sai Qian Zhang