2 papers
cs.LG2026
SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models
Xin Nie, Haicheng Zhang, Liang Dong +3
Mixed-precision quantization is a promising approach for compressing large language models under tight memory budgets. However, existing mixed-precision methods typically suffer fr…
cs.LG2026
ELUTQ: Optimizing Quantization Accuracy under LUT-Based Computation for Edge LLMs
Xin Nie, Liang Dong, Haicheng Zhang +2
Weight quantization effectively reduces memory consumption and enable the deployment of Large Language Models on edge devices, yet existing hardware-friendly methods often rely on…