Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
ProQuant: Preserving Expert Quality over Quantity in Ultra-Low-Bit Quantization of Mixture-of-Experts Models
Jiaqi Chen, Xianglong Yan, Chengzhu Bao +2
Mixture-of-Experts (MoE) large language models reduce computation through sparse activation but still incur substantial storage costs. Mixed-precision post-training quantization (P…
cs.AI2026
FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling
Xianglong Yan, Hong Liu, Chengzhu Bao +4
Large language models (LLMs) achieve remarkable performance but are expensive to deploy due to their enormous size. FP4 quantization, with formats such as MXFP4 and NVFP4, offers a…