by JiangyongYu Papers
2 papers found
MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
Zhixuan Chen, Xing Hu, Dawei Yang et al.
ICML 2025poster
8
citations
RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
XUCHEN, Yuxuan Yue, Zukang Xu et al.
ICML 2025poster