Awesome Model Quantization ------模型量化综述(Model Quantization)
Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization基于共享权重的异构组注意力专家混合模型用于动态逐令牌键值优化
https://aclanthology.org/2025.emnlp-main.1166.pdf
HMoE: Heterogeneous Mixture of Experts for Language Modeling用于语言建模的异构专家混合模型
HMoE: Heterogeneous Mixture of Experts for Language Modeling - ACL Anthology
