Mixed-Precision Quantization for Language Models: Techniques and Prospects
"混合精度量化" 相关文章
MC#: Mixture Compressor for Mixture-of-Experts Large Models
CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models
MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models
扩散模型低位量化突破！有效扩散量化的极限推向2-4位，W2A4位宽下FID降低58%，超越SOTA方法
扩散模型低位量化突破！有效扩散量化的极限推向2-4位，W2A4位宽下FID降低58%，超越SOTA方法
