ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers
Yuxiong He, Conglong Li, Xiaoxia Wu, Zhewei Yao, Conglong Li, Yuxiong He
Topics & Concepts
Computer scienceTransformerQuantization (signal processing)Electronic engineeringControl theory (sociology)EngineeringElectrical engineeringAlgorithmMathematicsSignal processingAdvanced Neural Network ApplicationsAdvanced Memory and Neural ComputingParallel Computing and Optimization Techniques