Open sjquan opened 1 year ago
추가 ref. (Yao, 2022) ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers, Neurips 2022. (Dettmer, 2022) LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale, Neurips 2022.
When
Who :
What
Keywords:
Preliminaries:
발표자료