Athena: Efficient Block-Wise Post-Training Quantization for Large
Language Models Using Second-Order Matrix Derivative Information

Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information

24 May 2024

Papers citing "Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information"

Title
No papers