Mingrun Wei

MPPQ: Enhancing Post-Training Quantization for LLMs via Mixed Supervision, Proxy Rounding, and Pre-Searching

Recently, post-training quantization (PTQ) methods for large language models (LLMs) primarily focus on tackling the challenges caused by outliers. Scaling transformation has proven to be effective while how to enhance the performance of extremely low-bitwidth (e.g., 2-bit) PTQ under it remains large