AngelSlim：一个更易获取、全面且高效的大型模型压缩工具包

AngelSlim is a comprehensive and versatile toolkit for large model compression developed by the Tencent Hunyuan team. It consolidates cutting-edge algorithms such as quantization, speculative decoding, token pruning, and distillation, providing a unified pipeline that streamlines the transition from model compression to industrial-scale deployment. To facilitate efficient acceleration, AngelSlim integrates state-of-the-art FP8 and INT8 Post-Training Quantization (PTQ) algorithms alongside pioneering research in ultra-low-bit regimes, featuring HY-1.8B-int2 as the first industrially viable 2-bit large model. Furthermore, a training-aligned speculative decoding framework is proposed, compatible with various model architectures, enhancing the efficiency and practicality of model compression.