Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization
关注自身思维:通过1.58比特量化视角打破推理型大语言模型的后训练量化障碍
机构 * Intel Labs China(英特尔中国实验室)
AI总结 该研究提出ScaleQ-1.58三值后训练量化框架,通过集成AYOT校准方法,提升推理型LLM量化性能,该框架可扩展且泛化性强,仅需少量校准token即可实现优异效果。
Comments This research work was completed and submitted for publication in early May 2026. The project page: https://github.com/IntelChina-AI/BitTern