fairy2i-complex-llm-quantization

【效率与协作】Enable extreme 1-2bit quantization of pre-trained LLMs by leveraging complex-valued arithmetic. Convert real-valued linear layers to complex domain losslessly, quantize to fourth roots of unity {±1, ±i}, and apply recursive residual error quantization for near full-precision performance.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准