liguodongiot--llm-action/llm-compression/quantization/fp4.md

https://github.com/nbasyl/LLM-FP4

LLM-FP4: 4-Bit Floating-Point Quantized Transformers

ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats