MACaQ achieves SOTA model-agnostic quantization for GGUF, enabling local inference and beyond for text, image, video, and audio models with llama.cpp, vLLM, Diffusers, and PyTorch

Original headline: "huawei-csl/MACaQ: SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run text, image, video and audio models with llama.cpp, vLLM, Diffusers and PyTorch."