transformers/pr_40546/en/quantization/optimum.md

Optimum

Optimum is an optimization library that supports quantization for Intel, Furiosa, ONNX Runtime, GPTQ, and lower-level PyTorch quantization functions. It is designed to enhance performance for specific hardware - Intel CPUs/HPUs, AMD GPUs, Furiosa NPUs, etc. - and model accelerators like ONNX Runtime.