transformers/pr_26617/en/quantization/optimum.md

Optimum

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