Hugging Face's logo

Optimum documentation

Configuration

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Configuration

RyzenAIConfig

class optimum.amd.ryzenai.RyzenAIConfig

< >

( opset: typing.Optional[int] = None quantization: typing.Optional[optimum.amd.ryzenai.configuration.QuantizationConfig] = None **kwargs )

Parameters

  • opset (Optional[int], defaults to None) — ONNX opset version to export the model with.
  • quantization (Optional[QuantizationConfig], defaults to None) — Specify a configuration to quantize ONNX model

RyzenAIConfig is the configuration class handling all the VitisAI parameters related to the ONNX IR model export, and quantization parameters.

< > Update on GitHub

←RyzenAI Inference Pipelines Quantization→