Module burn::tensor::quantization

Tensor quantization module.

Structs

• AffineQuantization
  Affine quantization scheme.
• CalibrationRange
  The observed input calibration range.
• MinMaxCalibration
  Computes the per-tensor quantization range mapping based on the min and max values.
• QuantizationParameters
  The quantization parameters.
• QuantizationParametersPrimitive
  The quantization parameters primitive.
• SymmetricQuantization
  Symmetric quantization scheme.

Enums

• QuantizationScheme
  Quantization scheme.
• QuantizationStrategy
  Quantization strategy.
• QuantizationType
  Quantization data type.

Traits

• Calibration
  Calibration method used to compute the quantization range mapping.
• QTensorPrimitive
  Quantized tensor primitive.
• Quantization
  Quantization scheme to convert elements of a higher precision data type E to a lower precision data type Q and vice-versa.