Module quantization 

Tensor quantization module.

Structs

BlockSize

Copyable block size, specialized version of SmallVec.

CalibrationRange

The observed input calibration range.

QParamTensor

A quantization parameter tensor descriptor.

QParams

The quantization tensor data parameters.

QuantScheme

Describes a quantization scheme/configuration.

QuantizationParametersPrimitive

The quantization parameters primitive.

QuantizedBytes

Quantized data bytes representation.

Enums

Calibration

Calibration method used to compute the quantization range mapping.

QuantLevel

Level or granularity of quantization.

QuantMode

Strategy used to quantize values.

QuantParam

Quantization floating-point precision.

QuantPropagation

Specify if the output of an operation is quantized using the scheme of the input or returned unquantized.

QuantStore

Data type used to stored quantized values.

QuantValue

Data type used to represent quantized values.

Constants

QPARAM_ALIGN

Alignment (in bytes) for quantization parameters in serialized tensor data.

Traits

QTensorPrimitive

Quantized tensor primitive.

Functions

compute_q_params

Compute the quantization parameters.

compute_range

Compute the quantization range mapping.

params_shape

Calculate the shape of the quantization parameters for a given tensor and level

Type Aliases

QuantizationParameters

The tensor quantization parameters.