Module quantization 

Model quantization for reduced precision inference

Quantization reduces model size and improves inference speed by converting floating-point weights and activations to lower precision formats.

Structs

QuantizationConfig

Quantization configuration

QuantizationConfigBuilder

Builder for quantization configuration

QuantizationParams

Quantization parameters

QuantizationResult

Result of model quantization

Enums

QuantizationMode

Quantization mode

QuantizationType

Quantization type

Functions

calibrate_quantization

Calibrates quantization parameters using a dataset

dequantize_tensor

Dequantizes a tensor using the provided parameters

quantize_model

Quantizes an ONNX model

quantize_tensor

Quantizes a tensor using the provided parameters