Struct QuantizationParams 

pub struct QuantizationParams {
    pub scale: f32,
    pub zero_point: i32,
}

Parameters describing how floating-point values were quantized to integers.

Supports both per-tensor (single scale/zero_point) and per-channel quantization (vectors of scales/zero_points).

Fields

scale: f32

zero_point: i32

Implementations

impl QuantizationParams

pub fn from_range(min: f32, max: f32) -> Self

Compute quantization parameters from observed min/max values.

Uses asymmetric affine quantization: scale = (max - min) / 255 zero_point = round(-min / scale)

Trait Implementations

impl Clone for QuantizationParams

fn clone(&self) -> QuantizationParams

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for QuantizationParams

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.