Struct QuantizationParams 

pub struct QuantizationParams {
    pub scale: f32,
    pub zero_point: i8,
    pub min_val: f32,
    pub max_val: f32,
}

Unstable: INT8 quantization parameters; scale/bias scheme may change.

Quantization parameters for int8 conversion.

Fields

scale: f32

Unstable: scale factor; formula may change with scheme update.

zero_point: i8

Unstable: zero point offset; may be removed for symmetric-only quantization.

min_val: f32

Unstable: min float value; may be removed.

max_val: f32

Unstable: max float value; may be removed.

Implementations

impl QuantizationParams

pub fn from_vector(vector: &[f32]) -> Self

Unstable: parameter computation; may be folded into QuantizedVector::from_f32.

Handles edge cases: empty vectors, NaN, Inf, near-zero vectors.

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.

impl Copy for QuantizationParams