Struct CalibrationConfig 

pub struct CalibrationConfig {
    pub method: CalibrationMethod,
    pub num_bins: usize,
    pub percentile: f32,
    pub windowsize: usize,
    pub per_channel: bool,
    pub symmetric: bool,
    pub ema_factor: f32,
    pub max_iterations: usize,
    pub convergence_threshold: f32,
}

Configuration for quantization calibration

Fields

method: CalibrationMethod

Method used for calibration

num_bins: usize

Number of histogram bins for entropy-based methods

percentile: f32

Percentile value for percentile-based methods (0.0 to 1.0)

windowsize: usize

Moving average window size for min-max methods

per_channel: bool

Whether to use per-channel calibration

symmetric: bool

Whether to use symmetric quantization

ema_factor: f32

Smoothing factor for exponential moving average (0.0 to 1.0) Higher values give more weight to recent observations

max_iterations: usize

Number of calibration iterations for dynamic methods

convergence_threshold: f32

Convergence threshold for iterative calibration methods

Trait Implementations

impl Clone for CalibrationConfig

fn clone(&self) -> CalibrationConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CalibrationConfig

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

Formats the value using the given formatter.

impl Default for CalibrationConfig

fn default() -> Self

Returns the “default value” for a type.