Enum AccuracyTarget 

pub enum AccuracyTarget {
    Maximum,
    High,
    Balanced,
    Compact,
}

Target accuracy levels for adaptive quantization

Variants

Maximum

Maximum accuracy (~99.9%), uses FP16 (2x compression)

High

High accuracy (~99%), uses QInt8 (4x compression)

Balanced

Balanced accuracy (~95-97%), uses QInt4 (8x compression)

Compact

Compact storage (~85-90%), uses Binary (32x compression)

Trait Implementations

impl Clone for AccuracyTarget

fn clone(&self) -> AccuracyTarget

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AccuracyTarget

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

Formats the value using the given formatter.

impl PartialEq for AccuracyTarget

fn eq(&self, other: &AccuracyTarget) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Copy for AccuracyTarget

impl Eq for AccuracyTarget

impl StructuralPartialEq for AccuracyTarget