Enum QuantizationBits

pub enum QuantizationBits {
    Int8,
    Int16,
    Int4,
    Mixed {
        weight_bits: u8,
        activation_bits: u8,
    },
}

Quantization precision levels

Variants

Int8

8-bit quantization

Int16

16-bit quantization

Int4

4-bit quantization (experimental)

Mixed

Mixed precision

Fields

weight_bits: u8

Number of bits for weight quantization

activation_bits: u8

Number of bits for activation quantization

Trait Implementations

impl Clone for QuantizationBits

fn clone(&self) -> QuantizationBits

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizationBits

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

Formats the value using the given formatter.

impl PartialEq for QuantizationBits

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

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

const 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 QuantizationBits

impl StructuralPartialEq for QuantizationBits