Enum QuantizationPrecision 

pub enum QuantizationPrecision {
    Int4,
    Int8,
    Int16,
    Float16,
    Mixed,
}

Quantization precision levels

Variants

Int4

4-bit integer (extreme compression)

Int8

8-bit integer (standard quantization)

Int16

16-bit integer

Float16

16-bit floating point (half precision)

Mixed

Mixed precision (different precisions for different layers)

Implementations

impl QuantizationPrecision

pub fn bits_per_param(&self) -> u8

Get the bits per parameter for this precision

pub fn memory_reduction_ratio(&self) -> f32

Get memory reduction ratio compared to FP32

Trait Implementations

impl Clone for QuantizationPrecision

fn clone(&self) -> QuantizationPrecision

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizationPrecision

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for QuantizationPrecision

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Hash for QuantizationPrecision

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for QuantizationPrecision

fn eq(&self, other: &QuantizationPrecision) -> 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 Serialize for QuantizationPrecision

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for QuantizationPrecision

impl Eq for QuantizationPrecision

impl StructuralPartialEq for QuantizationPrecision