Enum QuantizationPrecision 

pub enum QuantizationPrecision {
    FP32,
    FP16,
    INT8,
    Mixed,
}

Quantization precision level

Variants

FP32

Full precision (FP32) - no quantization

FP16

Half precision (FP16) - good for GPU

INT8

8-bit integer (INT8) - good for CPU

Mixed

Mixed precision (automatic selection)

Implementations

impl QuantizationPrecision

pub fn size_reduction_factor(&self) -> f32

Get the size reduction factor compared to FP32

pub fn speedup_factor(&self) -> f32

Get the expected speedup factor compared to FP32

pub fn accuracy_loss(&self) -> f32

Get the typical accuracy loss percentage

pub fn is_gpu_suitable(&self) -> bool

Check if this precision is suitable for GPU

pub fn is_cpu_suitable(&self) -> bool

Check if this precision is suitable for CPU

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 Default for QuantizationPrecision

fn default() -> QuantizationPrecision

Returns the “default value” for a type.

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 Display for QuantizationPrecision

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

Formats the value using the given formatter.

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