Struct QuantizedWeights 

pub struct QuantizedWeights { /* private fields */ }

Quantized weight storage for reduced memory usage.

Stores neural network weights in a compressed format to reduce memory footprint while maintaining accuracy.

Implementations

impl QuantizedWeights

pub fn from_f32( data: &[f32], rows: usize, cols: usize, bits: u8, group_size: usize, ) -> Result<Self>

Create new quantized weights from f32 data.

pub fn to_f32(&self) -> Vec<f32>

Dequantize to f32.

pub fn shape(&self) -> (usize, usize)

Get shape.

pub fn memory_size(&self) -> usize

Get memory size in bytes.

Trait Implementations

impl Clone for QuantizedWeights

fn clone(&self) -> QuantizedWeights

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizedWeights

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for QuantizedWeights

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for QuantizedWeights

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

where __S: Serializer,

Serialize this value into the given Serde serializer.