Realm

oa::ml::matrix::QuantMatrix

A GPU-resident weight stored in OA’s native Q4 or Q8 block encoding. Constructed by quantize; the packed payload and scale planes are private implementation detail and never exposed as public matrix values.

StRust public API

Declaration

pub struct QuantMatrix { /* private fields */ }
Public Rust declaration.

Public Methods

pub fn shape(&self) -> &[usize]
pub fn num_elements(&self) -> usize
pub const fn quantization(&self) -> Quantization
fn clone(&self) -> QuantMatrix

Public Method Documentation

pub fn shape( &self ) -> &[usize]
No public source comment is attached to this declaration.
pub fn num_elements( &self ) -> usize
No public source comment is attached to this declaration.
pub const fn quantization( &self ) -> Quantization
No public source comment is attached to this declaration.
fn clone( &self ) -> QuantMatrix
No public source comment is attached to this declaration.