Struct QuantizedMatmulParams 

pub struct QuantizedMatmulParams {
    pub m: u32,
    pub k: u32,
    pub n: u32,
    pub group_size: u32,
    pub bits: u32,
}

Parameters describing the quantized matmul dimensions and format.

Fields

m: u32

Number of input rows (tokens).

k: u32

Inner dimension (shared between input and weight).

n: u32

Number of output columns.

group_size: u32

Number of consecutive values sharing one scale/bias pair.

bits: u32

Quantization bit width (4, 6, or 8).

Trait Implementations

impl Clone for QuantizedMatmulParams

fn clone(&self) -> QuantizedMatmulParams

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantizedMatmulParams

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

Formats the value using the given formatter.

impl Copy for QuantizedMatmulParams