Struct ExpertQuantization 

pub struct ExpertQuantization {
    pub bits: usize,
    pub block_size: usize,
    pub blocks_per_row: usize,
}

Quantization geometry needed to interpret one expert’s packed tensor slice.

Fields

bits: usize

Number of quantized weight bits per logical value.

block_size: usize

Number of logical input values sharing one scale/zero-point block.

blocks_per_row: usize

Number of quantization blocks represented by each tensor row.

Trait Implementations

impl Clone for ExpertQuantization

fn clone(&self) -> ExpertQuantization

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for ExpertQuantization

impl Debug for ExpertQuantization

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

Formats the value using the given formatter.

impl Eq for ExpertQuantization

impl PartialEq for ExpertQuantization

fn eq(&self, other: &ExpertQuantization) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for ExpertQuantization