Struct AttentionNumerics 

pub struct AttentionNumerics {
    pub queries: Taken,
    pub keys_values: Taken,
    pub weights: Taken,
}

How an attention a chip computes on narrower units than its values takes its operands: its queries, its keys and values, and its weights — each weight times its value row’s scale where the values are quantized.

Fields

queries: Taken

keys_values: Taken

weights: Taken

Trait Implementations

impl Clone for AttentionNumerics

fn clone(&self) -> AttentionNumerics

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AttentionNumerics

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

Formats the value using the given formatter.

impl PartialEq for AttentionNumerics

fn eq(&self, other: &AttentionNumerics) -> 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 Copy for AttentionNumerics

impl StructuralPartialEq for AttentionNumerics