Enum AttentionType 

pub enum AttentionType {
    Standard,
    Mla,
}

Attention architecture family.

Variants

Standard

Standard multi-head or grouped-query attention (Qwen3.5, Llama, etc.)

Mla

Multi-head Latent Attention — compressed KV via low-rank projection. (Mistral Small 4, DeepSeek-V2/V3)

Trait Implementations

impl Clone for AttentionType

fn clone(&self) -> AttentionType

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AttentionType

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

Formats the value using the given formatter.

impl PartialEq for AttentionType

fn eq(&self, other: &AttentionType) -> 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 AttentionType

impl Eq for AttentionType

impl StructuralPartialEq for AttentionType