Enum AttentionKind 

pub enum AttentionKind {
    Gqa,
    KimiHybrid(KimiHybridAttention),
}

Which attention mechanism a model uses. Gqa (grouped-query attention + RoPE, uniform across every layer) is the only variant ferrox-core/ferrox-models::decoder actually implement today – it’s what every preset runs through, including the two whose real published attention differs (DeepSeek V4 Pro’s CSA/HCA, Kimi K3’s hybrid KDA/Gated-MLA). KimiHybrid exists so Kimi K3’s real, cited attention hyperparameters are captured accurately rather than silently discarded, even though Decoder itself still runs the GQA path for every layer (the dedicated Kimi decoder is the one consumer of the hybrid variant today).

Variants

Gqa

KimiHybrid(KimiHybridAttention)

Trait Implementations

impl Clone for AttentionKind

fn clone(&self) -> AttentionKind

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AttentionKind

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

Formats the value using the given formatter.