pub fn attention(
q: &[f32],
k_cache: &[f32],
v_cache: &[f32],
n_heads: usize,
n_kv_heads: usize,
head_dim: usize,
) -> Result<Vec<f32>, EngineError>Expand description
Causal attention for single query step against KV cache. q: [n_heads * head_dim], k_cache/v_cache: [seq, n_kv_heads * head_dim]