pub fn attention_causal_with_scale(
q: &[f32],
k_cache: &[f32],
v_cache: &[f32],
n_heads: usize,
n_kv_heads: usize,
head_dim: usize,
scale: f32,
window: Option<usize>,
) -> Result<Vec<f32>, EngineError>Expand description
Prefill causal attention with an explicit softmax scale.
window is the sliding-window length (None = full causal prefix).