pub fn forward_batch_graph(
_model: &Arc<CmfModel>,
_kv_id: u64,
_layers: &[GraphLayer<'_>],
_invf: &[f32],
_h: &mut [f32],
_nh: usize,
_nkv: usize,
_hd: usize,
_rd: usize,
_hidden: usize,
_inter: usize,
_positions: &[usize],
_cap: usize,
_gemma: bool,
_eps: f32,
_k: usize,
) -> boolExpand description
Batched prefill: k contiguous positions through the whole graph in one submit
(projections/FFN as GEMMs, attention/GDN looped over scratch). h is
[k·hidden] in/out; positions len k. wgpu only.