Enum GraphFfn 

pub enum GraphFfn<'a> {
    Dense {
        gate: GraphW<'a>,
        up: GraphW<'a>,
        down: GraphW<'a>,
    },
    Moe {
        router: GraphW<'a>,
        shared_gate: GraphW<'a>,
        experts: Vec<(usize, usize, usize)>,
        n_exp: usize,
        top_k: usize,
        inter: usize,
        norm_topk: bool,
    },
}

The FFN of one graph layer: a dense SwiGLU trio, or a routed MoE — router + top-k selection + all selected experts run ON DEVICE (the routing decision depends on the resident hidden state, so a CPU round-trip per layer would forfeit the one-submit design).

Variants

Dense

Fields

gate: GraphW<'a>

up: GraphW<'a>

down: GraphW<'a>

Moe

Fields

router: GraphW<'a>

Router logits weight (f32, kind 4) [n_exp, hidden].

shared_gate: GraphW<'a>

Shared-expert sigmoid gate (f32) [1, hidden].

experts: Vec<(usize, usize, usize)>

Per-expert q4_tiled directory indices (gate, up, down); the SHARED expert rides as the LAST entry — the select kernel pins it with the sigmoid weight.

n_exp: usize

Routed experts (shared excluded).

top_k: usize

inter: usize

norm_topk: bool