pub fn launch_dense_mlp(
layer: &K3BoundLayer,
gpu: &dyn GpuBackend,
x: &[f32],
hidden: usize,
inter: usize,
beta: f32,
linear_beta: f32,
stream: u64,
) -> Result<Vec<f32>>Expand description
2026-09-25: Finds the layer’s resident gate/up/down weights (under
.mlp. for a dense layer, .block_sparse_moe.shared_experts. for a
LatentMoE layer), checks each holds hidden * inter values, and runs
launch_dense_matrices.