pub fn build_dense_mlp(
gpu: &dyn GpuBackend,
cfg: &Glm5NextMlpConfig,
tp_rank: usize,
full_inter: usize,
prefix: &str,
load: LoadFn<'_>,
) -> Result<Glm5NextDenseMlpWeights>Expand description
2026-09-25: TP-slice and upload one BF16 SwiGLU MLP, a dense layer or a routed layer’s
shared expert. full_inter is the unsliced width; the rank keeps full_inter / tp. Errors
when full_inter does not divide over TP or a tensor has the wrong element count.