pub fn build_moe(
gpu: &dyn GpuBackend,
cfg: &Glm5NextMlpConfig,
tp_rank: usize,
full_shared_inter: usize,
load: LoadFn<'_>,
expert: ExpertFn<'_>,
) -> Result<Glm5NextMoeWeights>Expand description
Bind one routed MoE site for this rank: replicated router, TP-sharded shared expert, and
exactly the local_experts routed experts this EP rank owns.