pub fn load_moe(
store: &WeightStore,
layer_prefix: &str,
num_experts: usize,
gpu: &dyn GpuBackend,
config: &ModelConfig,
variant: Nvfp4Variant,
qctx: QuantizeCtx,
) -> Result<MoeWeights>Expand description
2026-09-25: Load the {layer_prefix}.mlp MoE weights of a layer.
Only experts for which config.is_local_expert(e) holds are loaded; the
others are ExpertWeight::null().