Function load_moe_no_shared 

pub fn load_moe_no_shared(
    store: &WeightStore,
    layer_prefix: &str,
    num_experts: usize,
    gpu: &dyn GpuBackend,
    config: &ModelConfig,
    variant: Nvfp4Variant,
) -> Result<MoeWeights>

2026-09-25: Load a MoE block that has no shared expert. A zero-filled shared expert of real expert size stands in: its packed codes, scales and weight_scale_2 are all 0, so it contributes 0. Routed experts go through quantized_auto, which panics for Fp8Dequanted and Bf16Raw.