load_moe_skip_experts

metrale_model_layers::weight_map::loaders_fp8

Function load_moe_skip_experts 

Source 
pub fn load_moe_skip_experts(
    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_moe with every routed expert left as ExpertWeight::null(). The native-FP8 qwen3 loader uses it and loads the routed experts separately.