Function moe_weighted_sum_blend_batch3 

pub fn moe_weighted_sum_blend_batch3(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    output: DevicePtr,
    expert_out: DevicePtr,
    expert_weights: DevicePtr,
    shared_out: DevicePtr,
    input: DevicePtr,
    gate_weight: DevicePtr,
    hidden: u32,
    top_k: u32,
    k: u32,
    stream: u64,
) -> Result<()>

Fused weighted sum + sigmoid blend for K=3 tokens.

Grid: (ceil(hidden/256), 3, 1) Block: (256, 1, 1)