pub fn moe_topk_sigmoid(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
gate_logits: DevicePtr,
bias: DevicePtr,
expert_indices: DevicePtr,
expert_weights: DevicePtr,
num_experts: u32,
top_k: u32,
normalize: bool,
scaling_factor: f32,
stream: u64,
) -> Result<()>