moe_topk_sigmoid

Function moe_topk_sigmoid 

Source
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<()>
Expand description

2026-09-25: Sigmoid router, one token. The bias is added to the scores for selection only; the weights come from the pre-bias sigmoid scores. top_k and num_experts are bounded by MOE_TOPK_SIGMOID_MAX_TOP_K and MOE_TOPK_SIGMOID_MAX_EXPERTS.