Function moe_topk_softmax_bias_batched 

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

Batched twin: one block per token.