Function moe_hash_route_batched 

pub fn moe_hash_route_batched(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    gate_logits: DevicePtr,
    tid2eid: DevicePtr,
    token_ids: DevicePtr,
    expert_indices: DevicePtr,
    expert_weights: DevicePtr,
    num_experts: u32,
    top_k: u32,
    normalize: bool,
    scaling_factor: f32,
    n: u32,
    stream: u64,
) -> Result<()>

2026-09-25: moe_hash_route for n tokens, one block per token, reading token_ids[n].