pub fn moe_sort_by_expert(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
topk_ids: DevicePtr,
sorted_token_ids: DevicePtr,
sorted_expert_ids: DevicePtr,
expert_offsets: DevicePtr,
token_to_perm: DevicePtr,
total_expanded: u32,
num_experts: u32,
topk: u32,
stream: u64,
) -> Result<()>