int L2NormHelper::enqueue(int batchSize, const void* const* inputs, void** outputs, void* workspace, cudaStream_t stream)
{
    const void* inputData = inputs[0];
    void* outputData = outputs[0];
    bool status = executeInference(stream, op_type, eps, batchSize, C, H, W, inputData, outputData);
    ASSERT(status == 0);
    return 0;
}