/*in_flight_nodes_limit=*/in_flight_nodes_limit)),
        op_(nullptr),
        thread_(tensorflow::Env::Default()->StartThread(
            tensorflow::ThreadOptions(), "parallel_device_execute",
            std::bind(&DeviceThread::Run, this))) {}
  ~DeviceThread();

  // Requests that the worker thread execute the specified operation. Blocks

//
// Since this function is used to satisfy the TFE_CustomDevice C API,
// device_info is passed in using a C-style generic. It must always be a
// ParallelDevice.
void ParallelDeviceExecute(const TFE_Op* original_op, int* num_outputs,
                           TFE_TensorHandle** outputs, TF_Status* status,
                           void* device_info) {