std::vector<TFE_TensorHandle*> device_inputs;
    device_inputs.reserve(inputs.size());
    for (int input_index = 0; input_index < inputs.size(); ++input_index) {
      // Parallel tensors are divided between operations by device.
      device_inputs.push_back(inputs[input_index]->tensor(device_index));
    }
    device_thread->StartExecute(
        context, operation_name, std::move(device_inputs), attributes,