VLOG(1) << "Running the dequeue op";
  TF_Output output{dequeue_op, 0};
  TF_Tensor* ret;
  TF_SessionRun(session, /*run_options*/ nullptr,
                // input related parameters
                /*inputs*/ nullptr, /*input_values*/ nullptr, /*ninputs*/ 0,
                // output related parameters
                /*outputs*/ &output, /*output_values*/ &ret,
                /*noutputs*/ 1,

  }
  ResetOutputValues();
  output_values_.resize(outputs_.size(), nullptr);

  const TF_Output* inputs_ptr = inputs_.empty() ? nullptr : &inputs_[0];
  TF_Tensor* const* input_values_ptr =
      input_values_.empty() ? nullptr : &input_values_[0];

  const TF_Output* outputs_ptr = outputs_.empty() ? nullptr : &outputs_[0];
  TF_Tensor** output_values_ptr =
      output_values_.empty() ? nullptr : &output_values_[0];

        absl::StrCat("ZerosLike", ToId(t)).c_str()));
  }
  TF_RETURN_IF_ERROR(op->AddInput(t));
  int num_outputs = 1;
  std::vector<AbstractTensorHandle*> outputs(num_outputs);
  TF_RETURN_IF_ERROR(
      op->Execute(absl::Span<AbstractTensorHandle*>(outputs), &num_outputs));
  *result = outputs[0];
  return absl::OkStatus();
}
}  // namespace

Status GradientRegistry::Register(

                               /*expected_max_outputs=*/1,
                               cancellation_manager);
  auto outputs = parallel_device.Join(
      /*expected_output_shapes=*/{PartialTensorShape({})}, status.get());
  ASSERT_TRUE(TF_GetCode(status.get()) == TF_OK) << TF_Message(status.get());
  const std::vector<std::unique_ptr<ParallelTensor>>& handles = *outputs;
  const std::vector<int64_t>* shape;

    for (int i = 0; i < noutputs; ++i) {
      output_names_vec.push_back(string(output_names[i]));
    }
  }

  // Process control output names.
  std::vector<string> control_output_names_vec;
  if (control_output_names) {
    control_output_names_vec.reserve(ncontrol_outputs);
    for (int i = 0; i < ncontrol_outputs; ++i) {
      control_output_names_vec.push_back(string(control_output_names[i]));
    }
  }

                absl::Span<AbstractTensorHandle*> outputs) {
  return ops::AddV2(ctx, inputs[0], inputs[1], &outputs[0], "Add");
}

Status ExpModel(AbstractContext* ctx,
                absl::Span<AbstractTensorHandle* const> inputs,
                absl::Span<AbstractTensorHandle*> outputs) {
  return ops::Exp(ctx, inputs[0], &outputs[0], "Exp");
}

Status SqrtModel(AbstractContext* ctx,

    // Extract the resulting tensor.
    add_output2 = TF_OutputListGet(add_outputs, 0);
    TF_DeleteOutputList(add_outputs);
  }

  // 3rd Output will be Matrix Multiplication of add_output1 and add_output2
  TF_AbstractTensor* mm_output;
  {
    // Build an abstract operation, inputs and output.
    auto* mm_op = TF_NewAbstractOp(graph_ctx);
    TF_AbstractOpSetOpType(mm_op, "MatMul", s);

ParallelDevice::Join(
    const std::vector<PartialTensorShape>& expected_output_shapes,
    TF_Status* status) const {
  absl::optional<std::vector<std::unique_ptr<ParallelTensor>>> result;
  // Compute per-device per-output tensors
  std::vector<std::vector<TensorHandlePtr>> per_device_output_tensors;
  per_device_output_tensors.reserve(underlying_devices_.size());
  int first_op_output_count = 0;
  StatusPtr first_bad_status(nullptr);

                                    vector<AbstractTensorHandle*> f_outputs)
      : forward_inputs_(f_inputs), forward_outputs_(f_outputs) {
    for (auto input : forward_inputs_) {
      if (input) {
        input->Ref();
      }
    }
    for (auto output : forward_outputs_) {
      if (output) {
        output->Ref();
      }
    }
  }

  Status Compute(AbstractContext* ctx,

    }
    inputs_.push_back(t->output_);
    *output = tensorflow::down_cast<TracingTensorHandle*>(outputs[0]);
    return absl::OkStatus();
  }

  Status Finalize(OutputList* outputs, AbstractFunction** f) override {
    std::vector<TF_Output> graph_outputs;
    graph_outputs.reserve(outputs->outputs.size());
    for (auto* abstract_output : outputs->outputs) {