TFE_Executor* executor = TFE_ContextGetExecutorForThread(ctx);
  TFE_ExecutorWaitForAllPendingNodes(executor, status);
  ASSERT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);

  // TODO(b/136478427): Figure out how to correctly shut the server down.
  worker_server.release();

  // Update the server def with a new set of names (worker instead of
  // localhost).

  ASSERT_EQ(errors::OK, status_.code()) << status_.message();

  ASSERT_NO_FATAL_FAILURE(CompareNumericalAndAutodiffGradients(
      ExpModel, BuildGradModel(ExpModel, registry_),
      immediate_execution_ctx_.get(), {x.get()}, UseFunction()));
}

TEST_P(CppGradients, TestMatMulGrad) {
  // TODO(vnvo2409): Figure out why `gradient_checker` does not work very
  // well with `MatMul` and remove `TestMatMul*` in

          "Operation '", op.node.DebugString(), "' was changed by ",
          mutation_type,
          " after it was run by a session. This mutation will have no effect, "
          "and will trigger an error in the future. Either don't modify "
          "nodes after running them or create a new session.");
    }
  }
}

namespace {

// Helper method that creates a shape handle for a shape described by dims.

  TFE_DeleteExecutor(executor);
  TFE_ContextRemoveFunction(ctx, "AddVariablesFunction", status);
  TFE_DeleteContext(ctx);

  TF_DeleteStatus(status);

  // TODO(b/136478427): Figure out how to correctly shut the server down.
  worker_server1.release();
  worker_server2.release();
}

TEST(CAPI, TestLocalFunctionWithPackedInput) {
  TestFunctionWithPackedInput(/*remote=*/false);
}

  EXPECT_NE(TF_GetCode(status.get()), TF_CANCELLED);
  EXPECT_EQ(TF_GetCode(status.get()), TF_INVALID_ARGUMENT);
  EXPECT_THAT(TF_Message(status.get()), HasSubstr("assertion failed"));

  // Note that future collectives with the same context do not work at the
  // moment; once canceled, the collective executor requires the program to be
  // restarted / context to be reset.
}

        !DeviceNameUtils::IsSameAddressSpace(
            underlying_devices_[component_index], underlying_devices_[0])) {
      // Device names are from different address spaces, or we can't figure out
      // whether they are, so we'll fully-qualify everything.
      return underlying_devices_;
    }
  }
  std::vector<std::string> local_names;
  local_names.reserve(underlying_devices_.size());

               {x1.get(), x2.get()}, absl::MakeSpan(outputs), UseFunction());
  ASSERT_EQ(errors::OK, status_.code()) << status_.message();
  EXPECT_EQ(outputs[0], nullptr);
  ASSERT_NO_FATAL_FAILURE(CheckTensorValue(outputs[1], {1.0f}, /*dims*/ {},
                                           /*abs_error*/ 0));
  outputs[1]->Unref();
}

#ifdef PLATFORM_GOOGLE
INSTANTIATE_TEST_SUITE_P(

  targets_.clear();
  for (TF_Operation* t : targets) {
    targets_.emplace_back(t);
  }
}

void CSession::Run(TF_Status* s) {
  if (inputs_.size() != input_values_.size()) {
    ADD_FAILURE() << "Call SetInputs() before Run()";
    return;
  }
  ResetOutputValues();
  output_values_.resize(outputs_.size(), nullptr);

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

    ASSERT_EQ(errors::OK, s.code()) << s.message();
    B.reset(B_raw);
  }

  float expected_dA[4] = {-.5f, 2.0f, -.5f, 2.0f};
  ASSERT_NO_FATAL_FAILURE(CompareNumericalAndManualGradients(
      MatMulModel, ctx_.get(), {A.get(), B.get()}, 0, expected_dA, 4,
      UseFunction()));
}

TEST_P(GradientCheckerTest, TestMul) {
  AbstractTensorHandlePtr x;
  {

              const std::vector<TF_Operation*>& outputs,
              const std::vector<string>& output_names,
              bool expect_failure = false) {
    DefineT(num_opers, opers, ToOutput(inputs), ToOutput(outputs), output_names,
            expect_failure);
  }

  // Caller must delete[] the returned value
  static const char** ToArray(const std::vector<string>& strs) {
    const char** ptr = nullptr;