Implementation:Tensorflow Serving Tfrt Regressor Test

Knowledge Sources	Tensorflow_Serving
Domains	Testing, Regression, TFRT
Last Updated	2026-02-13 00:00 GMT

Overview

Test suite validating the TFRT-based regressor servable, which handles regression inference using the TFRT runtime.

Description

This test file validates the TFRT regressor implementation which uses the TFRT execution engine for regression inference. The TfrtRegressorTest fixture initializes a TFRT runtime with 4 inter-op threads, sets up a ServerCore with saved_model_half_plus_two_cpu model using TfrtSavedModelSourceAdapterConfig, and uses RunRegress via TfrtSavedModelServable.

Key areas tested include:

• Basic regression with single and multiple examples
• Regression with context features
• Empty input and example list validation
• Invalid function name, input size, output size, input name, output name handling
• Session run failures
• Unexpected output tensor number, shape, size, and type

Usage

Run these tests to validate changes to the TFRT regressor, TFRT servable interface, or TFRT-based regression pipeline.

Code Reference

Source Location

• Repository: Tensorflow_Serving
• File: tensorflow_serving/servables/tensorflow/tfrt_regressor_test.cc
• Lines: 1-570

Test Fixture

class TfrtRegressorTest : public ::testing::Test {
 public:
  static void SetUpTestSuite() {
    tfrt_stub::SetGlobalRuntime(
        tfrt_stub::Runtime::Create(/*num_inter_op_threads=*/4));
  }
  void SetUp() override {
    // Creates ServerCore with TfrtSavedModelSourceAdapterConfig
    // and saved_model_half_plus_two_cpu model
  }
 protected:
  absl::Status CallRegress(ServerCore* server_core,
                           const RegressionRequest& request,
                           RegressionResponse* response) {
    ServableHandle<Servable> servable;
    TF_RETURN_IF_ERROR(GetSavedModelServableHandle(server_core, &servable));
    return RunRegress(run_options, kTestModelVersion,
        &(down_cast<TfrtSavedModelServable*>(servable.get()))->saved_model(),
        request, response);
  }
  static std::unique_ptr<ServerCore> server_core_;
  RegressionRequest request_;
};

Build Target

bazel test //tensorflow_serving/servables/tensorflow:tfrt_regressor_test

Test Coverage

Key Test Cases

Test Name	Category	Description
Basic	Integration	Tests basic regression with multiple examples
BasicWithContext	Integration	Tests regression with context features
EmptyExampleList	Validation	Tests error on empty example list
EmptyExampleListWithContext	Validation	Tests error on empty example list with context
EmptyInput	Validation	Tests error on empty input
InvalidFunctionName	Error Handling	Tests error on non-existent function name
InvalidFunctionUnmatchedInputSize	Error Handling	Tests error on mismatched input count
InvalidFunctionUnmatchedOutputSize	Error Handling	Tests error on mismatched output count
InvalidFunctionInvalidInputName	Error Handling	Tests error on invalid input tensor name
InvalidFunctionInvalidOutputName	Error Handling	Tests error on invalid output tensor name
RunsFails	Error Handling	Tests handling of TFRT run failures
UnexpectedOutputTensorNumber	Validation	Tests error on unexpected number of output tensors
UnexpectedOutputTensorShape	Validation	Tests error on unexpected output tensor shape
UnexpectedOutputTensorSize	Validation	Tests error on unexpected output tensor size
UnexpectedOutputTensorType	Validation	Tests error on unexpected output tensor type

Usage Examples

Test Pattern

TEST_F(TfrtRegressorTest, Basic) {
  auto request = test_util::CreateProto<RegressionRequest>(
      "model_spec {"
      "  name: \"test_model\""
      "  signature_name: \"regress_x_to_y\""
      "}"
      "input { example_list { examples { features { ... } } } }");
  RegressionResponse response;
  TF_ASSERT_OK(CallRegress(server_core_.get(), request, &response));
  // Validate regression value: 0.5 * x + 2
}

Related Pages

• Implementation:Tensorflow_Serving_Tfrt_Regressor
• Implementation:Tensorflow_Serving_Regressor_Test