func.func @serving_default(%arg0: tensor<1x32x32x128xf32> {tf_saved_model.index_path = ["a"]}) -> (tensor<1x64x64x128xf32> {tf_saved_model.index_path = ["b"]}) attributes {tf.entry_function = {control_outputs = "", inputs = "c:0", outputs = "d:0"}, tf_saved_model.exported_names = ["serving_default"]} {
      %0  = "tf.Const"() {value = dense<[56, 904]> : tensor<2xi32>} : () -> tensor<2xi32>

  return %0 : tensor<1xf32>
}
// The contents of `@serving_default` should have been inlined to `@batch_func`.
// CHECK: func.func @serving_default(%[[ARG0:.*]]: tensor<1xf32>, %[[ARG1:.*]]: tensor<1xf32>) -> tensor<1xf32>
// CHECK-NOT: tf.BatchFunction
// CHECK: %[[ADD0:.*]] = "tf.AddV2"(%[[ARG0]], %[[ARG1]])
// CHECK: return %[[ADD0]] : tensor<1xf32>

    // If the signature_key has not been explicitly specified, use the default
    // value of "serving_default".
    const std::string signature_key = dataset_config.has_signature_key()
                                          ? dataset_config.signature_key()
                                          : "serving_default";
    if (repr_dataset_file_map.contains(signature_key)) {
      return absl::InvalidArgumentError(

  // LINT.IfChange(savedmodel_to_stablehlo)
  m.def(
      "savedmodel_to_stablehlo",
      [](absl::string_view input_path,
         const std::vector<std::string>& exported_model_signatures =
             {"serving_default"},
         const std::vector<std::string>& tag_names = {"serve"},
         absl::string_view input_arg_shapes_str = "") -> py::bytes {
        auto module_bytecode =

// RUN: tf-opt -tf-saved-model-mark-initialized-variables-invalid-session-test %s | FileCheck %s --check-prefix=INVALID


module attributes {tf_saved_model.semantics, tf_saved_model.under_construction} {

  func.func @serving_default(%arg0: tensor<!tf_type.resource<tensor<100x50xf32>>> {tf.resource_name = "dense/kernel"}, %arg1: tensor<!tf_type.resource<tensor<50xf32>>> {tf.resource_name = "dense/bias"}) -> (tensor<100x50xf32> {tf_saved_model.index_path = ["dense_2"]})

  def test_quantize_model_fails_when_invalid_quant_options_serialization(self):
    src_saved_model_path = self.create_tempdir().full_path
    dst_saved_model_path = self.create_tempdir().full_path
    signature_def_keys = ['serving_default']
    quant_opts_serialized = 'invalid proto serialization string'.encode('utf-8')

    with self.assertRaisesRegex(TypeError, 'incompatible function arguments'):
      pywrap_quantize_model.quantize_ptq_static_range(

  EXPECT_THAT(FindMainFuncOp(*module_op), IsNull());
}

TEST_F(FindMainFuncOpTest, ReturnsServingDefaultFuncOp) {
  constexpr absl::string_view kModuleWithServingDefaultFunc = R"mlir(
    module {
      func.func @serving_default() -> () {
        return
      }
    }
  )mlir";

  OwningOpRef<ModuleOp> module_op =
      ParseModuleOpString(kModuleWithServingDefaultFunc);
  EXPECT_THAT(*module_op, NotNull());

// CHECK: return %[[CUSTOM_AGGREGATOR_1]] : tensor<1x3xf32>
// CHECK: }
// CHECK: }

// -----

// Tests that stablehlo op serialization also works for the "serving_default"
// function.

func.func @serving_default(%arg0: tensor<1x4xf32>) -> tensor<1x3xf32> {
  %0 = stablehlo.constant dense<1.0> : tensor<4x3xf32>

    %cst = "tf.Const"() {device = "", value = dense<[[[[-0.315365672, 0.27481091], [0.0901821703, -0.382271349], [-0.105572946, -0.354302853]], [[-0.47703138, -0.307006568], [0.306320101, -0.209111646], [0.252869487, 0.449634969]], [[0.167675957,...

# ==============================================================================

# LINT.IfChange(savedmodel_to_stablehlo)
def savedmodel_to_stablehlo(
    input_path: str,
    exported_model_signatures: list[str] = ["serving_default"],
    tag_names: list[str] = ["serve"],
    input_arg_shapes_str: str = "",
) -> bytes: ...
# LINT.ThenChange()

# LINT.IfChange(tensorflow_module_to_stablehlo)
def tensorflow_module_to_stablehlo(