// CHECK-NEXT:  } ],
// CHECK-NEXT:  description: "MLIR Converted.",

// CHECK:  metadata: [ {
// CHECK-NEXT:    name: "min_runtime_version",
// CHECK-NEXT:    buffer: 8
// CHECK-NEXT:  } ],
// CHECK-NEXT:  signature_defs: [ {
// CHECK-NEXT:    inputs: [ {
// CHECK-NEXT:      name: "input1",
// CHECK-NEXT:      tensor_index: 1
// CHECK-NEXT:    }, {
// CHECK-NEXT:      name: "input2"
// CHECK-NEXT:    } ],

  tensor_info_s = tf.compat.v1.saved_model.utils.build_tensor_info(s)
  tensor_info_t = tf.compat.v1.saved_model.utils.build_tensor_info(t)

  signature_def = tf.saved_model.signature_def_utils.build_signature_def(
      inputs=None, outputs={'s': tensor_info_s}, method_name='some_function')
  signature_def2 = tf.saved_model.signature_def_utils.build_signature_def(
      inputs=None, outputs={'t': tensor_info_t}, method_name='some_function')

  tensor_info_x = tf.saved_model.utils.build_tensor_info(x)
  tensor_info_r = tf.saved_model.utils.build_tensor_info(r)

  signature_def = tf.saved_model.signature_def_utils.build_signature_def(
      inputs={'x': tensor_info_x},
      outputs={'r': tensor_info_r},
      method_name='some_function')
  signature_def2 = tf.saved_model.signature_def_utils.build_signature_def(
      inputs={'x': tensor_info_x},
      outputs={'r': tensor_info_r},

  tensor_info_result = tf.compat.v1.saved_model.utils.build_tensor_info(result)

  signature_def = tf.saved_model.signature_def_utils.build_signature_def(
      inputs=None,
      outputs={'result': tensor_info_result},
      method_name='some_function')

  return {'key_1': signature_def, 'key_2': signature_def}, None, None


if __name__ == '__main__':
  common_v1.set_tf_options()

        }
      }
    }
  }
  signature_def: {
    key: "predict0"
    value: {
      inputs: {
        key: "inputs"
        value: {
          name: "input0"
          dtype: DT_STRING
        }
      }
      outputs: {
        key: "outputs"
        value: {
          name: "batch_func:0"
        }
      }
    }
  }
  signature_def: {
    key: "predict1"
    value: {

  result = tf.transpose(merge_op)

  tensor_info_result = tf.compat.v1.saved_model.utils.build_tensor_info(result)

  signature_def = tf.saved_model.signature_def_utils.build_signature_def(
      inputs=None,
      outputs={'result': tensor_info_result},
      method_name='some_function')

  return {'key': signature_def}, None, None


if __name__ == '__main__':
  common_v1.set_tf_options()

  Returns:
    Signature def map where the values (`SignatureDef`) are serialized.
  """
  signature_def_map_serialized = {}
  for key, signature_def in signature_def_map.items():
    signature_def_map_serialized[key] = signature_def.SerializeToString()

  return signature_def_map_serialized


def _has_quantization_method(
    quantization_specs: qc.QuantizationSpecs, method: str
) -> bool:

  // CHECK:   } ],
  // CHECK:   metadata: [ {
  // CHECK:     name: "min_runtime_version",
  // CHECK:     buffer: 2
  // CHECK:   } ],
  // CHECK:   signature_defs: [  ]
  // CHECK: }

  // Test that i4 buffers are densely packed, i.e. [-8, 3, -2, -5] should be
  // be packed low-bits-first as [0x38, 0xBE] or [56, 190]. Tensor type should
  // be INT4.

// CHECK-NEXT:  } ],
// CHECK-NEXT:  metadata: [ {
// CHECK-NEXT:    name: "min_runtime_version",
// CHECK-NEXT:    buffer: 2
// CHECK-NEXT:  } ],
// CHECK-NEXT:  signature_defs: [  ]
// CHECK-NEXT: }
func.func @main(%arg0 : tensor<!tf_type.variant<tensor<2xi32>>>) -> tensor<!tf_type.variant<tensor<2xi32>>> {
  func.return %arg0 : tensor<!tf_type.variant<tensor<2xi32>>>

// CHECK-NEXT:  } ],
// CHECK-NEXT:  metadata: [ {
// CHECK-NEXT:    name: "min_runtime_version",
// CHECK-NEXT:    buffer: 2
// CHECK-NEXT:  } ],
// CHECK-NEXT:  signature_defs: [ {
// CHECK-NEXT:    inputs: [  ],
// CHECK-NEXT:    outputs: [ {
// CHECK-NEXT:      name: "start_logits"
// CHECK-NEXT:    } ],
// CHECK-NEXT:    signature_key: "serving_default"
// CHECK-NEXT:  } ]