pipeline_config=qc.PipelineConfig(
            merge_fusion_with_dequantize=merge_fusion_with_dequantize
        ),
    )
    quantization.quantize_saved_model(
        self._input_saved_model_path,
        self._output_saved_model_path,
        config,
    )

    expected_outputs = model.matmul(input_data)

  for spec in quantization_specs.specs:
    if spec.method.HasField(method):
      return True
  return False


# TODO: b/310594193 - Export API to pip package.
def quantize_saved_model(
    src_saved_model_path: str,
    dst_saved_model_path: str,
    config: qc.QuantizationConfig,
) -> None:
  """Quantizes a saved model.

  Args:

      == _PresetMethod.METHOD_STATIC_RANGE_INT8
  ):
    # Check and populate calibration options.
    _populate_calibration_options(quantization_options)


@tf_export.tf_export('quantization.experimental.quantize_saved_model')
def quantize(
    saved_model_path: str,
    output_directory: Optional[str] = None,
    quantization_options: Optional[_QuantizationOptions] = None,
    representative_dataset: Optional[

  quantization_options = tf.quantization.experimental.QuantizationOptions(
      signature_keys=['serving_default'],
      representative_datasets=dataset_file_map,
  )
  tf.quantization.experimental.quantize_saved_model(
      '/tmp/input_model',
      '/tmp/output_model',
      quantization_options=quantization_options,
  )
  ```
  """

  def __init__(
      self,