EXPECT_THAT(pre_calibration_result, IsOk());

  SmallVector<func::FuncOp> func_ops;
  for (auto func_op : pre_calibration_result->getOps<func::FuncOp>()) {
    func_ops.push_back(func_op);
  }
  ASSERT_THAT(func_ops, SizeIs(2));
  EXPECT_THAT(func_ops, Contains(HasSymName("main")));
  EXPECT_THAT(func_ops, Contains(HasSymName("composite_dot_general_fn_1")));

        auto dequantize_op = builder->create<TFL::DequantizeOp>(
            op->getLoc(), dequantized_input_type, input.get());
        dequantized_inputs.push_back(dequantize_op);
      } else {
        dequantized_inputs.push_back(input.get());
      }
    }

    // Result types.
    SmallVector<Type, 4> result_types;
    for (auto result_type : op->getResultTypes()) {

    // each entry function. The one exception are initializer functions, which
    // have `tf_saved_model.initializer_type` instead.
    if (IsEntryFunction(func)) {
      entry_funcs.push_back(func);
    }
  });
  return entry_funcs;
}

LogicalResult GetCallees(SymbolUserOpInterface op, SymbolTable &symtab,
                         llvm::SmallVector<func::FuncOp> &callees) {

    if (std::fabs(rmax - rmin) < std::numeric_limits<double>::epsilon()) {
      scales.push_back(1.0);
      zeroPoints.push_back(qmin);
      continue;
    }

    double scale;
    int64_t nudgedZeroPoint;
    getNudgedScaleAndZeroPoint(qmin, qmax, rmin, rmax, scale, nudgedZeroPoint);
    scales.push_back(scale);
    zeroPoints.push_back(nudgedZeroPoint);
  }

    SmallVector<int64_t, 4> non_unit_dims;

    for (int i = 0; i < input_shape_extended.size(); i++) {
      int64_t dim = broadcast_shape[i];
      if (dim != 1) {
        non_unit_dims.push_back(dim);
        input_carryover_dims.push_back(input_shape_extended[i]);
      }
    }

    // If the reshape rank is less than the number of non-unit dimensions
    // of the broadcast, then the reshape collapses non-unit dimensions.

    if (context_.mode == RendererContext::kHeader) {
      absl::StrAppend(&text, argument.Initializer());
    }
    if (argument.HasDefaultValue()) {
      args_with_default_val.push_back(text);
    } else {
      args_without_default_val.push_back(text);
    }
  }
  std::vector<string> arguments;
  arguments.reserve(args_without_default_val.size() +
                    args_with_default_val.size());

      std::vector<uint8_t>(expected_value.begin(), expected_value.end());
  input_model.buffers.push_back(std::move(model_metadata_buffer));
  auto metadata_t = std::make_unique<tflite::MetadataT>();
  metadata_t->name = tflite::optimize::kTfLiteReducedPrecisionKey;
  metadata_t->buffer = input_model.buffers.size() - 1;
  input_model.metadata.push_back(std::move(metadata_t));

  // Sparsify and create output model

               const std::string &contents) {
  std::vector<const char *> include_directories;
  auto local_include_directory = flatbuffers::StripFileName(filename);
  include_directories.push_back(local_include_directory.c_str());
  include_directories.push_back(nullptr);
  if (!parser->Parse(contents.c_str(), include_directories.data(),
                     filename.c_str())) {
    fprintf(stderr, "Failed to parse flatbuffer schema '%s'\n",

        values_for_results.push_back(output);
      }
    }
  }
  return values_for_results;
}

// Compute signature for raised func from arugments and outputs of
// Operation partition.
llvm::SmallVector<Type> TypesFromValues(
    const llvm::SmallVector<Value>& values) {
  llvm::SmallVector<Type> types;
  for (auto value : values) {
    types.push_back(value.getType());
  }
  return types;

    TF_RET_CHECK(sit != shape_info.end())
        << "Missing shape information for node " << node->name();
    std::vector<PartialTensorShape> shapes;
    for (const auto& output : sit->second) shapes.push_back(output.shape);

    auto it = expected_shapes.find(node->name());
    if (it != expected_shapes.end()) {
      if (!PartialTensorShapeUtils::AreIdentical(shapes, it->second)) {
        return errors::InvalidArgument(