return "Replace quantization candidates with composite functions into the "
           "module for post-training dynamic range case";
  }

  void getDependentDialects(DialectRegistry& registry) const override {
    registry.insert<TF::TensorFlowDialect>();
  }

  void runOnOperation() override;

 private:
  Option<OpSet> target_opset_{
      *this, "target-opset", llvm::cl::init(OpSet::TF),

  StringRef getDescription() const final {
    // This is a brief description of the pass.
    return "Insert quantized functions into the module";
  }

  void getDependentDialects(DialectRegistry& registry) const override {
    registry.insert<TF::TensorFlowDialect, func::FuncDialect>();
  }

 private:
  void runOnOperation() override;

  // Returns the function library for the given quantization method and opset
  // pair.

// name should be unique to the graph it is being inserted to. If the
// `ignore_unregistered_attrs` argument is set to true, the attributes which are
// not in the op registry will be ignored. If the `ignore_unregistered_attrs`
// argument is not set to true, _output_shapes attribute is added to nodes with
// ShapedType for the leading values with ShapedType in the results of the

        *registry, InferSparseSegmentOpCost<mlir::TF::SparseSegmentMeanOp>);
    RegisterCostFunction<mlir::TF::SparseSegmentSqrtNOp>(
        *registry, InferSparseSegmentOpCost<mlir::TF::SparseSegmentSqrtNOp>);
    RegisterCostFunction<mlir::TF::LookupTableFindV2Op>(
        *registry, InferLookupTableFindV2Cost);
    return registry;
  }();
  return *registry;
}

}  // namespace

// Creates an MLIRContext with the extensions required for quantization are
// registered.
inline std::unique_ptr<MLIRContext> CreateMlirContextForQuantization() {
  DialectRegistry registry{};
  func::registerAllExtensions(registry);
  return std::make_unique<MLIRContext>(registry);
}

}  // namespace mlir::quant::stablehlo

  std::vector<AbstractTensorHandle*> outputs(1);
  GradientRegistry registry;
  s = RegisterGradients(&registry);
  ASSERT_EQ(errors::OK, s.code()) << s.message();
  auto tape = std::make_unique<Tape>(/*persistent=*/false);
  s = Execute(check_numerics_op.get(), ctx.get(), absl::MakeSpan(outputs),
              &num_retvals, &forward_op, tape.get(), registry);
  ASSERT_EQ(errors::OK, s.code()) << s.message();

  string read_message;

          mlir::registerPassManagerCLOptions();
          mlir::DialectRegistry registry;
          registry.insert<mlir::BuiltinDialect>();
          registry.insert<mlir::arith::ArithDialect>();
          registry.insert<mlir::func::FuncDialect>();
          registry.insert<mlir::TFL::TensorFlowLiteDialect>();
          return registry;
        }()) {
    context_.loadAllAvailableDialects();

  absl::flat_hash_set<std::string> denylisted_mlir_op_names;
  for (auto& entry : denylisted_ops) {
    denylisted_mlir_op_names.insert(TfLiteToMlir(entry));
  }

  DialectRegistry registry;
  MLIRContext context(registry);
  StatusScopedDiagnosticHandler statusHandler(&context,
                                              /*propagate=*/true);

  // Import input_model to a MLIR module

class LowerGlobalsToMlProgram
    : public impl::LowerGlobalsToMlProgramPassBase<LowerGlobalsToMlProgram> {
 public:
  void getDependentDialects(DialectRegistry &registry) const override {
    registry.insert<mlir::tf_saved_model::TensorFlowSavedModelDialect,
                    ml_program::MLProgramDialect>();
  }

  void runOnOperation() override {

    const std::vector<std::string>& exported_model_signatures,
    const std::vector<std::string>& tag_names,
    absl::string_view input_arg_shapes_str) {
  mlir::DialectRegistry registry;
  RegisterAllTensorFlowDialects(registry);
  mlir::MLIRContext context(registry);
  context.loadAllAvailableDialects();

  auto module =
      TfToStablehlo(input_path, &context, exported_model_signatures, tag_names,