return WalkResult::advance();
  });
  if (result.wasInterrupted()) {
    return failure();
  }

  return builder.getArrayAttr(function_list);
}

// Creates a pruned module containing the XlaCallModule's entry function and
// other functions transitively called by the entry function.
FailureOr<OwningOpRef<ModuleOp>> PruneStablehloModule(

  } else {
    builder.setInsertionPointToStart(&block);
  }
  TypeAttr type_attr = TypeAttr::get(new_type);
  auto quantize = builder.create<TFL::QuantizeOp>(value.getLoc(), new_type,
                                                  value, type_attr);
  auto dequantize = builder.create<TFL::DequantizeOp>(
      value.getLoc(), expressed_type, quantize.getOutput());
  value.replaceAllUsesWith(dequantize);

    if (failed(applyPatternsAndFoldGreedily(func, frozen_patterns))) {
      func.emitError() << "quant-propagate-quantize-type failed.";
      signalPassFailure();
    }
  }
}

}  // namespace

// Creates an instance of the TensorFlow dialect PropagateQuantizeType pass.
std::unique_ptr<OperationPass<ModuleOp>> CreatePropagateQuantizeTypePass() {
  return std::make_unique<PropagateQuantizeType>();
}

#include "tfrt/support/rc_array.h"  // from @tf_runtime
#include "tfrt/tensor/dense_host_tensor.h"  // from @tf_runtime
#include "tfrt/tensor/tensor.h"  // from @tf_runtime

namespace tensorflow {
namespace {

// Creates a BEF file with a program that runs
// tfrt_fallback_async.batch_function with a empty function forwarding inputs or
// outputs.
std::pair<tfrt::BefBuffer, tfrt::RCReference<tfrt::BEFFile>> CreateBefFile(

    if (constant.getType().getRank() != 2) return failure();

    // Create a tfl.transpose op that performs ZX transpose on `input`.
    auto create_z_x_transpose_op = [&](Value input) -> Value {
      RankedTensorType input_type =
          mlir::cast<RankedTensorType>(input.getType());
      const int input_rank = input_type.getRank();

      // Create a 1D I32 tensor for representing the dimension permutation.

        module_(mlir::ModuleOp::create(mlir::UnknownLoc::get(&context_))),
        builder_(&module_->getBodyRegion()) {
    context_.loadAllAvailableDialects();
  }

 protected:
  mlir::MLIRContext context_;
  mlir::OwningOpRef<mlir::ModuleOp> module_;
  mlir::OpBuilder builder_;
};

TEST_F(XlaLegalizeTargetsTest, CreatesConversionTargets) {
  auto const_int = builder_.create<mlir::arith::ConstantIntOp>(

    func->removeAttr("tf_saved_model.exported_names");

    ArrayRef<Value> args;
    builder.create<func::CallOp>(session_initializer.getLoc(),
                                 func.getFunctionType().getResults(),
                                 func.getSymName(), args);
  }
  builder.create<func::ReturnOp>(session_initializer.getLoc());

  session_initializer.erase();
}

}  // namespace

  ASSERT_TRUE(tensorflow::GrpcServer::Create(
                  server_def, tensorflow::Env::Default(), &worker_server1)
                  .ok());
  ASSERT_TRUE(worker_server1->Start().ok());

  server_def.set_task_index(2);
  std::unique_ptr<tensorflow::GrpcServer> worker_server2;
  ASSERT_TRUE(tensorflow::GrpcServer::Create(
                  server_def, tensorflow::Env::Default(), &worker_server2)

  mlir::OpBuilder::InsertPoint insert_point = builder->saveInsertionPoint();

  auto launch = builder->create<mlir::tf_device::LaunchOp>(
      loc, builder->getStringAttr(device), op->getResultTypes());
  launch.getBody().push_back(new mlir::Block);

  builder->setInsertionPointToEnd(&launch.GetBody());
  builder->create<mlir::tf_device::ReturnOp>(loc, op->getResults());

  // Move op inside cluster.

ConstantOp GetScalarConstOfType(Type ty, Location loc, int64_t raw_value,
                                OpBuilder* builder) {
  return builder->create<ConstantOp>(loc, hlo::getScalarOfType(ty, raw_value));
}

ConstantOp GetScalarNegZeroOfType(Type ty, Location loc, OpBuilder* builder) {
  return builder->create<ConstantOp>(loc, hlo::getScalarNegZeroOfType(ty));
}

DenseIntElementsAttr GetI64ElementsAttr(ArrayAttr attr) {
  RankedTensorType ty =