context_.loadAllAvailableDialects();

    mlir::OpBuilder builder(&context_);
    module_ = builder.create<mlir::ModuleOp>(builder.getUnknownLoc());

    builder.setInsertionPointToStart(module_->getBody());
    auto func = builder.create<mlir::func::FuncOp>(  //
        builder.getUnknownLoc(), "main", builder.getFunctionType({}, {}));
    func->setAttr("tfl.func", builder.getUnitAttr());

        builder.getUnknownLoc(), storage_type_width, effective_mins[0],
        effective_maxs[0], narrow_range, converter.expressed_type, is_signed);
    if (legacy_float_scale) {
      quantized_element_type =
          DownCastScale(quantized_element_type, effective_mins[0],
                        effective_maxs[0], builder.getUnknownLoc());
    }
  } else if (min.size() == max.size()) {

        RankedTensorType type = RankedTensorType::get(
            {}, TF::StringType::get(builder.getContext()));
        auto const_op = builder.create<TF::ConstOp>(
            builder.getUnknownLoc(),
            DenseStringElementsAttr::get(type, {filename}));

        it = const_ops.insert({asset.getSymName(), const_op}).first;
      }

      argument.replaceAllUsesWith(it->second.getOutput());

      builder.getFunctionType(input_types, return_types);

  std::string function_name = absl::StrCat("func_", subgraph.subgraph_id_);

  func::FuncOp new_func = func::FuncOp::create(builder.getUnknownLoc(),
                                               function_name, function_type);
  new_func.setVisibility(func::FuncOp::Visibility::Private);
  new_func.addEntryBlock();

  rewriter.setInsertionPointToStart(&new_func.getBody().front());

  auto one_val = DenseElementsAttr::get(type, kOne);
  auto one_cst =
      rewriter.create<stablehlo::ConstantOp>(rewriter.getUnknownLoc(), one_val);

  auto half_val = DenseElementsAttr::get(type, kHalf);
  auto half_cst =
      rewriter.create<stablehlo::ConstantOp>(one_cst.getLoc(), half_val);

}

quant::QuantParams DefaultQuantParamsPass::GetDefaultQuantParams(
    Builder builder) {
  if (!default_quant_params_) {
    default_quant_params_ = quantfork::fakeQuantAttrsToType(
        builder.getUnknownLoc(),
        /*numBits=*/8, default_min_, default_max_, /*narrowRange=*/false,
        builder.getF32Type(), is_signed_);
  }
  return default_quant_params_;
}

        builder_(context_.get()) {
    RegisterDialects(*context_);
    // TODO(aminim) figure out the location story here
    module_ = ModuleOp::create(builder_.getUnknownLoc());
    func_ = func::FuncOp::create(
        builder_.getUnknownLoc(), name,
        builder_.getFunctionType(std::nullopt, std::nullopt));
    module_->push_back(func_);
    builder_ = OpBuilder::atBlockBegin(func_.addEntryBlock());
  }

    }
    node_to_output_map[node_name].push_back(
        {output_count++, tensor_index, call_op_return});
  }

  Value scalar_one =
      CreateScalarConstValue<float>(builder, builder.getUnknownLoc(), 1.0);
  llvm::SmallVector<Value> returning_values(output_count, Value());
  for (const auto& node_name : node_to_output_map.keys()) {
    auto node_output_tensors = node_to_output_map[node_name];

void QuantizationDriver::QuantizeArg(BlockArgument arg,
                                     const QuantizedType quantized_type) {
  builder_.setInsertionPointToStart(arg.getOwner());
  QuantizeValue(arg, quantized_type, builder_.getUnknownLoc());
}

void QuantizationDriver::QuantizeValue(Value value,
                                       QuantizedType quantized_type,
                                       const Location loc) {

            output_zero_point_value);

    Value conv_output_value = op.getResult();
    auto output_uniform_quantized_tensor_type = RankedTensorType::getChecked(
        rewriter.getUnknownLoc(),
        /*shape=*/
        mlir::cast<TensorType>(conv_output_value.getType()).getShape(),
        output_uniform_quantized_type);

    SmallVector<Type> new_conv_output_types = {