#define DEBUG_TYPE "quantization-context"

namespace mlir {
namespace quant {

QuantizeContext::QuantizeContext(func::FuncOp func, const DeviceTarget &spec)
    : func_(func), target_spec_(spec) {
  llvm::DenseMap<Value, int> value_to_state;
  func.walk([&](quantfork::QuantizeRegionOp op) {
    for (int i = 0, e = op.getNumOperands(); i != e; ++i) {

    // results and arguments.
    llvm::DenseMap<OpValue, int> operand_states_;
    llvm::DenseMap<OpValue, int> result_states_;
  };

  func::FuncOp func_;

  DeviceTarget target_spec_;

  StatesManager states_manager_;
};

}  // namespace quant
}  // namespace mlir

    }

    public void copyTo(JavaExecSpec targetSpec) {
        // JavaExecSpec
        targetSpec.setArgs(getArgs());
        targetSpec.getArgumentProviders().addAll(getArgumentProviders());
        targetSpec.getMainClass().set(getMainClass());
        targetSpec.getMainModule().set(getMainModule());
        targetSpec.getModularity().getInferModulePath().set(getModularity().getInferModulePath());

        super(resolver);
    }

    public void copyTo(ExecSpec targetSpec) {
        // Fork options
        super.copyTo(targetSpec);
        // BaseExecSpec
        copyBaseExecSpecTo(this, targetSpec);
        // ExecSpec
        targetSpec.setArgs(getArgs());
        targetSpec.getArgumentProviders().addAll(getArgumentProviders());
    }

        "            np.float32\n",
        "        )\n",
        "    }\n",
        "converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)\n",
        "converter.target_spec.supported_ops = [\n",
        "    tf.lite.OpsSet.SELECT_TF_OPS,  # enable TensorFlow ops.\n",
        "    tf.lite.OpsSet.TFLITE_BUILTINS,  # enable TFL ops.\n",
        "]\n",

int main(int argc, char* argv[]) {
  tensorflow::InitMlir y(&argc, &argv);
  LOG(INFO) << "odml_to_stablehlo is being deprecated, please use "
               "TFlite converter with flag: "
               "converter.target_spec.supported_ops = "
               "[tf.lite.OpsSet.EXPERIMENTAL_STABLEHLO_OPS] ";

  mlir::odml::initAllPasses();
  mlir::PassPipelineCLParser passPipeline("", "Add available compiler passes.");

    srcs = [
        "odml_to_stablehlo.cc",
    ],
    copts = ["-O3"],
    deprecation = "odml_to_stablehlo is being deprecated, please use TFlite converter with flag: " +
                  "converter.target_spec.supported_ops = " +
                  " [tf.lite.OpsSet.EXPERIMENTAL_STABLEHLO_OPS]",
    deps = [
        ":check_accepted_ops_pass",
        ":op_stat_pass",
        ":stablehlo_util",
        ":transforms",

        public void all(boolean testTaskShouldRunAfter) {
            targets.add(new TargetSpec(null, "all", builder, testTaskShouldRunAfter));
        }
    }

    private static class TargetSpec extends BlockStatement implements BlockBody {
        private final BuildScriptBuilder builder;
        private final String name;

          "ops and disabling `_experimental_lower_tensor_list_ops` flag in the "
          "TFLite converter object. For example, "
          "converter.target_spec.supported_ops = "
          "[tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]\\n "
          "converter._experimental_lower_tensor_list_ops = False");
      signalPassFailure();
    }
  } else {

    *   Enabled post training with calibrations for models that require user
        provided TensorFlow Lite custom op libraries via
        `converter.target_spec._experimental_custom_op_registerers`. used in
        Python Interpreter API.

*   TF Core:

    *   Corrected higher-order gradients of control flow constructs (`tf.cond`,