// converting them to NHWC formats along with extra optimizations such as
// constant folding the transpose->convolution pattern. This is useful when
// downstream pipeline (e.g. XLA) is more optimized when accepting NHWC formats.
void AddProcessNchwTensorPasses(OpPassManager& pm);

// Registers quantization pass pipelines. This is only required when running

#ifndef TENSORFLOW_COMPILER_MLIR_LITE_PYTHON_JAX_TO_TFL_FLATBUFFER_H_
#define TENSORFLOW_COMPILER_MLIR_LITE_PYTHON_JAX_TO_TFL_FLATBUFFER_H_

#include <string>

#include "tensorflow/core/lib/core/errors.h"
#include "tensorflow/core/platform/status.h"
#include "tensorflow/core/platform/types.h"
#include "tensorflow/lite/toco/model_flags.pb.h"
#include "tensorflow/lite/toco/toco_flags.pb.h"

namespace tensorflow {

#include "tensorflow/compiler/mlir/tensorflow/utils/export_utils.h"
#include "tensorflow/core/framework/attr_value.pb.h"
#include "tensorflow/core/framework/node_def.pb.h"
#include "tensorflow/core/framework/node_def_util.h"
#include "tensorflow/core/framework/op_def_builder.h"
#include "tensorflow/core/platform/status.h"

namespace tensorflow {

#include "mlir/IR/Operation.h"  // from @llvm-project
#include "mlir/IR/Types.h"  // from @llvm-project
#include "tensorflow/core/framework/attr_value.pb.h"
#include "tensorflow/core/framework/function.h"
#include "tensorflow/core/framework/node_def.pb.h"
#include "tensorflow/core/framework/node_def_util.h"
#include "tensorflow/core/lib/core/status.h"

namespace mlir {
class ShapedType;
}  // namespace mlir

namespace tensorflow {

    // functions, as it may sometimes remove arguments and results.
    enable_grappler = false;
  }

  // If true, use ServingCoreSelector to pick TPU core. Otherwise, obtain core
  // location from assigned device name.
  // Currently we don't use core_selector for training use cases.
  bool tpu_use_core_selector = false;

#define TENSORFLOW_COMPILER_JIT_XLA_HOST_SEND_DEVICE_CONTEXT_H_

#include "xla/shape.h"
#include "xla/stream_executor/device_memory.h"
#include "xla/stream_executor/stream.h"
#include "tensorflow/core/framework/device_base.h"
#include "tfrt/concurrency/async_value_ref.h"  // from @tf_runtime

namespace tensorflow {

// XlaHostSendDeviceContext is a DeviceContext that is intended to be

#include "tensorflow/compiler/mlir/quantization/tensorflow/exported_model.pb.h"
#include "tensorflow/compiler/mlir/quantization/tensorflow/python/py_function_lib.h"
#include "tensorflow/core/protobuf/meta_graph.pb.h"

namespace mlir::quant::stablehlo {

// Performs post-calibration graph transformation as part of post-training
// static-range quantization.
//

namespace mlir {
namespace odml {

// Given a Composite op that wraps a core.aten.avg_pool2d, returns the padding
// configuration required for the `tfl.pad` if the padding part of the op is
// to be done before average pooling.
DenseIntElementsAttr GetPadOpAttr(Builder& builder, mhlo::CompositeOp op);

// Given a Composite op that wraps a core.aten.avg_pool2d, and assuming that
// the padding part is extracted into a tfl.pad op prior to a

#include "tensorflow/compiler/mlir/quantization/tensorflow/python/py_function_lib.h"
#include "tensorflow/core/framework/graph.pb.h"
#include "tensorflow/core/framework/graph_debug_info.pb.h"
#include "tensorflow/core/lib/core/errors.h"
#include "tensorflow/core/platform/status.h"
#include "tensorflow/core/platform/types.h"
#include "tensorflow/lite/toco/model_flags.pb.h"
#include "tensorflow/lite/toco/toco_flags.pb.h"

#include "mlir/IR/Builders.h"  // from @llvm-project
#include "tensorflow/compiler/mlir/tensorflow/ir/tf_attributes.h"
#include "tensorflow/core/framework/tensor.h"
#include "tensorflow/core/framework/tensor.pb.h"
#include "tensorflow/core/framework/tensor_shape.pb.h"
#include "tensorflow/core/protobuf/struct.pb.h"

namespace tensorflow {

using tsl::StatusOr;

// Converts an TensorFlow tensor proto into an MLIR elements attribute.