```

### 3. Failure after conversion
If the conversion is successful, but the generated model is wrong, then state what is wrong:

- Model produces wrong results and/or has lesser accuracy.
- Model produces correct results, but it is slower than expected.

### 4. (optional) RNN conversion support
If converting TF RNN to TFLite fused RNN ops, please prefix [RNN] in the title.

    deps = [
        ":immediate_execution_context",
        "//tensorflow/c:conversion_macros",
    ],
)

cc_library(
    name = "tfe_cancellation_manager_internal",
    hdrs = ["tfe_cancellation_manager_internal.h"],
    visibility = [
        "//tensorflow:internal",
    ],
    deps = [
        "//tensorflow/c:conversion_macros",
        "//tensorflow/core:framework",
    ],
)

cc_library(

        "//tensorflow/core:protos_all_cc",
        # TODO(b/74620627): remove when _USE_C_SHAPES is removed
    ],
    alwayslink = 1,
)

cc_library(
    name = "conversion_macros",
    hdrs = [
        "conversion_macros.h",
    ],
    visibility = ["//tensorflow:__subpackages__"],
)

cc_library(
    name = "c_op_requires",
    hdrs = ["c_op_requires.h"],

TF_CAPI_EXPORT extern void TFE_ContextEndStep(TFE_Context* ctx);

#ifdef __cplusplus
} /* end extern "C" */
#endif

#ifdef __cplusplus
// A workaround to ease conversion to and from numpy objects and
// TFE_TensorHandle's.
//
// TODO(ashankar): Figure out an alternative scheme that precludes the need for
// these API-boundary breaking methods.
namespace tensorflow {
class Tensor;

    * when converter flag "_experimenal_use_buffer_offset" is enabled, additional metadata is automatically excluded from the generated model. The behaviour is the same as "exclude_conversion_metadata" is set
    * If the model is larger than 2GB, then we also require "exclude_conversion_metadata" flag to be set

### Major Features and Improvements

        "//tensorflow/lite/kernels:builtin_ops",
        "//tensorflow/lite/kernels:reference_ops",
        "//tensorflow/lite/schema:schema_fbs",
        "//tensorflow/lite/toco/logging:conversion_log_util",
        "//tensorflow/lite/toco/logging:toco_conversion_log_proto_cc",
        "//tensorflow/lite/toco:model_flags_proto_cc",
        "//tensorflow/lite/toco:toco_convert",
        "//tensorflow/lite/toco:toco_flags_proto_cc",

// DT_RESOURCE. The string serialization is converted back to a
// ResourceHandle during Session run where the TF_Tensor is converted to a
// Tensor.
// TFv2 does not depend on this conversion. There is no matching
// TF_TensorFromTensorV1 because the conversion to string is performed by the
// python side of Session.
static Status TF_TensorToTensorV1(const TF_Tensor* src, Tensor* dst) {
  Status status = TF_TensorToTensor(src, dst);

/tests/tf_to_tfrt_data,tensorflow/compiler/mlir/tfrt/tests/saved_model,tensorflow/compiler/mlir/tfrt/transforms/lhlo_gpu_to_tfrt_gpu,tensorflow/compiler/mlir/tfrt/transforms/mlrt,tensorflow/core/runtime_fallback,tensorflow/core/runtime_fallback/conversion,tensorflow/core/runtime_fallback/kernel,tensorflow/core/runtime_fallback/opdefs,tensorflow/core/runtime_fallback/runtime,tensorflow/core/runtime_fallback/util,tensorflow/core/runtime_fallback/test,tensorflow/core/runtime_fallback/test/gpu,tenso...

process images, audio, videos, and text. There are several modules specialized
in taking those formats, modifying them, and/or converting them to intermediate
formats that can be processed by TensorFlow.

These modifications and conversions are handled by a variety of libraries that
have different security properties and provide different levels of confidence
when dealing with untrusted data. Based on the security history of these