sufficient description, if applicable unit tests are added, if it is a
  reasonable contribution (meaning it is not a single liner cosmetic PR).

**2. Valid?**

-   If the PR passes all the quality checks then we go ahead and assign a
    reviewer.
-   If the PR didn't meet the validation criteria, we request for additional
    changes to be made to PR to pass quality checks and send it back or on a

        "//tensorflow/compiler/mlir/quantization/tensorflow/python:quantize_model_cc_impl",
        "//tensorflow/compiler/mlir/quantization/tensorflow:passes",
        "//tensorflow/compiler/mlir/tensorflow",
        "//tensorflow/compiler/mlir/tensorflow/c:mlir_c_api_registration",
        "//tensorflow/compiler/mlir/tensorflow:error_util",

            [kernel and op registration C API](https://github.com/tensorflow/community/blob/master/rfcs/20190814-kernel-and-op-registration.md).
        *   Register custom graph optimization passes with
            [graph optimization C API](https://github.com/tensorflow/community/blob/master/rfcs/20201027-modular-tensorflow-graph-c-api.md).
*   [oneAPI Deep Neural Network Library (oneDNN)](https://github.com/oneapi-src/oneDNN)

# that directory.
@test "bazel nobuild passes on all of TF except TF Lite and win toolchains" {
    bazel build --experimental_cc_shared_library --nobuild --keep_going -- //tensorflow/... -//tensorflow/lite/... -//tensorflow/tools/toolchains/win/... -//tensorflow/tools/toolchains/win_1803/...
}

@test "API compatibility test passes, ensuring no unexpected changes to the TF API" {