Getting error 'Op type not registered 'Scann>ScannSearchBatched' while inferencing a TF recommender SCANN model in Java

Hi, I trained a ScaNN powered model described here in Python.

Tf version: 2.7.0
Environment: Mac and Ubuntu

I am trying to infer it in JAVA using native tensorflow-core-platform version 0.4.0

Java code:

        URL modelURL = Main.class.getClassLoader().getResource("model/1");
        String modelPath = Paths.get(modelURL.toURI()).toString();

        SavedModelBundle model = SavedModelBundle.load(modelPath, "serve");

I am getting error Op type not registered 'Scann>ScannSearchBatched' in binary running on xx. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.

Please let me know what's going on?
I know Mac is not supported by ScaNN but its not working on Ubuntu too.
So Can I use Tf native core platform in JAVA for Scann based model?

Start with the Python ScaNN model described in the linked TensorFlow Recommenders example and the Java call to SavedModelBundle.load. Reproduce the missing Scann>ScannSearchBatched error on Ubuntu with TensorFlow 2.7.0 and tensorflow-core-platform 0.4.0, then determine whether this model is supported in Java and record the compatibility result.