Implementations MAY choose to support other parent resources.
                            Implementations supporting other types of parent resources MUST clearly
                            document how/if Port is interpreted.


                            For the purpose of status, an attachment is considered successful as

    *   Keras-based LSTM models must be converted with an explicit batch size in
        the input layer.

## Bug Fixes and Other Changes

### TF Core:

*   Set `tf2_behavior` to 1 to enable V2 for early loading cases.
*   Add `execute_fn_for_device function` to dynamically choose the
    implementation based on underlying device placement.
*   Eager:
    *   Add `reduce_logsumexp` benchmark with experiment compile.