*   Added support for `tflite_convert` command line tool in 2.0.
    *   Post-training quantization tool supports quantizing weights shared by
        multiple operations. The models made with versions of this tool will use
        INT8 types for weights and will only be executable interpreters from
        this version onwards.
    *   Post-training quantization tool supports fp16 weights and GPU delegate

                                pool for the upstream service that can be ejected.
                              format: int32
                              type: integer
                            minHealthPercent:
                              description: Outlier detection will be enabled as long
                                as the associated load balancing pool has at least

                                pool for the upstream service that can be ejected.
                              format: int32
                              type: integer
                            minHealthPercent:
                              description: Outlier detection will be enabled as long
                                as the associated load balancing pool has at least