type: object
                type: array
              type:
                description: |-
                  Specifies the type of Wasm Extension to be used.

                  Valid Options: HTTP, NETWORK
                enum:
                - UNSPECIFIED_PLUGIN_TYPE
                - HTTP
                - NETWORK
                type: string
              url:

### `tf.lite`:

*   `TFLiteConverter`:
    *   Support optional flags `inference_input_type` and
        `inference_output_type` for full integer quantized models. This allows
        users to modify the model input and output type to integer types
        (`tf.int8`, `tf.uint8`) instead of defaulting to float type
        (`tf.float32`).
*   NNAPI