* Add docs about [overriding the `operationId` for all the *path operations*](https://fastapi.tiangolo.com/advanced/path-operation-advanced-configuration/#using-the-path-operation-function-name-as-the-operationid) based on their function name. PR [#642](https://github.com/tiangolo/fastapi/pull/642) by [@SKalt](https://github.com/SKalt).

        operation is a scalar.
    *   Fix `NNAPI` delegate failure when Axis input for reduce operation is a
        scalar.
    *   Expose option to limit the number of partitions that will be delegated
        to `NNAPI`.
    *   If a target accelerator is specified, use its feature level to determine
        operations to delegate instead of SDK version.
*   `tf.random`:

non-trivial square root Result = Composite W = 41 B = 2c # End of iteration Result = Composite W = 41 B = 16 # End of iteration Result = Composite W = 41 B = 14 # End of iteration Result = Composite W = 41 B = 2 # End of iteration Result = Composite W = 41 B = 3a # End of iteration Result = Composite W = 55 B = 40 # End of iteration Result = Composite W = 55 B = 7 # End of iteration Result = Composite W = 55 B = 23 # End of iteration Result = Composite W = 55 B = 2e # End of iteration Result = Composite...

non-trivial square root Result = Composite W = 41 B = 2c # End of iteration Result = Composite W = 41 B = 16 # End of iteration Result = Composite W = 41 B = 14 # End of iteration Result = Composite W = 41 B = 2 # End of iteration Result = Composite W = 41 B = 3a # End of iteration Result = Composite W = 55 B = 40 # End of iteration Result = Composite W = 55 B = 7 # End of iteration Result = Composite W = 55 B = 23 # End of iteration Result = Composite W = 55 B = 2e # End of iteration Result = Composite...