For the curious, Apple has an analogous Tensorflow Metal plugin to allow for Apple Silicon (and AMD GPU) acceleration using the same plugin architecture.
For example, tf.sort only sorts up to 16 values and overwrites the rest with -0. Apparently not fixed for over one year: https://developer.apple.com/forums/thread/689299
Also, tf.random always returns the same random numbers: https://developer.apple.com/forums/thread/69705
Although I guess these bugs are not the fault of Tensorflow's plugin architecture but rather Apple's implementation.
reminds of this particular xkcd [1], How someone fucks up that bad is beyond me.