It doesn't. I can be done quickly on any conventional computer: https://en.wikipedia.org/wiki/Optimal_solutions_for_Rubik%27...
The time is still impressive, but this doesn't showcase any real improvements to any technology.
It's kind of misleading to phrase it as the chip solving it, when the focus is on the actuators.
If you want impressive actuators, check out modern pick-and-place machines [1].
https://www.youtube.com/watch?v=EHsZQ1WiojE
edit: here a better impressions of flying probes, but not as fast https://www.youtube.com/watch?v=fjmjYVNuLEE
Bolting the caps to the actuators was the bigger trick anyway. Compared to cages or grippers, dramatically reduced inertia and much stiffer, so less damping required and it's easier to dump energy back into the actuators. I'm half-tempted to call that "cheating", but I don't know what the actual rules are - I doubt that this robot can "put down" or "pick up" the cube in less than a minute or two. The older version had the cube actually soldered in.
At 60 fps, unless you're streaming subframe data you're looking at around 160ms ms per frame, and that's not counting any time for image processing.
(Presumably they could cheat by looking at the cube beforehand, but it sounds like a realtime thing)
More accurately - probably not. It depends how the actuators work and whether they include optical monitoring of the twist.
If so, the solution won't need to monitor the colours, but it will need to make sure the actuators spin the sides accurately.
Otherwise - cube explosion.