Pascal was indeed a big jump in efficiency, but that by itself doesn't really reflect the longer term trend. Prior to Pascal efficiency had stalled for a couple of years as GPUs were stuck on a 28nm process for much longer than previous node sizes. This pattern is likely to continue as advancements in fabrication continue to slow down and architectural gains become smaller.

This is my guess. I think that soon we will start to hit limits for single threaded performance so eventually we will just keep adding support for more threads to increase performance

That's only because it's cheaper to build a whole new facility

Uh... people aren't 'building whole new facilities' for their gaming desktops. The new GPUs also have the same rated power consumption.