The state of the art on path rendering, both academic approaches such as Random Access Vector Graphics (Hoppe and Nehab), Massively Parallel Vector Graphics (Ganacim et al) and more practical implementations such as Slug (Lengyel), Pathfinder (Walton) have advanced considerably beyond NV path rendering. I also hope to do considerably better - my approach is most similar to Pathfinder but with more of the expensive CPU operations moved to GPU.

I'd like to humbly suggest that Rasterizer may have extended the state of the art of 2D GPU-accelerated rendering: https://twitter.com/Vector_GL/status/1214507005316128768