I did took a native c++ approach when writing a relational transformers engine (RelativeDB). My journey was pytorch -> c++ -> Triton (lang). While C++ was more performant than Triton, I couldn't afford to optimize on every gpu. I just accepted the ~15% throughput loss for my cloud service, which honestly wasn't bad for the amount of flexibility I got out of it.

But the cpp port of vllm looks great, that'd be great if you'll maintain that. I hit the same limitations with vllm.