AMD dropped ZLUDA funding, the remains were opensourced and it won't ever be a viable option.
For production workloads, I generally agree. It's an unsupported hack with a questionable future, I wouldn't do anything money-making with it.
However, for tinkering and consumer workloads, it already works pretty well. Enough of cuDNN and cuBLAS work to run PyTorch and in turn, Stable Diffusion with https://github.com/lshqqytiger/ZLUDA - there's even a fairly user-friendly setup process already in https://github.com/vladmandic/automatic .
I was able to get a personal non-ML related project working on my AMD card in just a few minutes, which saved me a lot of development time before I then deployed the production workload on NV hardware (this is probably why AMD pulled the plug on the project - it's almost more of a boost to NV than anything else, AMD really need people to be writing code on ROCm to deploy on AMD datacenter hardware).
Not everything is DNNs and tensors...
As for the Stable Diffusion thing, a silly edge case - because MIOpen (and therefore PyTorch-on-ROCm) doesn't work on Windows yet (they're slated to ship it next month, I think).
Sure, but you could use PyTorch for cuBLAS/cuRAND etc type functionality too.
https://github.com/vosen/ZLUDA
The article also mentions exactly this fact.