HF demo errors with "CUDA driver version is insufficient for CUDA runtime version"

[pierow2k]

I love the project and made some really creative posters shortly after the Hugging Face demo became available.

Today while trying to use the HF demo, I received an error in the logs:

❌ Generation failed: CUDA error: CUDA driver version is insufficient for CUDA runtime version
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Device-side assertions were explicitly omitted for this error check; the error probably arose while initializing the DSA handlers.

Any chance that you can correct the CUDA version in the demo?