Commandline arg for disabling "torch.backends.cudnn.benchmark"

[sarahhemail]

Is there an existing issue for this?

• I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

'torch.backends.cudnn.benchmark = True' in devices.py can cause inconsistent results when re-launching the webUI.
(as described in https://pytorch.org/docs/stable/notes/randomness.html)

PNGinfo > txt2img can fail to produce a identical result. Smaller, uncomplicated promts have low chance to fail, complex promts, especially if they exceed token limit or have high emphasis are nearly impossible to reproduce 2nd time.

Integrate a command line arg to disable the benchmarking backend.

Proposed workflow

1. Go to ....
2. Press ....
3. ...

Additional information

No response

[vladmandic]

if you look at devices.py, you'll see that cudnn.benchmark is NOT enabled for all, its enabled for a very specific HW only and for a reason (due to bug where those specific old cards falsy report no fp16 ops are possible). are you having that exact HW and still want to disable it?

[sarahhemail]

I already did disable it in the .py.
Though, it was the case for me causing non-deterministic behaviour (gtx 2080 super) upon relaunching the web ui. That I'm 100% sure off.

Thats bad if I want to XYZ re- sample a prevoius image for post processing reasons.

And since hardly anyone seems to be aware of that, I thouht it might be good idea to add a command line arg to disable it for sure.

[catboxanon]

Closing this in favor of #12879 because it's actually a bug (I have two GPUs installed and the cuDNN check looks for anything with a compute cabability of 7.5). You are correct it shouldn't apply to the 20XX series either though.