Hi,
If you need to use TVAI this year, then I wouldn’t recommend buying a RTX 50X0 card for that …
There are four reasons behind why:
All Topaz products rely on super-ancient TensorRT versions. Those versions simply do not support the Blackwell architecture. Revamping all their software to a modern TensorRT version is a Massive undertaking.
TensorRT support for Blackwell requires CUDA 12.8+. IIRC Topaz is still on CUDA 11.8, so again, a massive upgrade headache for them.
nVidia still has driver issues to flesh out, so at this very moment the card is finicky. PyTorch isn’t even running on CUDA 12.8, and that’s what most everyone is using to build and manage their models (Including Topaz I assume).
Without TensorRT support, the additional ~30% capacity of the 50-cards are wasted. The massive bandwidth can make up for some of it, but not all.
Oh my God, can this be true?
We buy expensive software (TOPAZ) and expensive graphics cards,
and they don't work together?
I'm currently running a 4K file
-> upscale to 5K (for processing reserve in DaVinci) with IRIS.
(REHA creates too many artifacts in faces/people)
And I'm currently at 65% CPU (i9 11900, 32GB 4600MT RAM)
and 55% GPU (RTX 5080) utilization!
It's running at 1.7 fps,
and both the GPU and CPU have 'free time'...
... I can't believe it...
TOPAZ should indicate which card generation
it's optimized for in the model descriptions
in the GUI fly-out menu!
In general, I've noticed that the TOPAZ models
exhibit very different levels of hardware utilization.
For example, with Starlight Mini:
I have 100% GPU utilization...?
(only one time used in a 1080 project)
Sincerely seifenchef
