-
Notifications
You must be signed in to change notification settings - Fork 1.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Idea: Implement DirectML to add partial support for AMD GPU's #432
Comments
I would love to see AMD support I have a RX 6600 it would cut my process time in half. I have a I7 3770 with 24gb DDR3 ram using model MDX-Net Inst 3 it takes 3 to 6 min to process a track. |
Any update? @Anjok07 |
lmao I have an Nvidia GPU now even though I have no need for this anymore I would still love to see something like this added soon |
seems like there's an experimental branch for amd gpu's now |
I added a branch for AMD GPU support using OpenCL. I was able to get MDX-Net & VR Arch models to run. I'm still working out some kinks though |
thank you for your work! I no longer have a need for this as I upgraded to an rtx 3060 now but I would still appreciate if you get it to work |
Thank you so much!! |
someone else made a fork of this code and implemented this successfully although with some drawbacks (like demucs completely not functioning and mdx-net being buggy but im sure these issues can be fixed)
https://github.com/Aloereed/ultimatevocalremovergui-directml
it would be really nice to finally have support for AMD GPU's since running off of cpu is painfully slow for most people (52 minutes for 5 minute file 😭 ) and i hope this issue gets noticed and gets successfully added to the main branch of this project.
thank you to the developers and all of the contributors for making this great GUI and making a lot of peoples lives way easier
The text was updated successfully, but these errors were encountered: