RVC-Project
Blackwell version with cuda 12.8 please!
Hello!
Some of us have 50xx cards that use Blackwell/sm_120 architecture and we can't use RVC until this is fixed :(
What we need
-the embedded python/pytorch to use the 'nightly' build from
https://pytorch.org/ pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128
Could someone please fork it or fix it using this pytorch?
You can first install the nightly version of torch yourself. First, uninstall the pre-installed version.
.\runtime\python.exe -m pip uninstall torch torchaudio torchvision -y
Then install the torchcu128 version.
.\runtime\python.exe -m pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128
WARNING: The script isympy.exe is installed in .RVC1006Nvidia\runtime\Scripts' which is not on PATH. Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location. WARNING: The scripts torchfrtrace.exe and torchrun.exe are installed in .\RVC1006Nvidia\runtime\Scripts' which is not on PATH. Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location. ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. torch-directml 0.2.0.dev230426 requires torch==2.0.0, but you have torch 2.8.0.dev20250323+cu128 which is incompatible. torch-directml 0.2.0.dev230426 requires torchvision==0.15.1, but you have torchvision 0.22.0.dev20250324+cu128 which is incompatible. xformers 0.0.19 requires torch==2.0.0, but you have torch 2.8.0.dev20250323+cu128 which is incompatible.
Any thoughts on this?
on load it says
WARNING | xformers | WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for: PyTorch 2.0.0+cu118 with CUDA 1108 (you have 2.8.0.dev20250323+cu128) Python 3.9.13 (you have 3.9.13) Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers) Memory-efficient attention, SwiGLU, sparse and more won't be available. Set XFORMERS_MORE_DETAILS=1 for more details 2025-03-24 09:25:22 | INFO | configs.config | Found GPU NVIDIA GeForce RTX 5080 is_half:True, device:cuda:0
anyone here 🐙
You can try Applio. It has 50xx fix, if you install it manually. Just download repo and start install.bat
anyone here 🐙
Did you figure it out? Did you try Applio or did you get RVC to work with your new GPU? Thanks!
not yet, i like the rvc interface 100% better than applio , but thank you trymydmy for the suggestion
not yet, i like the rvc interface 100% better than applio , but thank you trymydmy for the suggestion
Yeah, I'm used to RVC too. But I had an older version of it I'm guessing because I just installed Applio and there are a couple things that are cool. Might be in the latest RVC too.
someone had a fix, did something now getting this xformers error
WARNING | xformers | WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for: PyTorch 2.0.0+cu118 with CUDA 1108 (you have 2.7.0+cu128) Python 3.9.13 (you have 3.9.13) Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers) Memory-efficient attention, SwiGLU, sparse and more won't be available. Set XFORMERS_MORE_DETAILS=1 for more details 2025-07-27 18:12:57 | INFO | configs.config | Found GPU NVIDIA GeForce RTX 5090 is_half:True, device:cuda:0 2025-07-27 18:12:58 | INFO | main | Use Language: en_US Running on local URL: http://0.0.0.0:7897
its almost aug and no one seems to care about 50 series ,its still working ,installed nightly and it detected rtx 5080 but still some pytorch related errors
Surely some python savant will take pity on us 50xx'rs and bless us with a fork or update!
Hi guys! I tried everything to run it on rtx 5070 and no result. I am a BIG fan of your project and I am very used to it. it was one of the reasons I got a stronger card. Can we get a fix for these new cards in the near future?
Hi guys! I tried everything to run it on rtx 5070 and no result. I am a BIG fan of your project and I am very used to it. it was one of the reasons I got a stronger card. Can we get a fix for these new cards in the near future?
Try Apolio
I used applio but the conversion quality was top notch on mangio rvc which I was using on a 4070ti , The quality i get with applio is low and not usable especially in music production . kindly help fix this rvc compatibility issue or let me know if i am doing something wrong with Applio. i got an RTX 5080
