-
Notifications
You must be signed in to change notification settings - Fork 308
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
Unable to run on Mac : Torch not compiled with CUDA enabled #74
Comments
I think its impossible to run on Mac. I have m3 max too! And 48 gb version. #71 I've tried multuply variants, used even chatgpt. Nothing helped. I was fucking with this whole 12 hours |
This comment was marked as spam.
This comment was marked as spam.
Hello |
@paras-genmo can you ban @FurkanGozukara from here since he's just showing up to spam his patreon |
Hi, I tried to run Mochi on a Mac from bobo-fun, but encountered a bug where Mochi produces a completely black screen video. I discovered that the issue lies with the 'out_cond' and 'out_uncond' variables in the model_fn() function, which consistently display as tensor([[[[[nan, nan, nan, ..., nan, nan, nan]...)... |
was able to get some output with mps that wasn't totally blank, but still looks like mostly noise |
Hi
Newbie here. I am trying to run Mochi on my Mac. Getting the below error:
I tried uninstalling Torch and installing the nightly version, but still getting the same error. I looked at the code and appears that there's tight coupling to Torch-CUDA.
Machine config:
I tried running Mochi standalone as well as thro' ComfyUI. Please let me know if there's any way I can run the model on Mac.
Thanks
The text was updated successfully, but these errors were encountered: