Skip to content

Made RUNNING_ON_GPU.md point to CUDA 12.4 #45

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.

Sign up for GitHub

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

Merged
Lyrcaxis merged 2 commits into from
Aug 24, 2025
Merged

Made RUNNING_ON_GPU.md point to CUDA 12.4 #45

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
65c2772
Update RUNNING_ON_GPU.md
Onkitova Aug 22, 2025
d577d54
Update RUNNING_ON_GPU.md
Onkitova Aug 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion RUNNING_ON_GPU.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ tts.SpeakFast("Hello from GPU!", KokoroVoiceManager.GetVoice("af_heart"));

For NVIDIA GPUs with CUDA support:
- Choose either [KokoroSharp.GPU.Windows](https://www.nuget.org/packages/KokoroSharp.GPU.Windows), [KokoroSharp.GPU.Linux](https://www.nuget.org/packages/KokoroSharp.GPU.Linux), or [KokoroSharp.GPU](https://www.nuget.org/packages/KokoroSharp.GPU).
- Download & install [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit), and make sure it's in SYSTEM PATH.
- Download & install [CUDA Toolkit (v12.x)](https://developer.nvidia.com/cuda-12-4-0-download-archive), and make sure it's in SYSTEM PATH or put the libraries next to your compiled executable.
- Download & install [cuDNN](https://developer.nvidia.com/cudnn), and make sure it's in SYSTEM PATH.
- Restart your IDE/terminal after installation, then, run:
```cs
Expand Down Expand Up @@ -65,3 +65,16 @@ It's also possible to receive this error if you have more packages than you shou
`DllNotFoundException` means you have no runtime AT ALL. For plug & play support (still fast), use the [KokoroSharp.CPU](https://www.nuget.org/packages/KokoroSharp.CPU) package.

Always reset your IDE/terminal after installing dependencies, to make sure the system path is in sync.

### Exact list of CUDA / CUDNN libraries nessesary for inference
- cudnn_engines_runtime_compiled64_9.dll
- cudnn_engines_precompiled64_9.dll
- cudnn_heuristic64_9.dll
- cudnn_graph64_9.dll
- cublasLt64_12.dll
- cudnn_adv64_9.dll
- cudnn_ops64_9.dll
- cublas64_12.dll
- cudart64_12.dll
- cufft64_11.dll
- cudnn64_9.dll

@Lyrcaxis Lyrcaxis Aug 24, 2025

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can this be made collapsable somehow? Also, is this tested?

@Onkitova Onkitova Aug 24, 2025

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can this be made collapsable somehow?

Done.

Also, is this tested?

This is a bare minimum that allows to run cuda-inference in such a "portable" env.
Btw, do you have any warnings like this when running gpu-powered generation on your side? I have 4070, just one version (12.9) of cuda installed atm and -- outside of this weird cuda-blindness -- my system feels pretty stable.

Screenshot 2025-08-24 215024

@Lyrcaxis Lyrcaxis Aug 24, 2025

Copy link
Copy Markdown
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

That is super cool, great find!

I was wanting to poke at auto-library resolvement somehow for an App I'm making using KokoroSharp, so it's very useful info. Thanks!