You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: RUNNING_ON_GPU.md
+17-19Lines changed: 17 additions & 19 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -29,7 +29,7 @@ tts.SpeakFast("Hello from GPU!", KokoroVoiceManager.GetVoice("af_heart"));
29
29
30
30
For NVIDIA GPUs with CUDA support:
31
31
- 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).
32
-
- 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.
32
+
- Download & install [CUDA Toolkit (v12.x)](https://developer.nvidia.com/cuda-12-4-0-download-archive), and make sure it's in SYSTEM PATH.
33
33
- Download & install [cuDNN](https://developer.nvidia.com/cudnn), and make sure it's in SYSTEM PATH.
34
34
- Restart your IDE/terminal after installation, then, run:
tts.SpeakFast("Hello from GPU!", KokoroVoiceManager.GetVoice("af_heart"));
40
40
```
41
41
42
+
<details>
43
+
<summary> **IF you choose to NOT install CUDA/cuDNN, this is the full list of libraries needed to be loaded** [Click to expand] </summary>
44
+
- cudnn_engines_runtime_compiled64_9.dll <br>
45
+
- cudnn_engines_precompiled64_9.dll <br>
46
+
- cudnn_heuristic64_9.dll <br>
47
+
- cudnn_graph64_9.dll <br>
48
+
- cublasLt64_12.dll <br>
49
+
- cudnn_adv64_9.dll <br>
50
+
- cudnn_ops64_9.dll <br>
51
+
- cublas64_12.dll <br>
52
+
- cudart64_12.dll <br>
53
+
- cufft64_11.dll <br>
54
+
- cudnn64_9.dll <br>
55
+
</details>
56
+
57
+
42
58
43
59
## CoreML
44
60
@@ -65,21 +81,3 @@ It's also possible to receive this error if you have more packages than you shou
65
81
`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.
66
82
67
83
Always reset your IDE/terminal after installing dependencies, to make sure the system path is in sync.
68
-
69
-
70
-
71
-
### Exact list of CUDA / CUDNN libraries nessesary for inference
0 commit comments