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: docs/source/content/installation.md
+5-5Lines changed: 5 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,12 +20,12 @@ Both plugins and data sets can be loaded directly within the application, as doc
20
20
21
21
By default, the application runs embedding models for semantic queries on the CPU, which may result in longer loading times depending on the model, data size, and hardware. GPU acceleration generally reduces these loading times. Below is a list of supported platforms for GPU acceleration:
22
22
23
-
### NVIDIA GPUs
24
-
GPU acceleration supported using CUDA. Requires CUDA 12.x installed. Available on Linux and Windows.
25
-
For installation, see [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads).
23
+
### NVIDIA
24
+
GPU acceleration supported using CUDA. Requires[ CUDA 12.x](https://developer.nvidia.com/cuda-toolkit-archive) and [cuDNN 9.x](https://developer.nvidia.com/cudnn) installed. Available on Linux and Windows.
25
+
For installation, see [CUDA Installation Guide](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html) and [Installing cuDNN Backend](https://docs.nvidia.com/deeplearning/cudnn/installation/latest/windows.html).
0 commit comments