Skip to content

Add CUDA 13.3 and 13.4 variant support to Inference Runtime settings #265

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

Open
kulbhushanchand wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Add CUDA 13.3 and 13.4 variant support to Inference Runtime settings #265

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b2d7222
Add support for CUDA 13.3 and 13.4 variants
kulbhushanchand Aug 28, 2026
0bd99f7
Add CUDA 13.3 and 13.4 options to InferenceRuntime
kulbhushanchand Aug 28, 2026
1df856f
Merge pull request #2 from kulbhushanchand/patch-1
kulbhushanchand Aug 28, 2026
baf0fc4
Merge pull request #1 from kulbhushanchand/patch-2
kulbhushanchand Aug 28, 2026
a61d553
Potential fix for pull request finding
kulbhushanchand Aug 28, 2026
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
2 changes: 2 additions & 0 deletions src/main/utils/llamacpp.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,6 +165,8 @@ const getAssetPattern = (tag: string, variant: string): { pattern: string; isZip
cpu: `llama-${tag}-bin-win-cpu-${archStr}.zip`,
'cuda-12.4': `llama-${tag}-bin-win-cuda-12.4-x64.zip`,
'cuda-13.1': `llama-${tag}-bin-win-cuda-13.1-x64.zip`,
'cuda-13.3': `llama-${tag}-bin-win-cuda-13.3-x64.zip`, // new
'cuda-13.4': `llama-${tag}-bin-win-cuda-13.4-x64.zip`, // new
vulkan: `llama-${tag}-bin-win-vulkan-x64.zip`
}
const name = variantMap[variant] ?? variantMap.cpu
Expand Down
2 changes: 2 additions & 0 deletions src/renderer/src/lib/components/Main/Settings/InferenceRuntime.svelte
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,8 @@
{ value: 'cpu', label: $i18n.t('settings.inference.variantCPU') },
{ value: 'cuda-12.4', label: 'CUDA 12.4' },
{ value: 'cuda-13.1', label: 'CUDA 13.1' },
{ value: 'cuda-13.3', label: 'CUDA 13.3' },
{ value: 'cuda-13.4', label: 'CUDA 13.4' },
{ value: 'vulkan', label: 'Vulkan' }
]
return [
Expand Down