Skip to content

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

Open
kulbhushanchand wants to merge 5 commits into
open-webui:mainfrom
kulbhushanchand:main
Open

Add CUDA 13.3 and 13.4 variant support to Inference Runtime settings#265
kulbhushanchand wants to merge 5 commits into
open-webui:mainfrom
kulbhushanchand:main

Conversation

@kulbhushanchand

Copy link
Copy Markdown

Description

The Inference Runtime settings only offered CUDA 12.4 and CUDA 13.1 as
llama.cpp variants. Recent llama.cpp releases (e.g. b10666) ship CUDA 13.3
and 13.4 Windows builds, so users on newer GPUs/drivers had no way to select
them and would fall back to CPU-only inference.

This PR adds cuda-13.3 and cuda-13.4 as additional pinned variant
options, alongside the existing cuda-12.4 and cuda-13.1 — same pattern,
same exact-match asset resolution already used in getAssetPattern().
Nothing existing was changed or removed, so pinning an older release tag
(via the Release Version field) that only shipped cuda-13.1 still resolves
correctly.

Related Issues

Fixes #264


Contributor License Agreement

Note

Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in.

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Pull request overview

Adds additional CUDA variant choices to the Inference Runtime settings so Windows users can select llama.cpp release assets built for CUDA 13.3 and 13.4 (in addition to existing CUDA 12.4 and 13.1 options), aligning the UI options with newer upstream release artifacts and addressing #264.

Changes:

  • Expose cuda-13.3 and cuda-13.4 in the Windows inference variant dropdown.
  • Extend Windows asset name resolution to match cuda-13.3 / cuda-13.4 zip naming.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File Description
src/renderer/src/lib/components/Main/Settings/InferenceRuntime.svelte Adds CUDA 13.3/13.4 entries to the Windows variant selector options.
src/main/utils/llamacpp.ts Adds CUDA 13.3/13.4 to the Windows variantMap used for exact asset name resolution.

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

Comment thread src/renderer/src/lib/components/Main/Settings/InferenceRuntime.svelte Outdated
Comment thread src/main/utils/llamacpp.ts
Removed inline "// new" markers

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

bug/feat: Please provide Cuda 13.3 support in the settings drop down menu

2 participants