Add CUDA 13.3 and 13.4 variant support to Inference Runtime settings - #265
Open
kulbhushanchand wants to merge 5 commits into
Open
Add CUDA 13.3 and 13.4 variant support to Inference Runtime settings#265kulbhushanchand wants to merge 5 commits into
kulbhushanchand wants to merge 5 commits into
Conversation
For the bug/feat at open-webui#264
For the bug/feat at open-webui#264
Add support for CUDA 13.3 and 13.4 variants
Add CUDA 13.3 and 13.4 options to InferenceRuntime
There was a problem hiding this comment.
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-13.3andcuda-13.4in the Windows inference variant dropdown. - Extend Windows asset name resolution to match
cuda-13.3/cuda-13.4zip 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.
Removed inline "// new" markers Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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-13.3andcuda-13.4as additional pinned variantoptions, alongside the existing
cuda-12.4andcuda-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-13.1still resolvescorrectly.
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.