feat(cuda): add CUDA 13.3 Support - #141
Open
FerLuisxd wants to merge 1 commit into
Open
Conversation
- Add CUDA 13 runtime library candidates to Python and TypeScript preloading tables - Register cu13 flavor in release wheel index generator - Add dedicated .github/workflows/cuda13-windows.yml workflow targeting CUDA 13.3
Contributor
|
Thank you. I'll take a look. The main concern I have is just like binary bloat |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds support for NVIDIA CUDA 13.3 builds, added a new workflow that would create the new asset, updated some cu12 comments and some involved ts/python binding files.
This should fix #100
Scope
bindings/typescript: Added CUDA 13 runtime probing before falling back to CUDA 12 insrc/cuda.ts.bindings/python-native-cu12: Added CUDA 13 runtime library candidates to_NVIDIA_LIBSin__init__.py.scripts/ci: Registered"cu13"flavor inbuild_wheel_index.pyand updated documentation..github/workflows: Created dedicatedcuda13-windows.yml.AI Assistance
AI assistance (Antigravity IDE) was used to draft the workflow YAML and runtime library lookup tables. I guided the architecture decisions, reviewed all diffs, and checked this by manually updating the gglm and cuda dlls, confirming that it still works.
Validation
Manually tested on Windows with a 5060 TI RTX GPU by loading the CUDA 13.3 compiled
ggml-cuda.dlland CUDA 13.3 runtime DLLs. Verified that CUDA is recognized, and that live transcription still works.