Feature request: CUDA 13 support
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 4.7k
- Forks
- 536
- Avg merge
- 12h 12m
- Merged PRs (30d)
- 4
Description
Please add support for CUDA 13. I have a torch 2.9+cu13 stack with a blackwell dependency. While blackwell works with torch 2.7+ and can work with versions of CUDA supported by the current release here, I'm not in a position to downgrade from 13.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files, tests, or entry points are named in the issue. Start by reviewing the repository's existing CUDA support and compatibility checks, then trace how CUDA versions are selected and validated. Done means CTranslate2 supports the reported torch 2.9+cu13 and Blackwell stack without requiring a downgrade, with the relevant checks passing.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, pytorch
- Domain
- build-system, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100