Architecture Agnostic CUDA artifact
Open
@larryliu0820 is already working on this.
Since Feb 24, 2026.
module: cuda
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
🚀 The feature, motivation and pitch
Currently, you need to create one artifact per CUDA architecture. This puts significant burden on deployment / shipping setups and is a regression compared to TorchScript. Therefore I would like to ask for an architecture-agnostic artifact creation workflow.
Alternatives
No response
Additional context
No response
RFC (Optional)
No response
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.
Assessment
This issue has not been assessed yet.