AOTI as a delegate for CUDA, ROCm and MPS support
Open
@larryliu0820 is already working on this.
Since Aug 14, 2025.
module: rocm
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
🚀 The feature, motivation and pitch
Prototype the idea of using AOTI as a delegate in ExecuTorch, figure out the e2e flow to export and run.
Target is to use it on a real world model (such as MV3 or even LLM).
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.