SmolVLM encoder not getting delegated to XNNPack
Open
@GregoryComer is already working on this.
Since Oct 14, 2025.
module: xnnpack
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
🐛 Describe the bug
SmolVLM from Optimum (PR - https://github.com/huggingface/optimum-executorch/pull/163) is not getting fully delegated to XNNPack in the encoder subgraph.
The pte dump shows this - P1983888427, you can see undelegated addmms still in the encoder.
Printed EP right after torch.export: P1984977202
Printed EP right after to_edge_transform_and_lower: P1985017274
Versions
N/A
cc @GregoryComer @digantdesai @cbilgin @mergennachin
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.