pytorch / pytorch/executorch

SmolVLM encoder not getting delegated to XNNPack

Open
#14,987 9 comments 0 reactions 1 assignee View on GitHub

@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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.