pytorch / pytorch/executorch

iOS Llama demo app segfaults if the tokenizer file is malformed

Open
#10,879 0 comments 0 reactions 1 assignee View on GitHub

@larryliu0820 is already working on this.

Since May 14, 2025.

Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

🐛 Describe the bug

For example, this happens if you use stories110M with the tokenizer.bin in the llama2.c repo instead of converting it from tokenizer.model with our tools. We should handle malformed input gracefully.

Versions

main

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.