pytorch / pytorch/executorch

Build runner in cmake in 1 line

Open
#11,526 0 comments 0 reactions 1 assignee View on GitHub

@larryliu0820 is already working on this.

Since Jun 10, 2025.

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

Description

🚀 The feature, motivation and pitch

Currently we build ExecuTorch libraries and install them using 1 cmake command, and then build llm runner using the libraries in another cmake command.

This approach have some issues.

  1. It's very error prone because it relies on executorch-config.cmake to be able to configure the libraries correctly.
  2. It's a bad ux

Merging them into 1 cmake command runs into this issue: conflicting memory target in abseil and xnnpack. One solution is to build tokenizers (depends on abseil) as an external project.

Alternatives

No response

Additional context

No response

RFC (Optional)

No response

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.