pytorch / pytorch/executorch

Backend init configs

Open
#16,569 0 comments 0 reactions 1 assignee View on GitHub

@lucylq is already working on this.

Since Jan 13, 2026.

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

Description

Provide configs to the backend during module init. These configs are local to the method instance, not global backend configurations like what backend options provide today.

Option 1: Extend BackendInitContext

  • Pros; it's attached to the method and passed at init time.
  • Cons; as a user, it can be confusing to understand what belongs in BackendInitContext vs BackendOptions vs NamedDataMap

Option 2: Backend Options

  • Hacky, as these are global backend configs, not attached to a specific method.

Option 3: NamedDataMap

  • Hacky, as NamedDataMap is intended for read-only data (like tensors or data blobs). Overloading it with configs is confusing, especially if it's already being used for the intended purpose.

More discussion here: https://docs.google.com/document/d/1JBNTSBfIHgWk979vtleby67z7WNUN-ClqMEJfMdeczY/edit?tab=t.0

And here: https://fb.workplace.com/groups/pytorch.edge.users/permalink/1957044708499146/

cc @metascroy

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.