pytorch / pytorch/executorch

Handle comingling of mutable and constant weights in flattensor .ptd

Open
#7,633 0 comments 1 reaction 1 assignee View on GitHub

@JacobSzwejbka is already working on this.

Since Jan 13, 2025.

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

Description

🚀 The feature, motivation and pitch

These will need to be serialized in 2 separate segments. Currently we just serialize all external tensors in the same segment which will cause memory issues down the line if we start having configurations that want to have both in the same .ptd

Alternatives

No response

Additional context

No response

RFC (Optional)

No response

cc @angelayi

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.