Skip to content

make operator name consistent before and after serde #12877

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 29, 2025

Conversation

pytorchbot
Copy link
Collaborator

This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #12531 by @Gasoonjia
^ Please use this as the source of truth for the PR details, comments, and reviews
ghstack PR base: https://github.com/pytorch/executorch/tree/gh/gasoonjia/24/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/24/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/gasoonjia/23/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/24/orig
@diff-train-skip-merge

Pull Request resolved: #12462

We need to use the from_node informaton in deserialzied exported graph for operator tracing in et.inspector.  this diff updates the serizalier to support serde from_node info.
ghstack-source-id: 298666561

Differential Revision: [D78293986](https://our.internmc.facebook.com/intern/diff/D78293986/)
Pull Request resolved: #12531


Node name consistency is important for et because we need to trace the node flow by using node name + graph id + from_node info in the deserialized graph in inspector.

Currently we can not have a consistency experience because we didn't record node name as part of schema, but instead, leverging the output info, which didn't record the node name for multiple output node.

This diff makes node name as part of schema to ensure the consistency. Also create tests for coverage.
ghstack-source-id: 298666560

Differential Revision: [D78380855](https://our.internmc.facebook.com/intern/diff/D78380855/)
Copy link

pytorch-bot bot commented Jul 26, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12877

Note: Links to docs will display an error until the docs builds have been completed.

✅ You can merge normally! (1 Unrelated Failure)

As of commit 49bb08a with merge base e44da93 (image):

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jul 26, 2025
Base automatically changed from gh/gasoonjia/23/orig to main July 28, 2025 21:54
@kirklandsign kirklandsign requested a review from Gasoonjia as a code owner July 28, 2025 21:54
@kirklandsign kirklandsign merged commit fead7c7 into main Jul 29, 2025
97 of 98 checks passed
@kirklandsign kirklandsign deleted the gh/gasoonjia/24/orig branch July 29, 2025 05:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants