Skip to content

[devtools] Auto-record after-transform graph in ETRecord#17696

Merged
Gasoonjia merged 2 commits intogh/gasoonjia/119/origfrom
gh/gasoonjia/120/orig
Feb 25, 2026
Merged

[devtools] Auto-record after-transform graph in ETRecord#17696
Gasoonjia merged 2 commits intogh/gasoonjia/119/origfrom
gh/gasoonjia/120/orig

Conversation

@pytorchbot
Copy link
Copy Markdown
Collaborator

This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #17434 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/120/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/120/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/gasoonjia/119/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/120/orig
Differential Revision: D93176563
@diff-train-skip-merge

Pull Request resolved: #17434

When `to_edge_transform_and_lower` is called with `generate_etrecord=True` and custom `transform_passes` are applied, the after-transform graph is now automatically recorded in the ETRecord's `graph_map` under the key `"edge_after_transform"`. This enables backends like Qualcomm to use the post-custom-transform graph as the golden reference for numeric gap calculation, while have zero impact for regular exportation.


This is part of the operator-level numeric discrepancy detector project for ExecuTorch Qualcomm backend (#16381).

Design doc: https://docs.google.com/document/d/1GaCHiy9InytOsUrl2BKEgOiP1iKTfpCVdWg6QDh0N2E/edit?tab=t.0#heading=h.fcrpnrtb6cud
ghstack-source-id: 344497034
@exported-using-ghexport

Differential Revision: [D93176563](https://our.internmc.facebook.com/intern/diff/D93176563/)
@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Feb 25, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17696

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

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

@meta-cla meta-cla 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 Feb 25, 2026
…7697)

This PR was created by the merge bot to help merge the original PR into
the main branch.
ghstack PR number: #17459 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/121/base
ghstack PR head:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/121/head
Merge bot PR base:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/120/orig
Merge bot PR head:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/121/orig
Differential Revision:
[D93266779](https://our.internmc.facebook.com/intern/diff/D93266779/)
@diff-train-skip-merge

Co-authored-by: gasoonjia <gasoonjia@icloud.com>
@Gasoonjia Gasoonjia merged commit e57876a into gh/gasoonjia/119/orig Feb 25, 2026
17 of 18 checks passed
@Gasoonjia Gasoonjia deleted the gh/gasoonjia/120/orig branch February 25, 2026 08:05
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.

2 participants