[devtools] Auto-record after-transform graph in ETRecord by Gasoonjia · Pull Request #17434 · pytorch/executorch

Gasoonjia · 2026-02-13T02:03:50Z

Stack from ghstack (oldest at bottom):

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

Differential Revision: D93176563

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 Differential Revision: [D93176563](https://our.internmc.facebook.com/intern/diff/D93176563/) [ghstack-poisoned]

pytorch-bot · 2026-02-13T02:03:54Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17434

📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 81b8520 with merge base 63f9724 ():

NEW FAILURE - The following job has failed:

pull / unittest-arm-backend-with-no-deps (test_pytest_ops_tosa) / linux-job (gh)
RuntimeError: Command docker exec -t 3046b40fb7b12cdcd269fd97d76a2fd629ac56fa3cfbc39c3de17854faab3588 /exec failed with exit code 1

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

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 Differential Revision: [D93176563](https://our.internmc.facebook.com/intern/diff/D93176563/) ghstack-source-id: 340959332 Pull Request resolved: #17434

github-actions · 2026-02-13T02:04:44Z

This PR needs a `release notes:` label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

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 Differential Revision: [D93176563](https://our.internmc.facebook.com/intern/diff/D93176563/) [ghstack-poisoned]

winskuo-quic

LGTM.
Thanks for having this PR. This allows us to retrieve valuable information for graphs with edge passes while not break the BC.

winskuo-quic · 2026-02-24T05:12:34Z

+        # Verify that 'edge_after_transform' is NOT in graph_map
+        if etrecord.graph_map is not None:
+            self.assertNotIn(
+                "edge_after_transform/forward",


Just curious.
I am studying the logic of the graph_map naming:

executorch/devtools/etrecord/_etrecord.py

Line 651 in 43ee3f9

if isinstance(export_module, ExirExportedProgram):

.
This hardcoded forward is appened because an edge_after_transform could possibly consist of multimethods?

yes your are right. That's placeholder for multimethods supported.
Now we only support single forward name but in the future we will support multiple methods in the same program.

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 Differential Revision: [D93176563](https://our.internmc.facebook.com/intern/diff/D93176563/) [ghstack-poisoned]

larryliu0820

Review automatically exported from Phabricator review in Meta.

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 Differential Revision: [D93176563](https://our.internmc.facebook.com/intern/diff/D93176563/) [ghstack-poisoned]

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #17459 * #17434 * __->__ #17433 This change extends NumericalComparatorBase to support custom preprocessing before numeric gap calculation, enabling backends like Qualcomm to apply necessary tensor transformations (e.g., dequantization, layout conversion) before comparison. Key changes: - Extended NumericalComparatorBase with: - `__init__(inspector)` to store optional Inspector reference for accessing graph metadata - `preprocessing(mapping)` method that can be overridden for custom tensor transformations (default: identity) - `element_compare(a, b)` abstract method for element-level tensor comparison - `compare(mapping, ...)` method that orchestrates the full pipeline: preprocessing → element-wise compare → aggregate to DataFrame 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 Differential Revision: [D93169813](https://our.internmc.facebook.com/intern/diff/D93169813/)

…7459) Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * __->__ #17459 * #17434 * #17433 This change adds a `reference_graph` parameter to the `calculate_numeric_gap` API, allowing users to explicitly select which graph to use as the golden reference for numeric gap calculation, which enables backends like Qualcomm to use the post-custom-transform graph as the golden reference for numeric gap calculation. 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 Differential Revision: [D93266779](https://our.internmc.facebook.com/intern/diff/D93266779/)

@Gasoonjia

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](https://our.internmc.facebook.com/intern/diff/D93176563/) @diff-train-skip-merge --------- Co-authored-by: gasoonjia <gasoonjia@icloud.com>

Gasoonjia requested review from JacobSzwejbka and larryliu0820 as code owners February 13, 2026 02:03

Gasoonjia mentioned this pull request Feb 13, 2026

[devtools] Add preprocessing support to NumericalComparatorBase #17433

Merged

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 13, 2026

meta-codesync Bot added fb-exported meta-exported labels Feb 13, 2026

Gasoonjia mentioned this pull request Feb 13, 2026

[devtools] Add reference_graph parameter to calculate_numeric_gap #17459

Merged

winskuo-quic approved these changes Feb 24, 2026

View reviewed changes

winskuo-quic reviewed Feb 24, 2026

View reviewed changes

larryliu0820 approved these changes Feb 24, 2026

View reviewed changes

Gasoonjia added 2 commits February 24, 2026 16:10

Gasoonjia merged commit fe2628e into gh/gasoonjia/120/base Feb 25, 2026
202 of 203 checks passed

Gasoonjia deleted the gh/gasoonjia/120/head branch February 25, 2026 08:02

Gasoonjia temporarily deployed to cherry-pick-bot February 25, 2026 08:02 — with GitHub Actions Inactive

pytorchbot mentioned this pull request Feb 25, 2026

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

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[devtools] Auto-record after-transform graph in ETRecord#17434

[devtools] Auto-record after-transform graph in ETRecord#17434
Gasoonjia merged 6 commits intogh/gasoonjia/120/basefrom
gh/gasoonjia/120/head

Gasoonjia commented Feb 13, 2026 •

edited

Loading

Uh oh!

pytorch-bot Bot commented Feb 13, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Feb 13, 2026

Uh oh!

winskuo-quic left a comment

Uh oh!

winskuo-quic Feb 24, 2026

Uh oh!

Gasoonjia Feb 24, 2026

Uh oh!

larryliu0820 left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

Gasoonjia commented Feb 13, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot Bot commented Feb 13, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17434

❌ 1 New Failure

Uh oh!

github-actions Bot commented Feb 13, 2026

This PR needs a release notes: label

Uh oh!

winskuo-quic left a comment

Choose a reason for hiding this comment

Uh oh!

winskuo-quic Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

Gasoonjia Feb 24, 2026

Choose a reason for hiding this comment

Uh oh!

larryliu0820 left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Gasoonjia commented Feb 13, 2026 •

edited

Loading

pytorch-bot Bot commented Feb 13, 2026 •

edited

Loading

This PR needs a `release notes:` label