Add support for checking more than one output from delegate in numerical comparator #13722

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.

Sign up for GitHub

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

Jump to bottom

Merged

facebook-github-bot merged 1 commit into pytorch:main from kimishpatel:export-D80272038

Sep 5, 2025

Contributor

kimishpatel commented Aug 27, 2025

Summary:
We add

num outputs produced by each instruction as separate info in etrecord
in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Differential Revision: D80272038

kimishpatel requested review from Gasoonjia, JacobSzwejbka and larryliu0820 as code owners

August 27, 2025 03:30

pytorch-bot bot commented Aug 27, 2025 •

edited

Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13722

📄 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, 1 Unrelated Failure

As of commit effd802 with merge base c5ff74c ():

NEW FAILURE - The following job has failed:

Build documentation / build (buck2) / Build doc (gh)
At least one of the pre-conditions you specified did not hold

FLAKY - The following job failed but was likely due to flakiness present on trunk:

pull / test-models-linux-basic (mv3, xnnpack-quantization-delegation, cmake, linux.2xlarge, executorch-u... / linux-job (gh) (detected as infra flaky with no log or failing log classifier)

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

meta-cla bot added the CLA Signed label

Contributor

facebook-github-bot commented Aug 27, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

facebook-github-bot added the fb-exported label

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

2d4c6be

…cal comparator (pytorch#13722)

Summary:

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Differential Revision: D80272038

kimishpatel force-pushed the export-D80272038 branch from 60d8f65 to 2d4c6be Compare

August 27, 2025 14:05

Contributor

facebook-github-bot commented Aug 27, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

ce5d37b

…cal comparator (pytorch#13722)

Summary:
Pull Request resolved: pytorch#13722

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Differential Revision: D80272038

kimishpatel force-pushed the export-D80272038 branch from 2d4c6be to ce5d37b Compare

August 27, 2025 14:09

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

1f9ff16

…cal comparator (pytorch#13722)

Summary:

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Differential Revision: D80272038

kimishpatel force-pushed the export-D80272038 branch from ce5d37b to 1f9ff16 Compare

August 27, 2025 14:25

Contributor

facebook-github-bot commented Aug 27, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

Gasoonjia approved these changes

View reviewed changes

kimishpatel force-pushed the export-D80272038 branch from 1f9ff16 to d85f8e9 Compare

August 28, 2025 00:59

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

d85f8e9

…cal comparator (pytorch#13722)

Summary:

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Reviewed By: Gasoonjia

Differential Revision: D80272038

Contributor

facebook-github-bot commented Aug 28, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

9328dfe

…cal comparator (pytorch#13722)

Summary:

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Reviewed By: Gasoonjia

Differential Revision: D80272038

kimishpatel force-pushed the export-D80272038 branch from d85f8e9 to 9328dfe Compare

August 28, 2025 14:41

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

b4f9073

…cal comparator (pytorch#13722)

Summary:

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Reviewed By: Gasoonjia

Differential Revision: D80272038

kimishpatel force-pushed the export-D80272038 branch from 9328dfe to b4f9073 Compare

August 28, 2025 14:41

Contributor

facebook-github-bot commented Aug 28, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

1 similar comment

Contributor

facebook-github-bot commented Aug 28, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

b231e0c

…cal comparator (pytorch#13722)

Summary:
Pull Request resolved: pytorch#13722

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Reviewed By: Gasoonjia

Differential Revision: D80272038

kimishpatel force-pushed the export-D80272038 branch from b4f9073 to b231e0c Compare

August 28, 2025 14:44

kimishpatel added the release notes: devtools label

kimishpatel force-pushed the export-D80272038 branch from b231e0c to d774354 Compare

August 29, 2025 15:27

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

d774354

…cal comparator (pytorch#13722)

Summary:

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Reviewed By: Gasoonjia

Differential Revision: D80272038

Contributor

facebook-github-bot commented Aug 29, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

kimishpatel force-pushed the export-D80272038 branch from d774354 to ecd0e41 Compare

September 2, 2025 17:42

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

ecd0e41

…cal comparator (pytorch#13722)

Summary:

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Reviewed By: Gasoonjia

Differential Revision: D80272038

Contributor

facebook-github-bot commented Sep 2, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

kimishpatel force-pushed the export-D80272038 branch from ecd0e41 to 09dd845 Compare

September 3, 2025 00:33

kimishpatel requested review from jackzhxng and lucylq as code owners

September 3, 2025 00:33

kimishpatel added a commit to kimishpatel/executorch-1 that referenced this pull request


          Add support for checking more than one output from delegate in numeri…

09dd845

…cal comparator (pytorch#13722)

Summary:

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Reviewed By: Gasoonjia

Differential Revision: D80272038

Contributor

facebook-github-bot commented Sep 3, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

kimishpatel added a commit that referenced this pull request


          Adjust atol/rtol for ring attention's quantized kv cache test

9192afd

Summary:
In another PR, #13722, for
whatever reason, this test was failing. Adjusting the margin here since
I have seen this fail before on trunk but somehow it got resolved. So
there is some level of flakiness particularly around quantized kv cache
+ ring attention

Test Plan:
CI

Reviewers:

Subscribers:

Tasks:

Tags:

kimishpatel mentioned this pull request

Adjust atol/rtol for ring attention's quantized kv cache test #13909

Merged

kimishpatel added a commit that referenced this pull request


          Adjust atol/rtol for ring attention's quantized kv cache test

b9b28e0

Summary:
In another PR, #13722, for
whatever reason, this test was failing. Adjusting the margin here since
I have seen this fail before on trunk but somehow it got resolved. So
there is some level of flakiness particularly around quantized kv cache
+ ring attention

Test Plan:
CI

Reviewers:

Subscribers:

Tasks:

Tags:

kimishpatel added a commit that referenced this pull request


          Adjust atol/rtol for ring attention's quantized kv cache test (#13909)

76a8906

Summary:
In another PR, #13722, for
whatever reason, this test was failing. Adjusting the margin here since
I have seen this fail before on trunk but somehow it got resolved. So
there is some level of flakiness particularly around quantized kv cache
+ ring attention

Test Plan:
CI

Reviewers:

Subscribers:

Tasks:

Tags:

### Summary
[PLEASE REMOVE] See [CONTRIBUTING.md's Pull
Requests](https://github.com/pytorch/executorch/blob/main/CONTRIBUTING.md#pull-requests)
for ExecuTorch PR guidelines.

[PLEASE REMOVE] If this PR closes an issue, please add a `Fixes
#<issue-id>` line.

[PLEASE REMOVE] If this PR introduces a fix or feature that should be
the upcoming release notes, please add a "Release notes: <area>" label.
For a list of available release notes labels, check out
[CONTRIBUTING.md's Pull
Requests](https://github.com/pytorch/executorch/blob/main/CONTRIBUTING.md#pull-requests).

### Test plan
[PLEASE REMOVE] How did you test this PR? Please write down any manual
commands you used and note down tests that you have written if
applicable.


          Add support for checking more than one output from delegate in numeri…

effd802

…cal comparator (pytorch#13722)

Summary:

We add
- num outputs produced by each instruction as separate info in etrecord
- in numerical debugger, we check how many outputs are generated and for each output we find corresponding debug handle and use that to find corresponding tensor in AOT

Reviewed By: Gasoonjia

Differential Revision: D80272038

kimishpatel force-pushed the export-D80272038 branch from 09dd845 to effd802 Compare

September 4, 2025 18:08

Contributor

facebook-github-bot commented Sep 4, 2025

This pull request was exported from Phabricator. Differential Revision: D80272038

facebook-github-bot merged commit 09a2e88 into pytorch:main

113 of 118 checks passed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

Gasoonjia Gasoonjia approved these changes

JacobSzwejbka Awaiting requested review from JacobSzwejbka JacobSzwejbka is a code owner

larryliu0820 Awaiting requested review from larryliu0820 larryliu0820 is a code owner

lucylq Awaiting requested review from lucylq

jackzhxng Awaiting requested review from jackzhxng

Labels

CLA Signed fb-exported release notes: devtools