Skip to content

Updated merging logic of AOT to get the corresponding intermediate output #12351

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 1 commit into from
Jul 15, 2025

Conversation

Juntian777
Copy link
Contributor

Summary:
This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Differential Revision: D77956435

@Juntian777 Juntian777 requested a review from Gasoonjia as a code owner July 10, 2025 17:59
Copy link

pytorch-bot bot commented Jul 10, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12351

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

❌ 1 New Failure

As of commit 83d3314 with merge base aa44c06 (image):

NEW FAILURE - The following job has failed:

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 10, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

@Juntian777
Copy link
Contributor Author

@pytorchbot label "release notes: none"

@pytorch-bot pytorch-bot bot added the release notes: none Do not include this in the release notes label Jul 10, 2025
Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 11, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

1 similar comment
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 11, 2025
…tput (pytorch#12351)

Summary:
Pull Request resolved: pytorch#12351

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Differential Revision: D77956435
Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 11, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 11, 2025
…tput (pytorch#12351)

Summary:
Pull Request resolved: pytorch#12351

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Differential Revision: D77956435
Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 11, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 11, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 11, 2025
…tput (pytorch#12351)

Summary:
Pull Request resolved: pytorch#12351

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
@Juntian777 Juntian777 force-pushed the export-D77956435 branch 2 times, most recently from 056ad78 to 5ceca6e Compare July 14, 2025 21:00
Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 14, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 14, 2025
…tput (pytorch#12351)

Summary:
Pull Request resolved: pytorch#12351

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 15, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 15, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 15, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 15, 2025
…tput (pytorch#12351)

Summary:
Pull Request resolved: pytorch#12351

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 15, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 15, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

Juntian777 added a commit to Juntian777/executorch that referenced this pull request Jul 15, 2025
…tput (pytorch#12351)

Summary:

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
…tput (pytorch#12351)

Summary:
Pull Request resolved: pytorch#12351

This PR updated the mapping between AOT and runtime. The runtime_list has a size of 1 because AOT is either an integer or a list of integers with a size of 1, so no merging is needed for runtime_list during the mapping stage. However, AOT may needs to be merged during the mapping stage and the intermediate output should be retained according to the last integer of the corresponding runtime debug_handle tuples. This ensures that the AOT and runtime intermediate outputs match.

Additionally, ensure that the merged AOT debug_handle exactly matches the runtime debug_handle.

Reviewed By: Gasoonjia

Differential Revision: D77956435
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D77956435

@facebook-github-bot facebook-github-bot merged commit 206dcf4 into pytorch:main Jul 15, 2025
98 of 100 checks passed
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. fb-exported release notes: none Do not include this in the release notes
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants