Backend data separation test #10734
Merged
Backend data separation test #10734
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Pull Request resolved: #10531 Add backend data separation test with demo ExecutorBackend. Note: ExecutorBackend is a wrapper around a portable PTE file. It doesn't support delegated program-data separation in the sense of tagging tensors as external and placing them into the named data store as such. Rather, this test: 1. Creates a linear PTE file with data removed, using the portable flow. 2. Packages (1) into preprocessed blob as a delegate, using ExecutorBackend. Note: this discards the PTD portion. 3. Re-create the PTD portion via export_program (portable flow again). 4. Runs the delegated ExecutorBackend linear with portable linear.ptd file. Caveat: this means that LinearModule definition in export_program and export_delegated_program must stay in sync, as we get the PTE artifact from export_delegated_program (wrapped in ExecutorBackend), and the PTD artifact from export_program. ghstack-source-id: 282187684 @exported-using-ghexport Differential Revision: [D73679733](https://our.internmc.facebook.com/intern/diff/D73679733/)
lucylq
requested review from
larryliu0820,
kirklandsign,
JacobSzwejbka,
swolchok and
tarun292
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10734
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 2 New Failures, 12 PendingAs of commit c15aa98 with merge base e196b50 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
kirklandsign
approved these changes
May 6, 2025
phaiting
pushed a commit
that referenced
this pull request
May 6, 2025
Pull Request resolved: #10531 Add backend data separation test with demo ExecutorBackend. Note: ExecutorBackend is a wrapper around a portable PTE file. It doesn't support delegated program-data separation in the sense of tagging tensors as external and placing them into the named data store as such. Rather, this test: 1. Creates a linear PTE file with data removed, using the portable flow. 2. Packages (1) into preprocessed blob as a delegate, using ExecutorBackend. Note: this discards the PTD portion. 3. Re-create the PTD portion via export_program (portable flow again). 4. Runs the delegated ExecutorBackend linear with portable linear.ptd file. Caveat: this means that LinearModule definition in export_program and export_delegated_program must stay in sync, as we get the PTE artifact from export_delegated_program (wrapped in ExecutorBackend), and the PTD artifact from export_program. ghstack-source-id: 282187684 @exported-using-ghexport Differential Revision: [D73679733](https://our.internmc.facebook.com/intern/diff/D73679733/) Backend data separation test Add backend data separation test with demo ExecutorBackend. Note: ExecutorBackend is a wrapper around a portable PTE file. It doesn't support delegated program-data separation in the sense of tagging tensors as external and placing them into the named data store as such. Rather, this test: 1. Creates a linear PTE file with data removed, using the portable flow. 2. Packages (1) into preprocessed blob as a delegate, using ExecutorBackend. Note: this discards the PTD portion. 3. Re-create the PTD portion via export_program (portable flow again). 4. Runs the delegated ExecutorBackend linear with portable linear.ptd file. Caveat: this means that LinearModule definition in export_program and export_delegated_program must stay in sync, as we get the PTE artifact from export_delegated_program (wrapped in ExecutorBackend), and the PTD artifact from export_program. Differential Revision: [D73679733](https://our.internmc.facebook.com/intern/diff/D73679733/)
jhelsby
pushed a commit
to jhelsby/executorch
that referenced
this pull request
May 9, 2025
Pull Request resolved: pytorch#10531 Add backend data separation test with demo ExecutorBackend. Note: ExecutorBackend is a wrapper around a portable PTE file. It doesn't support delegated program-data separation in the sense of tagging tensors as external and placing them into the named data store as such. Rather, this test: 1. Creates a linear PTE file with data removed, using the portable flow. 2. Packages (1) into preprocessed blob as a delegate, using ExecutorBackend. Note: this discards the PTD portion. 3. Re-create the PTD portion via export_program (portable flow again). 4. Runs the delegated ExecutorBackend linear with portable linear.ptd file. Caveat: this means that LinearModule definition in export_program and export_delegated_program must stay in sync, as we get the PTE artifact from export_delegated_program (wrapped in ExecutorBackend), and the PTD artifact from export_program. ghstack-source-id: 282187684 @exported-using-ghexport Differential Revision: [D73679733](https://our.internmc.facebook.com/intern/diff/D73679733/) Backend data separation test Add backend data separation test with demo ExecutorBackend. Note: ExecutorBackend is a wrapper around a portable PTE file. It doesn't support delegated program-data separation in the sense of tagging tensors as external and placing them into the named data store as such. Rather, this test: 1. Creates a linear PTE file with data removed, using the portable flow. 2. Packages (1) into preprocessed blob as a delegate, using ExecutorBackend. Note: this discards the PTD portion. 3. Re-create the PTD portion via export_program (portable flow again). 4. Runs the delegated ExecutorBackend linear with portable linear.ptd file. Caveat: this means that LinearModule definition in export_program and export_delegated_program must stay in sync, as we get the PTE artifact from export_delegated_program (wrapped in ExecutorBackend), and the PTD artifact from export_program. Differential Revision: [D73679733](https://our.internmc.facebook.com/intern/diff/D73679733/)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Pull Request resolved: #10531
Add backend data separation test with demo ExecutorBackend.
Note: ExecutorBackend is a wrapper around a portable PTE file. It doesn't support delegated program-data separation in the sense of tagging tensors as external and placing them into the named data store as such. Rather, this test:
Caveat: this means that LinearModule definition in export_program and export_delegated_program must stay in sync, as we get the PTE artifact from export_delegated_program (wrapped in ExecutorBackend), and the PTD artifact from export_program. ghstack-source-id: 282187684
@exported-using-ghexport
Differential Revision: D73679733
Summary
[PLEASE REMOVE] See CONTRIBUTING.md's 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: " label. For a list of available release notes labels, check out CONTRIBUTING.md's 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.