Fix bundled program and plan_execute in pybindings #4595
Merged
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/4595
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 12fe06b with merge base 79c15ef ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D60939315 |
JacobSzwejbka
approved these changes
Aug 9, 2024
|
This pull request was exported from Phabricator. Differential Revision: D60939315 |
dulinriley
force-pushed
the
export-D60939315
branch
from
50c00da to
a314db7
Compare
dulinriley
added a commit
to dulinriley/executorch
that referenced
this pull request
Aug 9, 2024
Summary: Pull Request resolved: pytorch#4595 Bundled programs needed to use the `plan_execute` function on ExecutorchModule because the inputs were previously loaded. Unfortunately this meant that the programs didn't work if they did not have pre-planned outputs (i.e. the caller is supposed to provide the memory). Share code for allocating outputs as necessary between `run_method` and `plan_execute`. Also share code for *returning* those outputs, as there doesn't seem to be a reason to execute the method without getting its output. In order for the output storage to live long enough for the bundled program comparison, add the storages as private data members of `PyModule`. As an improvement in user API, have `verify_result_with_bundled_expected_output` do all of these things at once for the user. Differential Revision: D60939315
Summary: Pull Request resolved: pytorch#4595 Bundled programs needed to use the `plan_execute` function on ExecutorchModule because the inputs were previously loaded. Unfortunately this meant that the programs didn't work if they did not have pre-planned outputs (i.e. the caller is supposed to provide the memory). Share code for allocating outputs as necessary between `run_method` and `plan_execute`. Also share code for *returning* those outputs, as there doesn't seem to be a reason to execute the method without getting its output. In order for the output storage to live long enough for the bundled program comparison, add the storages as private data members of `PyModule`. As an improvement in user API, have `verify_result_with_bundled_expected_output` do all of these things at once for the user. Differential Revision: D60939315
|
This pull request was exported from Phabricator. Differential Revision: D60939315 |
dulinriley
force-pushed
the
export-D60939315
branch
from
a314db7 to
12fe06b
Compare
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.
Summary:
Bundled programs needed to use the
plan_executefunction on ExecutorchModulebecause the inputs were previously loaded. Unfortunately this meant that the
programs didn't work if they did not have pre-planned outputs
(i.e. the caller is supposed to provide the memory).
Share code for allocating outputs as necessary between
run_methodandplan_execute.Also share code for returning those outputs, as there doesn't seem to be a reason to
execute the method without getting its output.
In order for the output storage to live long enough for the bundled program comparison,
add the storages as private data members of
PyModule.Differential Revision: D60939315