Update MemoryPlanning Verifier to only assume model has user input if it has at least one tensor input #10617
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
has at least one tensor input MemoryPlanning verifier currently blows up if all the user inputs are prims. This change means its helper function _do_user_inputs_exist returns false if all its inputs are prims. It only returns true if at least one input is a tensor.
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10617
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 36d391d with merge base 7f5229f ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
Didn't find following labels among repository labels: Release notes: exir |
|
@pytorchbot label "release notes: exir" |
pytorch-bot
bot
added
the
release notes: exir
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Outdated suggestions cannot be applied.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.
Fixes #10522
Summary
MemoryPlanning verifier currently blows up if all the user inputs are prims. #10522 suggested:
This PR implements this suggestion, with accompanying unit tests.
_do_user_inputs_existnow returns True if it has at least one tensor input, and False otherwise.Test plan
Added unit tests to
test_memory_planning.pyand ran them withPlease note you must comment out the line 69 from
/pytest.inifor this to work:On my machine, I also had to comment out line 60 from
test_memory_planning.pyfor the test to run without errors.[The tests I wrote aren't dependent on this library.]