[backend_api] Delete partitioner tags after lowering #9435
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
There was a slight bug i found when lowering with: XnnpackDynamicallyQuantizedPartitioner --> XnnpackPartitioner. The issue arrises because the second time we partition, delegation tags from the previous partitioner still exist. Specifically they exist on the getitem node because the metadata was propagated. See: https://github.com/pytorch/pytorch/blob/main/torch/fx/passes/utils/fuser_utils.py#L235 Since the getitem nodes created in by the XnnpackDynamicallyQuantizedPartitioner still have the delegation tags, they sneak into partitions from XnnpackPartitioner. This shouldn't happen because delegation tags from previous Partitioner should not exist after the previous lowering. We update the code in to_backend here to erase all the "delegation_tags" from node.meta after we've performed all `_partition_and_lower` Differential Revision: [D71518362](https://our.internmc.facebook.com/intern/diff/D71518362/) [ghstack-poisoned]
mcr229
requested review from
JacobSzwejbka,
larryliu0820 and
tarun292
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9435
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit f372d4d with merge base 1300cda ( NEW FAILURE - The following job has failed:
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: D71518362 |
tarun292
approved these changes
Mar 20, 2025
cccclai
reviewed
Mar 20, 2025
exir/backend/backend_api.py
Outdated
Comment on lines
407
to
408
| if "delegation_tag" in node.meta: | ||
| del node.meta["delegation_tag"] |
There was a problem hiding this comment.
Suggested change
| if "delegation_tag" in node.meta: | |
| del node.meta["delegation_tag"] | |
| node.meta.pop("delegation_tag", None) |
cccclai
approved these changes
Mar 20, 2025
There was a slight bug i found when lowering with: XnnpackDynamicallyQuantizedPartitioner --> XnnpackPartitioner. The issue arrises because the second time we partition, delegation tags from the previous partitioner still exist. Specifically they exist on the getitem node because the metadata was propagated. See: https://github.com/pytorch/pytorch/blob/main/torch/fx/passes/utils/fuser_utils.py#L235 Since the getitem nodes created in by the XnnpackDynamicallyQuantizedPartitioner still have the delegation tags, they sneak into partitions from XnnpackPartitioner. This shouldn't happen because delegation tags from previous Partitioner should not exist after the previous lowering. We update the code in to_backend here to erase all the "delegation_tags" from node.meta after we've performed all `_partition_and_lower` Differential Revision: [D71518362](https://our.internmc.facebook.com/intern/diff/D71518362/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D71518362 |
facebook-github-bot
merged commit 6f675f3
into
gh/mcr229/15/base
79 of 82 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
Stack from ghstack (oldest at bottom):
There was a slight bug i found when lowering with:
XnnpackDynamicallyQuantizedPartitioner --> XnnpackPartitioner. The issue arrises because the second time we partition, delegation tags from the previous partitioner still exist. Specifically they exist on the getitem node because the metadata was propagated.
See:
https://github.com/pytorch/pytorch/blob/main/torch/fx/passes/utils/fuser_utils.py#L235
Since the getitem nodes created in by the XnnpackDynamicallyQuantizedPartitioner still have the delegation tags, they sneak into partitions from XnnpackPartitioner. This shouldn't happen because delegation tags from previous Partitioner should not exist after the previous lowering.
We update the code in to_backend here to erase all the "delegation_tags" from node.meta after we've performed all
_partition_and_lowerDifferential Revision: D71518362