Remove deprecated XNNPACK capture utilities and migrate tests#18134
Open
JacobSzwejbka wants to merge 2 commits intopytorch:mainfrom
Open
Remove deprecated XNNPACK capture utilities and migrate tests#18134JacobSzwejbka wants to merge 2 commits intopytorch:mainfrom
JacobSzwejbka wants to merge 2 commits intopytorch:mainfrom
Conversation
…pytorch#18111) Summary: Migrate test_pass_infra, test_debug_handle_map, test_delegate_map_builder, test_backends_nested, and hta_partitioner_demo to use the torch.export.export() + to_edge() flow instead of the deprecated exir.capture() API. Key changes: - Replace exir.capture(model, inputs, CaptureConfig()).to_edge() with to_edge(export(model, inputs, strict=True)) - Wrap plain functions in nn.Module for torch.export compatibility - Use dynamic debug handle extraction instead of hardcoded values in test_delegate_map_builder (handle numbering changed) - Collapse lifted/unlifted pattern variants in hta_partitioner_demo since torch.export always produces lifted graphs Differential Revision: D95605454
Summary: Delete capture_graph_for_xnnpack() and get_xnnpack_capture_config() which were only used in test files and relied on the deprecated exir.capture API. Migrate test_xnnpack_utils.py to use inline to_edge(export(...)) calls. Remove the deprecated exports from xnnpack/__init__.py. Differential Revision: D95605468
JacobSzwejbka
requested review from
Gasoonjia,
digantdesai and
larryliu0820
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18134
Note: Links to docs will display an error until the docs builds have been completed. ❌ 6 New Failures, 1 Cancelled Job, 4 Pending, 2 Unrelated FailuresAs of commit 3193513 with merge base eaf0d65 ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
Contributor
|
@JacobSzwejbka has exported this pull request. If you are a Meta employee, you can view the originating Diff in D95605468. |
This PR needs a
|
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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:
Delete capture_graph_for_xnnpack() and get_xnnpack_capture_config() which
were only used in test files and relied on the deprecated exir.capture API.
Migrate test_xnnpack_utils.py to use inline to_edge(export(...)) calls.
Remove the deprecated exports from xnnpack/init.py.
Differential Revision: D95605468