[executorch] Arm backend: Preserve Arm pass behavior for Conv1d conversion - #22086
Open
JacobSzwejbka wants to merge 1 commit into
Open
[executorch] Arm backend: Preserve Arm pass behavior for Conv1d conversion#22086JacobSzwejbka wants to merge 1 commit into
JacobSzwejbka wants to merge 1 commit into
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/22086
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 0382bc3 with merge base 6d1cdb0 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
zingo
added
release notes: arm
zingo
changed the title
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Keep the shared Conv1d-to-Conv2d transform on the Arm pass hierarchy so whole-graph retracing retains Arm handling for quantized operators without fake kernels. Restore targeted-pass filtering for convolution graphs.
Add a quantized Conv1d-plus-LeakyReLU regression that exercises the failure reported on D116841181.
Test plan:
buck test @fbcode//mode/dev-nosan fbcode//executorch/backends/arm/test:conv1d -- --exact "fbcode//executorch/backends/arm/test:conv1d - test_conv1d.py::test_convolution_1d_with_leaky_relu_tosa_INT"arc lint -aandarc linton changed filestest_ceres_u55_handwritingCI repro; the Buck daemon was killed by host OOM before completion.python -m py_compile backends/arm/_passes/conv1d_unsqueeze_pass.py backends/arm/test/ops/test_conv1d.pyThis PR was authored with Codex.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani