Repository navigation
Vulkan: keep a reshape that follows a dynamically quantized linear - #24055
Open
msluszniak wants to merge 1 commit into
Open
msluszniak wants to merge 1 commit into
msluszniak wants to merge 1 commit into
Conversation
QuantizedLinearMatch absorbed any single-user view_copy after the linear into the pattern once the input was dynamically quantized. The fused op replaces the pattern output and returns input.shape[:-1] + [N], so an unrelated reshape (e.g. [6, 32] -> [2, 3, 32]) was dropped and the next op failed shape propagation in FusePatternsPass. Only absorb the view that restores a decomposed N-D linear's leading dims.
pytorch-bot
Bot
added
the
module: vulkan
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24055
Note: Links to docs will display an error until the docs builds have been completed. ❌ 128 New Failures, 2 Unrelated Failures, 4 Unclassified FailuresAs of commit c6fcfe3 with merge base e9e21b5 ( NEW FAILURES - The following jobs have failed:
UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This was referenced Oct 21, 2026
executorch-triage
Bot
added
the
community: contribution
nil-is-all
added
the
release notes: vulkan
borys3kk
pushed a commit
to borys3kk/swm_executorch
that referenced
this pull request
Oct 22, 2026
This branch has not been deployed
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
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
QuantizedLinearMatchabsorbed any single-userview_copyafter a dynamically quantized linear into the pattern. The fusedlinear_dq8ca_q4gswreturnsinput.shape[:-1] + [N], so an unrelated reshape after the linear was dropped andFusePatternsPassfailed. Now only the view that restores a decomposed N-D linear's leading dims is absorbed.Test plan
python -m unittest backends.vulkan.test.test_vulkan_passes(newtest_fuse_8da4w_linear_keeps_following_reshapefails without the fix).cc @SS-JIA @manuelcandales @digantdesai @cbilgin @nil-is-all