Repository navigation
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24378
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 87b0be3 with merge base a84676e ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
Contributor
|
@psiddh has exported this pull request. If you are a Meta employee, you can view the originating Diff in D127010333. |
This PR needs a
|
psiddh
added a commit
to psiddh/executorch
that referenced
this pull request
Oct 31, 2026
Summary: native_layer_norm kept its build-time shape when the sequence length changed, so the next op failed to resize. It now resizes with its input, and the partitioner keeps layer norms over more than the last non-unit dim on CPU, where before they were delegated and computed wrong values. This unblocks dynamic-length transformers such as on-device text-to-speech in the browser. Follow-up (pre-existing, unchanged here): weight-only or bias-only layer norms and a dynamic normalized dim are still delegated. Differential Revision: D127010333
meta-codesync
Bot
changed the title
psiddh
force-pushed
the
export-D127010333
branch
from
October 31, 2026 07:31
09ea938 to
b059e3d
Compare
psiddh
added a commit
to psiddh/executorch
that referenced
this pull request
Oct 31, 2026
Summary: native_layer_norm kept its build-time shape when the sequence length changed, so the next op failed to resize. It now resizes with its input, and the partitioner keeps layer norms over more than the last non-unit dim on CPU, where before they were delegated and computed wrong values. This unblocks dynamic-length transformers such as on-device text-to-speech in the browser. Follow-up (pre-existing, unchanged here): weight-only or bias-only layer norms and a dynamic normalized dim are still delegated. Differential Revision: D127010333
psiddh
force-pushed
the
export-D127010333
branch
from
October 31, 2026 07:33
b059e3d to
2fc0293
Compare
Summary: native_layer_norm kept its build-time shape when the sequence length changed, so the next op failed to resize. It now resizes with its input, and the partitioner keeps layer norms over more than the last non-unit dim on CPU, where before they were delegated and computed wrong values. This unblocks dynamic-length transformers such as on-device text-to-speech in the browser. Follow-up (pre-existing, unchanged here): weight-only or bias-only layer norms and a dynamic normalized dim are still delegated. Differential Revision: D127010333
psiddh
force-pushed
the
export-D127010333
branch
from
November 7, 2026 19:13
2fc0293 to
87b0be3
Compare
psiddh
added a commit
to psiddh/executorch
that referenced
this pull request
Nov 7, 2026
Summary: native_layer_norm kept its build-time shape when the sequence length changed, so the next op failed to resize. It now resizes with its input, and the partitioner keeps layer norms over more than the last non-unit dim on CPU, where before they were delegated and computed wrong values. This unblocks dynamic-length transformers such as on-device text-to-speech in the browser. Follow-up (pre-existing, unchanged here): weight-only or bias-only layer norms and a dynamic normalized dim are still delegated. Differential Revision: D127010333
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:
native_layer_norm kept its build-time shape when the sequence length changed, so the next op failed to resize.
It now resizes with its input, and the partitioner keeps layer norms over more than the last non-unit dim on CPU, where before they were delegated and computed wrong values.
This unblocks dynamic-length transformers such as on-device text-to-speech in the browser.
Follow-up (pre-existing, unchanged here): weight-only or bias-only layer norms and a dynamic normalized dim are still delegated.
Differential Revision: D127010333