fix permute copy name #80
Closed
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
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D48488930 |
|
This pull request was exported from Phabricator. Differential Revision: D48488930 |
mcr229
force-pushed
the
export-D48488930
branch
from
c95b2a6 to
c746397
Compare
|
This pull request was exported from Phabricator. Differential Revision: D48488930 |
mcr229
force-pushed
the
export-D48488930
branch
from
c746397 to
b9d88f5
Compare
|
This pull request was exported from Phabricator. Differential Revision: D48488930 |
mcr229
force-pushed
the
export-D48488930
branch
from
b9d88f5 to
b400273
Compare
|
This pull request was exported from Phabricator. Differential Revision: D48488930 |
mcr229
force-pushed
the
export-D48488930
branch
from
b400273 to
7387f89
Compare
|
This pull request was exported from Phabricator. Differential Revision: D48488930 |
mcr229
force-pushed
the
export-D48488930
branch
from
7387f89 to
e76d877
Compare
|
This pull request was exported from Phabricator. Differential Revision: D48488930 |
mcr229
force-pushed
the
export-D48488930
branch
from
e76d877 to
ccb1686
Compare
|
This pull request was exported from Phabricator. Differential Revision: D48488930 |
mcr229
force-pushed
the
export-D48488930
branch
from
ccb1686 to
7f88285
Compare
Summary: Pull Request resolved: pytorch/executorch#66 DQ Linear runtime logic for XNNPACK is FB internal only, so we are adding a flag in the dq linear logic to remove dq linear logic from xnnpack delegate in OSS Differential Revision: D48335277 fbshipit-source-id: 6e9039c2df2ff68960a7a011a3dcc341c5b41403
Summary: Pull Request resolved: pytorch/executorch#80 We have a node_visitor for permute already, it was mistakenly named static_transpose after its xnnpack counterpart. permute_copy should not be skipped. It should only be skipped when applied to linear weights. Instead our linear conversion pass will convert away any permute_copies which are not actually to be executed. Reviewed By: kirklandsign Differential Revision: D48488930 fbshipit-source-id: 9d84e00bdfa04828768e8d0e352817a0348b0cc6
|
This pull request was exported from Phabricator. Differential Revision: D48488930 |
mcr229
force-pushed
the
export-D48488930
branch
from
7f88285 to
cbd9c22
Compare
|
This pull request has been merged in def08cf. |
larryliu0820
pushed a commit
that referenced
this pull request
Jul 2, 2025
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:
We have a node_visitor for permute already, it was mistakenly named static_transpose after its xnnpack counterpart. permute_copy should not be skipped. It should only be skipped when applied to linear weights.
Instead our linear conversion pass will convert away any permute_copies which are not actually to be executed.
Differential Revision: D48488930