Milestone2.1: Partition to_dim_order_copy op in XNN delegate #11286
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11286
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit 549b361 with merge base 18e4240 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
@pytorchbot label "release notes: none" |
pytorch-bot
bot
added
the
release notes: none
leafs1
force-pushed
the
milestone2.1
branch
4 times, most recently
from
7dc20ef to
a8e4be4
Compare
|
Add a more descriptive name to the Title of this PR |
leafs1
changed the title
There was a problem hiding this comment.
Implementation looks good to me. In addition to the test you added in in the pass tests, can you create a test file for to_copy under backends/xnnpack/test/ops? It might be good to add cover the following cases:
- to(channels_last) before linear.
- to(contiguous) before conv.
- Convert both dtype and dim order (for example, .to(torch.float, memory_format=torch.channels_last) with non-float inputs).
leafs1
force-pushed
the
milestone2.1
branch
4 times, most recently
from
74a7331 to
d195f85
Compare
|
@leafs1 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
leafs1
requested review from
jackzhxng,
larryliu0820,
swolchok and
mergennachin
as code owners
leafs1
force-pushed
the
milestone2.1
branch
2 times, most recently
from
d029d18 to
3e1a4e3
Compare
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
Add to_dim_order_copy op to the partitioner in XNN delegate and delegate dim order conversions (to_dim_order_copy op) manually initiated by user using .to(memory_format=)
Test plan
Confirmed expected output when having user specified dim order conversions as well as appropriate partitioning