modified all the operators to support generic implementation in specific cases #7936
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/7936
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Contributor
|
@zonglinpeng has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
hsharma35
requested review from
hsharma35,
mcremon-meta and
zonglinpeng
and removed request for
hsharma35 and
mcremon-meta
hsharma35
reviewed
Jan 28, 2025
| } | ||
|
|
||
| if ((out.scalar_type() == ScalarType::Int) || | ||
| bool optimized = 1; |
Contributor
There was a problem hiding this comment.
Please use true/false instead of implicit conversion from int (1) to bool true.
Contributor
|
LGTM, will wait for @zonglinpeng to test internally before we merge. |
added 2 commits
January 28, 2025 18:20
…ut data types are different or when input data type is different from output datatype
…n Scalar operation fixed an issue related to datatype of the second input
ckmadhira
force-pushed
the
diff_ip_datatype_support
branch
from
37c9e67 to
44fbbd8
Compare
Contributor
|
@zonglinpeng has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
zonglinpeng
approved these changes
Jan 28, 2025
Contributor
zonglinpeng
left a comment
zonglinpeng
left a comment
There was a problem hiding this comment.
all tests passed internally :) Layer norm might caused by something else yesterday will keep an eye on it.
hsharma35
approved these changes
Jan 28, 2025
zonglinpeng
pushed a commit
to zonglinpeng/executorch
that referenced
this pull request
Jan 28, 2025
…fic cases (pytorch#7936) Summary: modified all the operators to support generic implementation when input data types are different or when input data type is different from output datatype Pull Request resolved: pytorch#7936 Differential Revision: D68637610 Pulled By: zonglinpeng
Contributor
|
@zonglinpeng has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
YIWENX14
pushed a commit
that referenced
this pull request
Jan 29, 2025
…fic cases (#7936) * modified all the operators to support generic implementation when input data types are different or when input data type is different from output datatype * boolean variables are assiged with true or false instead of 1 or 0. In Scalar operation fixed an issue related to datatype of the second input --------- Co-authored-by: cmadhira@cadence.com <cmadhira@global.cadence.com> Co-authored-by: JP <46308822+zonglinpeng@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
Summary
modified all the operators to support generic implementation when input data types are different or when input data type is different from output datatype