Reintroduce has_weight_zeros as a template param #1991
Merged
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/ao/1991
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 3 PendingAs of commit 6a0489c with merge base 70fc520 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D71503133 |
Summary: Pull Request resolved: pytorch#1991 When introducing bias, we made has_weight_zeros a regular argument instead of a template arg. I've noticed this has decreased perf, so we re-introduce has_weight_zeros as a template arg. I keep has_bias and has_clamp as regular args because they are only applied in the outer most loop, and we want to reduce code bloat. Note that all of this happens during internal dispatch, and the user-level python op has no change in API. Reviewed By: drisspg Differential Revision: D71503133
|
This pull request was exported from Phabricator. Differential Revision: D71503133 |
20ff71f to
6a0489c
Compare
Jack-Khuu
approved these changes
Apr 1, 2025
jainapurva
pushed a commit
that referenced
this pull request
Apr 8, 2025
Differential Revision: D71503133 Pull Request resolved: #1991
liangel-02
pushed a commit
that referenced
this pull request
Aug 25, 2025
Differential Revision: D71503133 Pull Request resolved: #1991
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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:
When introducing bias, we made has_weight_zeros a regular argument instead of a template arg.
I've noticed this has decreased perf, so we re-introduce has_weight_zeros as a template arg. I keep has_bias and has_clamp as regular args because they are only applied in the outer most loop, and we want to reduce code bloat.
Note that all of this happens during internal dispatch, and the user-level python op has no change in API.
Reviewed By: drisspg
Differential Revision: D71503133