-
Notifications
You must be signed in to change notification settings - Fork 664
Add int32 quant/dequant back #14269
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Add int32 quant/dequant back #14269
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14269
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 3 Cancelled JobsAs of commit f5cb955 with merge base eec95d0 ( NEW FAILURE - The following job has failed:
CANCELLED JOBS - The following jobs were cancelled. Please retry:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
@mcremon-meta has exported this pull request. If you are a Meta employee, you can view the originating diff in D82282481. |
This PR needs a
|
@mcremon-meta has exported this pull request. If you are a Meta employee, you can view the originating diff in D82282481. |
Summary: Pull Request resolved: #14269 Now that the previous diff exists, we can add the int32 case back without adding to the code size of deployed models. Differential Revision: D82282481
c52612f
to
fd80b51
Compare
@mcremon-meta has exported this pull request. If you are a Meta employee, you can view the originating diff in D82282481. |
Summary: Pull Request resolved: #14269 Now that the previous diff exists, we can add the int32 case back without adding to the code size of deployed models. Reviewed By: hsharma35 Differential Revision: D82282481
fd80b51
to
a9bde68
Compare
@mcremon-meta has exported this pull request. If you are a Meta employee, you can view the originating diff in D82282481. |
Summary: Pull Request resolved: #14269 Now that the previous diff exists, we can add the int32 case back without adding to the code size of deployed models. Reviewed By: hsharma35 Differential Revision: D82282481
a9bde68
to
1997822
Compare
Summary: Pull Request resolved: #14239 As titled, those operators are generic implementations of the custom ops we use, they're not reference implementations (in the numerical sense). Make the change to reflect that. Differential Revision: D82231105 Reviewed By: ethansfng, hsharma35, DrJessop
Summary: As titled. Differential Revision: D82319999
Summary: Pull Request resolved: #14268 As titled. Differential Revision: D82183474 Reviewed By: hsharma35
Summary: Pull Request resolved: #14269 Now that the previous diff exists, we can add the int32 case back without adding to the code size of deployed models. Reviewed By: hsharma35 Differential Revision: D82282481
@mcremon-meta has exported this pull request. If you are a Meta employee, you can view the originating diff in D82282481. |
1997822
to
f5cb955
Compare
Summary: Now that the previous diff exists, we can add the int32 case back without adding to the code size of deployed models.
Differential Revision: D82282481