Skip to content
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

Better error message for quantized dispatch #28635

Closed
wants to merge 9 commits into from

Conversation

z-a-f
Copy link
Contributor

@z-a-f z-a-f commented Oct 25, 2019

Stack from ghstack:

Fixes #28518

Differential Revision: D18132566

z-a-f added a commit that referenced this pull request Oct 25, 2019
Fixes #28518

ghstack-source-id: a1c60d0a18bcf62dd3050e1ddc6655680c98f61b
Pull Request resolved: #28635
@z-a-f z-a-f added the oncall: quantization Quantization support in PyTorch label Oct 25, 2019
z-a-f added a commit that referenced this pull request Oct 25, 2019
Fixes #28518

ghstack-source-id: e82c911ae391457d11ceee6f5e6ba3d5c63c082e
Pull Request resolved: #28635
Copy link
Collaborator

@jamesr66a jamesr66a left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks! Left some small comments

cc @smessmer

aten/src/ATen/core/dispatch/DispatchTable.h Outdated Show resolved Hide resolved
aten/src/ATen/core/dispatch/DispatchTable.h Outdated Show resolved Hide resolved
z-a-f added a commit that referenced this pull request Oct 25, 2019
Fixes #28518

ghstack-source-id: 67896d6d732e90c5cbc69b5f3027ac78f65a1702
Pull Request resolved: #28635
z-a-f added a commit that referenced this pull request Oct 28, 2019
Fixes #28518

ghstack-source-id: 1c064ff83f6f841922fa7c0870744e9f32564fd2
Pull Request resolved: #28635
Copy link
Member

@jianyuh jianyuh left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

z-a-f added a commit that referenced this pull request Oct 29, 2019
Fixes #28518

ghstack-source-id: 6136b4d1d0e7f311a002f9cec0497f42471b1fb3
Pull Request resolved: #28635
zdevito pushed a commit to zdevito/ATen that referenced this pull request Oct 31, 2019
Summary:
Pull Request resolved: pytorch/pytorch#28635

Fixes #28518

Test Plan: Imported from OSS

Differential Revision: D18132566

Pulled By: z-a-f

fbshipit-source-id: 08acc3033b12a0b79b43a5346b7af100416ffa94
@facebook-github-bot
Copy link
Contributor

@z-a-f merged this pull request in 28be2d4.

@smessmer
Copy link
Contributor

smessmer commented Nov 1, 2019

I don't think we want this. The core dispatch logic is agnostic of quantization and should stay this way. Quantization depends on dispatch, not the other way round.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Merged oncall: quantization Quantization support in PyTorch
Projects
None yet
Development

Successfully merging this pull request may close these issues.

7 participants