Skip to content

[quant] Expose supportedQEngines to python #26474

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

Closed
wants to merge 6 commits into from

Conversation

jerryzh168
Copy link
Contributor

@jerryzh168 jerryzh168 commented Sep 19, 2019

Stack from ghstack:

Summary:
att

Test Plan:
python test/test_torch.py

Reviewers:
pt1quant

Subscribers:

Tasks:

Tags:

Differential Revision: D17517373

Summary:
att

Test Plan:
python test/test_torch.py

Reviewers:
pt1quant

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
Summary:
att

Test Plan:
python test/test_torch.py

Reviewers:
pt1quant

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
jerryzh168 added a commit that referenced this pull request Sep 19, 2019
Summary:
att

Test Plan:
python test/test_torch.py

Reviewers:
pt1quant

Subscribers:

Tasks:

Tags:

ghstack-source-id: e9fd9d7
Pull Request resolved: #26474
qengines = torch._C._supported_qengines()
# [TODO] Enable after the interface change
# original_qe = torch._C._get_qengine()
# for qe in qengines:
Copy link
Contributor

Choose a reason for hiding this comment

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

qe is an int but set_qengine expects at::QEngine. Will this work?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

it doens't work right now that's why I commented them out. it should work after the interface change. we should be returning/pass int in _get_qengine and _set_qengine as well

Summary:
att

Test Plan:
python test/test_torch.py

Reviewers:
pt1quant

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
Summary:
att

Test Plan:
python test/test_torch.py

Reviewers:
pt1quant

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
Copy link
Contributor

@supriyar supriyar left a comment

Choose a reason for hiding this comment

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

Looks good.
The plan after this is to change qengine to string (user facing) and return an int from supported_qengines.

@jerryzh168
Copy link
Contributor Author

plan is to change _set_qengine and _get_qengine to return/receive int. supported_qengines already returns a list of int

Summary:
att

Test Plan:
python test/test_torch.py

Reviewers:
pt1quant

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
Summary:
att

Test Plan:
python test/test_torch.py

Reviewers:
pt1quant

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request has been merged in 2667493.

mingbowan pushed a commit to mingbowan/pytorch that referenced this pull request Sep 23, 2019
Summary:
Pull Request resolved: pytorch#26474

att

Test Plan:
python test/test_torch.py

Imported from OSS

Differential Revision: D17517373

fbshipit-source-id: af931761d6ee31a88808d05f686002a83b6b25af
@facebook-github-bot facebook-github-bot deleted the gh/jerryzh168/78/head branch October 28, 2019 22:15
xxtEchjovs44 pushed a commit to xxtEchjovs44/pytorch that referenced this pull request Jan 29, 2020
Summary:
att

Test Plan:
python test/test_torch.py

Reviewers:
pt1quant

Subscribers:

Tasks:

Tags:

ghstack-source-id: 6688d99
Pull Request resolved: pytorch/pytorch#26474
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Merged module: internals Related to internal abstractions in c10 and ATen
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants