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.

Sign up for GitHub

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

Jump to bottom

Per-channel quantized tensor to have only a single axis #26675

Closed
wants to merge 2 commits into from
Closed

Per-channel quantized tensor to have only a single axis #26675

wants to merge 2 commits into from

Conversation

dzhulgakov
Copy link
Collaborator

@dzhulgakov dzhulgakov commented Sep 23, 2019 •
edited

Stack from ghstack:

Based on offline poll, we're very unlikely to have multi-axis quantized tensors in the foreseeable future. Let's simplify API and just return int instead of list. It also matches the singular axis name.

Differential Revision: D17537052

@pytorchbot pytorchbot added oncall: jit Add this issue/PR to JIT oncall triage queue module: docs Related to our documentation, both in docs/ and docblocks module: internals Related to internal abstractions in c10 and ATen module: operators module: printing Issues related to the printing format of tensors oncall: quantization Quantization support in PyTorch labels Sep 23, 2019
This was referenced Sep 23, 2019
Closed
Closed
jerryzh168
jerryzh168 approved these changes Sep 23, 2019
View reviewed changes
Copy link
Contributor

@jerryzh168 jerryzh168 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, Thanks!

Update on "Per-channel quantized tensor to have only a single axis"
3496475 
Based on offline poll, we're very unlikely to have multi-axis quantized tensors in the foreseeable future. Let's simplify API and just return int instead of list. It also matches the singular `axis` name.

Differential Revision: [D17537052](https://our.internmc.facebook.com/intern/diff/D17537052)

[ghstack-poisoned]
zdevito pushed a commit to zdevito/ATen that referenced this pull request Sep 24, 2019
@facebook-github-bot
Per-channel quantized tensor to have only a single axis (#26675)
cf9bb7b 
Summary:
Pull Request resolved: pytorch/pytorch#26675

Based on offline poll, we're very unlikely to have multi-axis quantized tensors in the foreseeable future. Let's simplify API and just return int instead of list. It also matches the singular `axis` name.

Test Plan: Imported from OSS

Differential Revision: D17537052

Pulled By: dzhulgakov

fbshipit-source-id: 676abc3b251d288468aaed467b5e5ca4063b98b0
@facebook-github-bot
Copy link
Contributor

@dzhulgakov merged this pull request in b93823c.

@facebook-github-bot facebook-github-bot deleted the gh/dzhulgakov/8/head branch October 28, 2019 22:08
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jerryzh168 jerryzh168 jerryzh168 approved these changes

@apaszke apaszke Awaiting requested review from apaszke

@raghuramank100 raghuramank100 Awaiting requested review from raghuramank100

@jamesr66a jamesr66a Awaiting requested review from jamesr66a

Assignees
No one assigned
Labels
Merged module: docs Related to our documentation, both in docs/ and docblocks module: internals Related to internal abstractions in c10 and ATen module: printing Issues related to the printing format of tensors oncall: jit Add this issue/PR to JIT oncall triage queue oncall: quantization Quantization support in PyTorch
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
5 participants
@dzhulgakov @facebook-github-bot @jerryzh168 @pytorchbot @mruberry