Skip to content

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

Closed
dzhulgakov wants to merge 2 commits intogh/dzhulgakov/8/basefrom
gh/dzhulgakov/8/head
Closed

Per-channel quantized tensor to have only a single axis#26675
dzhulgakov wants to merge 2 commits intogh/dzhulgakov/8/basefrom
gh/dzhulgakov/8/head

Conversation

@dzhulgakov
Copy link
Copy Markdown
Collaborator

@dzhulgakov dzhulgakov commented Sep 23, 2019

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

@dzhulgakov dzhulgakov requested a review from apaszke as a code owner September 23, 2019 21:55
@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
Copy link
Copy Markdown
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!

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
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
Copy Markdown
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
laurentdupin pushed a commit to laurentdupin/pytorch that referenced this pull request Apr 24, 2026
Summary:
Pull Request resolved: 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
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

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

Development

Successfully merging this pull request may close these issues.

5 participants