Skip to content

[ET-VK][Ops] quantization op shaders and impl #11369

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

Open
wants to merge 6 commits into
base: gh/ahmtox/11/base
Choose a base branch
from

Conversation

ahmtox
Copy link

@ahmtox ahmtox commented Jun 4, 2025

Creating the quantize_per_tensor and quantize_per_token logic shaders and impl which are linked with the testing framework.

NOTE: Currently the only input types supported are **half** (fp16) and **float** (fp32). The only output types supported are **byte** (uint8), **char** (int8), **short** (int16), **int** (int32).

Differential Revision: [D75959064](https://our.internmc.facebook.com/intern/diff/D75959064/)

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Jun 4, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11369

Note: Links to docs will display an error until the docs builds have been completed.

❌ 8 New Failures

As of commit 26a3dc8 with merge base cbd3874 (image):

NEW FAILURES - The following jobs have failed:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

ahmtox pushed a commit that referenced this pull request Jun 4, 2025
Creating the quantize_per_tensor and quantize_per_token logic shaders and impl which are linked with the testing framework.

NOTE: Currently the only input types supported are **half** (fp16) and **float** (fp32). The only output types supported are **byte** (uint8), **char** (int8), **short** (int16), **int** (int32).

Differential Revision: [D75959064](https://our.internmc.facebook.com/intern/diff/D75959064/)

ghstack-source-id: 288187842
Pull Request resolved: #11369
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jun 4, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D75959064

Creating the quantize_per_tensor and quantize_per_token logic shaders and impl which are linked with the testing framework.

NOTE: Currently the only input types supported are **half** (fp16) and **float** (fp32). The only output types supported are **byte** (uint8), **char** (int8), **short** (int16), **int** (int32).

Differential Revision: [D75959064](https://our.internmc.facebook.com/intern/diff/D75959064/)

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

This pull request was exported from Phabricator. Differential Revision: D75959064

Creating the quantize_per_tensor and quantize_per_token logic shaders and impl which are linked with the testing framework.

NOTE: Currently the only input types supported are **half** (fp16) and **float** (fp32). The only output types supported are **byte** (uint8), **char** (int8), **short** (int16), **int** (int32).

Differential Revision: [D75959064](https://our.internmc.facebook.com/intern/diff/D75959064/)

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

This pull request was exported from Phabricator. Differential Revision: D75959064

Creating the quantize_per_tensor and quantize_per_token logic shaders and impl which are linked with the testing framework.

NOTE: Currently the only input types supported are **half** (fp16) and **float** (fp32). The only output types supported are **byte** (uint8), **char** (int8), **short** (int16), **int** (int32).

Differential Revision: [D75959064](https://our.internmc.facebook.com/intern/diff/D75959064/)

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

This pull request was exported from Phabricator. Differential Revision: D75959064

Creating the quantize_per_tensor and quantize_per_token logic shaders and impl which are linked with the testing framework.

NOTE: Currently the only input types supported are **half** (fp16) and **float** (fp32). The only output types supported are **byte** (uint8), **char** (int8), **short** (int16), **int** (int32).

Differential Revision: [D75959064](https://our.internmc.facebook.com/intern/diff/D75959064/)

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

This pull request was exported from Phabricator. Differential Revision: D75959064

@ahmtox ahmtox added the release notes: vulkan Changes to the Vulkan backend delegate label Jun 11, 2025
Creating the quantize_per_tensor and quantize_per_token logic shaders and impl which are linked with the testing framework.

NOTE: Currently the only input types supported are **half** (fp16) and **float** (fp32). The only output types supported are **byte** (uint8), **char** (int8), **short** (int16), **int** (int32).

Differential Revision: [D75959064](https://our.internmc.facebook.com/intern/diff/D75959064/)

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

This pull request was exported from Phabricator. Differential Revision: D75959064

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported release notes: vulkan Changes to the Vulkan backend delegate
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants