Skip to content

[ET] enabling half dtype output for dequantization and making logic consistent #11552

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

Merged
merged 10 commits into from
Jun 14, 2025

Conversation

ahmtox
Copy link
Contributor

@ahmtox ahmtox commented Jun 11, 2025

…onsistent

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Jun 11, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11552

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

❌ 4 New Failures, 2 Cancelled Jobs, 18 Unrelated Failures

As of commit 5cfc153 with merge base 8cfa858 (image):

NEW FAILURES - The following jobs have failed:

CANCELLED JOBS - The following jobs were cancelled. Please retry:

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

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

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D76289181

…ing logic consistent"

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

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

This pull request was exported from Phabricator. Differential Revision: D76289181

@ahmtox ahmtox added the release notes: vulkan Changes to the Vulkan backend delegate label Jun 11, 2025
…ing logic consistent"

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

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

This pull request was exported from Phabricator. Differential Revision: D76289181

…ing logic consistent"

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

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

This pull request was exported from Phabricator. Differential Revision: D76289181

…ing logic consistent"

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

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

This pull request was exported from Phabricator. Differential Revision: D76289181

…ing logic consistent"

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

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

This pull request was exported from Phabricator. Differential Revision: D76289181

…ing logic consistent"

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

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

This pull request was exported from Phabricator. Differential Revision: D76289181

…ing logic consistent"

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

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

This pull request was exported from Phabricator. Differential Revision: D76289181

…ing logic consistent"

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

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

This pull request was exported from Phabricator. Differential Revision: D76289181

…ing logic consistent"

Enabling half dtype output and making dequantization logic consistent between per_tensor and per_token as it is currently prone to integer overflows on one over the other

Differential Revision: [D76289181](https://our.internmc.facebook.com/intern/diff/D76289181/)

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

This pull request was exported from Phabricator. Differential Revision: D76289181

@facebook-github-bot facebook-github-bot merged commit 64d1f4d into gh/ahmtox/17/base Jun 14, 2025
73 of 98 checks passed
@facebook-github-bot facebook-github-bot deleted the gh/ahmtox/17/head branch June 14, 2025 03:45
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.

3 participants