[ET-VK][Ops] quantize_per_channel shaders and impl #12205

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

Merged

facebook-github-bot merged 8 commits into gh/ahmtox/33/base from gh/ahmtox/33/head

Jul 14, 2025

Contributor

ahmtox commented Jul 3, 2025 •

edited

Loading

Stack from ghstack (oldest at bottom):

Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

Changes

This creates an extension of the existing files for quantize_per_channel.

Differential Revision: D77746140


          [ET-VK][Ops] quantize_per_channel shaders and impl

ee33a73

# Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

# Changes

This creates an extension of the existing files for quantize_per_channel.

Differential Revision: [D77746140](https://our.internmc.facebook.com/intern/diff/D77746140/)

[ghstack-poisoned]

ahmtox requested a review from SS-JIA as a code owner

July 3, 2025 18:17

pytorch-bot bot commented Jul 3, 2025 •

edited

Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12205

📄 Preview Python docs built from this PR

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

❌ 2 New Failures

As of commit 4669356 with merge base 1540659 ():

NEW FAILURES - The following jobs have failed:

pull / test-eval_llama-mmlu-linux / linux-job (gh)
RuntimeError: Command docker exec -t 5e91e12b7e83114f00b4d848dd29bf5bd91bd3bd94c106763bd602469dd81fdb /exec failed with exit code 1
pull / unittest / macos / macos-job (gh)
backends/xnnpack/test/ops/test_conv1d.py::TestConv1d::test_qs8_conv1d_batchnorm_seq

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

This was referenced Jul 3, 2025

[ET-VK][Ops] aligning Q/DQ/CQP op inputs with ATen impl #12199

Merged

[ET-VK][ez][Ops] registering Q/DQ/CQP ops and specifying optimal storage #12200

Merged

[ET-VK][ez] enabling fp64->fp32 converison for vulkan compatibility #12201

Merged

[ET-VK] lowering ExecuTorch tensor dtype for Vulkan tensor dtype to enable 64bit #12202

Open

[ET] correcting cpu ref quantize_per_channel logic to align with ATen #12203

Merged

[ET-VK][Ops] quantize_per_channel reference impl and testing #12204

Merged

[ET-VK][Ops] dequantize_per_channel reference impl and testing #12206

Merged

[ET-VK][Ops] dequantize_per_channel shaders and impl #12207

Merged

[ET-VK][Ops] quantize_per_tensor.tensor variant #12208

Merged

[ET-VK][Ops] dequantize_per_tensor.tensor variant #12209

Merged

[ET-VK][testing] Q/DQ/CQP op comprehensive delegate dynamic quantization testing #12210

Merged

github-actions bot commented Jul 3, 2025

This PR needs a `release notes:` label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

facebook-github-bot added the CLA Signed label

Contributor

facebook-github-bot commented Jul 3, 2025

This pull request was exported from Phabricator. Differential Revision: D77746140


          Update on "[ET-VK][Ops] quantize_per_channel shaders and impl"

ffb17cf

# Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

# Changes

This creates an extension of the existing files for quantize_per_channel.

Differential Revision: [D77746140](https://our.internmc.facebook.com/intern/diff/D77746140/)

[ghstack-poisoned]

Contributor

facebook-github-bot commented Jul 3, 2025

This pull request was exported from Phabricator. Differential Revision: D77746140

facebook-github-bot added the fb-exported label


          Update on "[ET-VK][Ops] quantize_per_channel shaders and impl"

e4e9d17

# Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

# Changes

This creates an extension of the existing files for quantize_per_channel.

Differential Revision: [D77746140](https://our.internmc.facebook.com/intern/diff/D77746140/)

[ghstack-poisoned]

Contributor

facebook-github-bot commented Jul 7, 2025

This pull request was exported from Phabricator. Differential Revision: D77746140

SS-JIA approved these changes

View reviewed changes


          Update on "[ET-VK][Ops] quantize_per_channel shaders and impl"

50da62f

# Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

# Changes

This creates an extension of the existing files for quantize_per_channel.

Differential Revision: [D77746140](https://our.internmc.facebook.com/intern/diff/D77746140/)

[ghstack-poisoned]

ahmtox mentioned this pull request

[ET-VK][Ops] affine quantization operators registration #12369

Merged

Contributor

facebook-github-bot commented Jul 10, 2025

This pull request was exported from Phabricator. Differential Revision: D77746140


          Update on "[ET-VK][Ops] quantize_per_channel shaders and impl"

12ca312

# Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

# Changes

This creates an extension of the existing files for quantize_per_channel.

Differential Revision: [D77746140](https://our.internmc.facebook.com/intern/diff/D77746140/)

[ghstack-poisoned]

Contributor

facebook-github-bot commented Jul 11, 2025

This pull request was exported from Phabricator. Differential Revision: D77746140


          Update on "[ET-VK][Ops] quantize_per_channel shaders and impl"

a46f81c

# Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

# Changes

This creates an extension of the existing files for quantize_per_channel.

Differential Revision: [D77746140](https://our.internmc.facebook.com/intern/diff/D77746140/)

[ghstack-poisoned]

Contributor

facebook-github-bot commented Jul 11, 2025

This pull request was exported from Phabricator. Differential Revision: D77746140


          Update on "[ET-VK][Ops] quantize_per_channel shaders and impl"

3e2b092

# Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

# Changes

This creates an extension of the existing files for quantize_per_channel.

Differential Revision: [D77746140](https://our.internmc.facebook.com/intern/diff/D77746140/)

[ghstack-poisoned]

Contributor

facebook-github-bot commented Jul 11, 2025

This pull request was exported from Phabricator. Differential Revision: D77746140


          Update on "[ET-VK][Ops] quantize_per_channel shaders and impl"

# Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

# Changes

This creates an extension of the existing files for quantize_per_channel.

Differential Revision: [D77746140](https://our.internmc.facebook.com/intern/diff/D77746140/)

[ghstack-poisoned]

Contributor

facebook-github-bot commented Jul 14, 2025

This pull request was exported from Phabricator. Differential Revision: D77746140

facebook-github-bot merged commit ca62806 into gh/ahmtox/33/base

97 of 100 checks passed

facebook-github-bot deleted the gh/ahmtox/33/head branch

July 14, 2025 14:58

facebook-github-bot temporarily deployed to cherry-pick-bot

July 14, 2025 14:58

— with

GitHub Actions Inactive

pytorchbot mentioned this pull request

[ET-VK][Ops] quantize_per_channel shaders and impl #12433

Merged

SS-JIA pushed a commit that referenced this pull request


          [ET-VK][Ops] quantize_per_channel shaders and impl

ebc7839

Pull Request resolved: #12205

# Context

We need to enable the core logic for quantize_per_channel in the vulkan shader. This implements the shader itself and its cpp header.

TODO: add more of a description regarding the operator

# Changes

This creates an extension of the existing files for quantize_per_channel.
ghstack-source-id: 295972786
@exported-using-ghexport

Differential Revision: [D77746140](https://our.internmc.facebook.com/intern/diff/D77746140/)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed fb-exported