[ET-VK][Ops] quantize ops skeleton test framework #11366

ahmtox · 2025-06-04T18:02:56Z

Stack from ghstack (oldest at bottom):

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation

Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

pytorch-bot · 2025-06-04T18:03:00Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11366

📄 Preview Python docs built from this PR

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

❌ 3 New Failures

As of commit e5894a9 with merge base 8cfa858 ():

NEW FAILURES - The following jobs have failed:

Build Presets / linux (linux, linux.2xlarge, executorch-ubuntu-22.04-clang12) / build (gh)
The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.
Build Presets / linux (llm, linux.2xlarge, executorch-ubuntu-22.04-clang12) / build (gh)
Lint / link-check / lint-urls / linux-job (gh)
The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.

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

facebook-github-bot · 2025-06-04T18:03:20Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-09T15:05:59Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-09T15:10:05Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-11T17:00:46Z

This pull request was exported from Phabricator. Differential Revision: D75959066

manuelcandales · 2025-06-11T18:39:39Z

backends/vulkan/test/op_tests/quantize_test.cpp

+    int64_t quant_max,
+    at::ScalarType dtype) {
+  auto out = at::empty_like(input, dtype);
+  // Convert at::ScalarType to executorch::ScalarType


see comments on #11480

manuelcandales · 2025-06-11T18:40:13Z

backends/vulkan/test/op_tests/quantize_test.cpp

+//
+
+// Helper function to get the name of a ScalarType for better error messages
+std::string scalar_type_name(c10::ScalarType dtype) {


see comments on #11480

manuelcandales · 2025-06-11T18:40:25Z

backends/vulkan/test/op_tests/quantize_test.cpp

+  }
+}
+
+vkcompute::vkapi::ScalarType from_at_scalartype(c10::ScalarType at_scalartype) {


see comments on #11480

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-11T19:00:58Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-11T21:50:17Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-12T14:52:01Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-12T17:00:44Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-12T17:05:09Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-12T19:50:34Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-13T04:14:57Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-13T15:14:43Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-13T18:04:25Z

This pull request was exported from Phabricator. Differential Revision: D75959066

Skeleton framework that is needed to build out the quantize_per_tensor and quantize_per_token operators based on cpu implementation Differential Revision: [D75959066](https://our.internmc.facebook.com/intern/diff/D75959066/) [ghstack-poisoned]

facebook-github-bot · 2025-06-13T22:50:47Z

This pull request was exported from Phabricator. Differential Revision: D75959066

ahmtox requested a review from SS-JIA as a code owner June 4, 2025 18:02

This was referenced Jun 4, 2025

[ET-VK] double, short, and uint16 dtype runtime support #11365

Open

[ET-VK][Ops] quantize_per_token.default test setup #11367

Open

[ET-VK][Ops] quantize_per_tensor.default test setup #11368

Open

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

Open

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 added the fb-exported label Jun 4, 2025

SS-JIA approved these changes Jun 11, 2025

View reviewed changes

manuelcandales requested changes Jun 11, 2025

View reviewed changes

ahmtox added the release notes: vulkan Changes to the Vulkan backend delegate label Jun 11, 2025

ahmtox mentioned this pull request Jun 11, 2025

[ET-VK][Ops] common test utils for converting aten types to vulkan types #11575

Open

manuelcandales approved these changes Jun 12, 2025

View reviewed changes

[ET-VK][Ops] quantize ops skeleton test framework #11366

Are you sure you want to change the base?

[ET-VK][Ops] quantize ops skeleton test framework #11366

Conversation

ahmtox commented Jun 4, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot bot commented Jun 4, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11366

❌ 3 New Failures

Uh oh!

facebook-github-bot commented Jun 4, 2025

Uh oh!

facebook-github-bot commented Jun 9, 2025

Uh oh!

facebook-github-bot commented Jun 9, 2025

Uh oh!

facebook-github-bot commented Jun 11, 2025

Uh oh!

manuelcandales Jun 11, 2025

Choose a reason for hiding this comment

Uh oh!

manuelcandales Jun 11, 2025

Choose a reason for hiding this comment

Uh oh!

manuelcandales Jun 11, 2025

Choose a reason for hiding this comment

Uh oh!

facebook-github-bot commented Jun 11, 2025

Uh oh!

facebook-github-bot commented Jun 11, 2025

Uh oh!

facebook-github-bot commented Jun 12, 2025

Uh oh!

facebook-github-bot commented Jun 12, 2025

Uh oh!

facebook-github-bot commented Jun 12, 2025

Uh oh!

facebook-github-bot commented Jun 12, 2025

Uh oh!

facebook-github-bot commented Jun 13, 2025

Uh oh!

facebook-github-bot commented Jun 13, 2025

Uh oh!

facebook-github-bot commented Jun 13, 2025

Uh oh!

facebook-github-bot commented Jun 13, 2025

Uh oh!

Uh oh!

ahmtox commented Jun 4, 2025 •

edited

Loading

pytorch-bot bot commented Jun 4, 2025 •

edited

Loading