[ET-VK][Ops] dequantize ops skeleton test framework#11480
Merged
Conversation
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11480
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Unrelated FailureAs of commit 8005443 with merge base 8cfa858 ( NEW FAILURE - The following job has failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This was referenced Jun 9, 2025
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
This was referenced Jun 11, 2025
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
manuelcandales
requested changes
Jun 11, 2025
| // | ||
|
|
||
| // Helper function to get the name of a ScalarType for better error messages | ||
| std::string scalar_type_name(c10::ScalarType dtype) { |
Contributor
There was a problem hiding this comment.
isn't this the same helper function you used for the quantized tests? if so, please refactor this into some utilities.
| } | ||
| } | ||
|
|
||
| vkcompute::vkapi::ScalarType from_at_scalartype(c10::ScalarType at_scalartype) { |
Contributor
There was a problem hiding this comment.
same as above, refactor into common utilities
| at::ScalarType dtype, | ||
| at::ScalarType out_dtype) { | ||
| auto out = at::empty_like(input, out_dtype); | ||
| // Convert at::ScalarType to executorch::ScalarType |
Contributor
There was a problem hiding this comment.
you use this conversion here two times, and also in the quantized tests, please refactor into a utility function
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
manuelcandales
approved these changes
Jun 12, 2025
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D76267021 |
facebook-github-bot
merged commit 763269a
into
gh/ahmtox/13/base
95 of 98 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
kedarnath03
pushed a commit
to kedarnath03/executorch
that referenced
this pull request
Jun 25, 2025
Pull Request resolved: pytorch/executorch#11480 # Context In this diff we plan on creating the skeleton test framework for dequantization. This is necessary as we need a reference to test our vulkan implementation of the dequantization operator against an existing cpu implementation. This test framework is heavily inspired by [sdpa_test.cpp](https://github.com/pytorch/executorch/blob/main/backends/vulkan/test/op_tests/sdpa_test.cpp). We make use of the [op_dequantize.cpp](https://github.com/pytorch/executorch/blob/main/kernels/quantized/cpu/op_dequantize.cpp) cpu implementation of the `dequantize_per_tensor`, and the `dequantize_per_token` operators. An explanation for the operator is included where the actual vulkan implementation is created in a future diff along this stack. # Changes The main thing in this difference is the creation of a new test framework `dequantize_test.cpp`, and also including it in targets.bzl such that we can properly call the test. As this is inspired by sdpa_test.cpp, we also follow a similar format. First we have forward declarations of the functions that we wish to test against (dequantize_per_tensor, and dequantize_per_token). Then we also have wrappers for the functions without context, and finally wrappers for the ATen implementations of the same operators using the `WRAP_TO_ATEN` macro. We don't need context as this is merely for testing. We also have a utility function to test the quantize arguments that will be used when actually using the vulkan implementation. This utility function is just for a sanity check. ghstack-source-id: 290376489 @exported-using-ghexport Differential Revision: [D76267021](https://our.internmc.facebook.com/intern/diff/D76267021/)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
Skeleton framework that is needed to build out the dequantize_per_tensor and dequantize_per_token operators based on cpu implementation
Differential Revision: D76267021