Skip to content

[ET-VK][testing] Add scripts to facilitate operator testiing #13593

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
SS-JIA merged 1 commit into from
Aug 23, 2025
Merged

[ET-VK][testing] Add scripts to facilitate operator testiing #13593

SS-JIA merged 1 commit into from
Aug 23, 2025

Conversation

@SS-JIA
Copy link
Contributor

@SS-JIA SS-JIA commented Aug 22, 2025 •
edited
Loading

@pytorch-bot
Copy link

pytorch-bot bot commented Aug 22, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13593

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

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

@meta-cla meta-cla 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 Aug 22, 2025
This was referenced Aug 22, 2025
Merged
Merged
Merged
Merged
@github-actions
Copy link

github-actions bot commented Aug 22, 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.

@SS-JIA
Copy link
Contributor Author

SS-JIA commented Aug 22, 2025

@SS-JIA has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

This was referenced Aug 22, 2025
Merged
Merged
Merged
@facebook-github-bot
Copy link
Contributor

facebook-github-bot commented Aug 22, 2025

This pull request was exported from Phabricator. Differential Revision: D80800081

@facebook-github-bot
Copy link
Contributor

facebook-github-bot commented Aug 22, 2025

This pull request was exported from Phabricator. Differential Revision: D80800081

1 similar comment
@facebook-github-bot
Copy link
Contributor

facebook-github-bot commented Aug 23, 2025

This pull request was exported from Phabricator. Differential Revision: D80800081

SS-JIA added a commit that referenced this pull request Aug 23, 2025
@SS-JIA
[ET-VK][ez] Fix partitioner logic of finding keepdim arg of reduce ops (
6c1f9fa 
#13598)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* #13595
* #13594
* #13593
* #13600
* #13599
* __->__ #13598

Title says it all. For reduce ops, their signature are not all alike so
some extra legwork needs to be done to identify specific arguments that
need to be checked.

Also included a small update to partitioner logging to improve
debuggability.

Differential Revision:
[D80741737](https://our.internmc.facebook.com/intern/diff/D80741737/)

---------

Co-authored-by: ssjia <[email protected]>
SS-JIA added a commit that referenced this pull request Aug 23, 2025
@SS-JIA
[ET-VK][ez] Support grouped convolutions (#13599)
975a4a3 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* #13595
* #13594
* #13593
* #13600
* __->__ #13599
* #13598

Title says it all!

Differential Revision:
[D80741734](https://our.internmc.facebook.com/intern/diff/D80741734/)

---------

Co-authored-by: ssjia <[email protected]>
SS-JIA added a commit that referenced this pull request Aug 23, 2025
@SS-JIA
[ET-VK][ez] Use XNNPACK's FuseBatchNorm pass (#13600)
bd70337 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* #13595
* #13594
* #13593
* __->__ #13600
* #13599
* #13598

As title. Use XNNPACK's FuseBatchNorm pass since it can fuse into linear
layers as well.

Differential Revision:
[D80741735](https://our.internmc.facebook.com/intern/diff/D80741735/)

Co-authored-by: ssjia <[email protected]>
@SS-JIA
[ET-VK][testing] Add scripts to facilitate operator testiing
d743a6c 
Pull Request resolved: #13593

Title says it all. All scripts to help with building + running operator tests. Also fixes an error with building these tests.

CI will be added at a later date. Currently the tests cannot be built on Linux due to an unrelated error

```
/home/ssjia/Github/executorch/runtime/kernel/test/operator_registry_test.cpp: In member function ‘virtual void OperatorRegistryTest_RegisterKernels_Test::TestBody()’:
/home/ssjia/Github/executorch/runtime/kernel/test/operator_registry_test.cpp:307:20: error: could not convert ‘(executorch::runtime::EValue**)(& kernels)’ from ‘executorch::runtime::EValue**’ to ‘executorch::runtime::Span<executorch::runtime::EValue*>’
  307 |   (*func)(context, kernels);
      |                    ^~~~~~~
      |                    |
      |                    executorch::runtime::EValue**
/home/ssjia/Github/executorch/runtime/kernel/test/operator_registry_test.cpp: In member function ‘virtual void OperatorRegistryTest_RegisterTwoKernels_Test::TestBody()’:
/home/ssjia/Github/executorch/runtime/kernel/test/operator_registry_test.cpp:373:22: error: could not convert ‘(executorch::runtime::EValue**)(& evalues)’ from ‘executorch::runtime::EValue**’ to ‘executorch::runtime::Span<executorch::runtime::EValue*>’
  373 |   (*func_1)(context, evalues);
      |                      ^~~~~~~
      |                      |
      |                      executorch::runtime::EValue**
/home/ssjia/Github/executorch/runtime/kernel/test/operator_registry_test.cpp:384:22: error: could not convert ‘(executorch::runtime::EValue**)(& evalues)’ from ‘executorch::runtime::EValue**’ to ‘executorch::runtime::Span<executorch::runtime::EValue*>’
  384 |   (*func_2)(context, evalues);
      |                      ^~~~~~~
      |                      |
      |                      executorch::runtime::EValue**
[ 66%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cat.cpp.o
/home/ssjia/Github/executorch/runtime/kernel/test/operator_registry_test.cpp: In member function ‘virtual void OperatorRegistryTest_ExecutorUsesKernel_Test::TestBody()’:
/home/ssjia/Github/executorch/runtime/kernel/test/operator_registry_test.cpp:485:20: error: could not convert ‘(executorch::runtime::EValue**)(& kernels)’ from ‘executorch::runtime::EValue**’ to ‘executorch::runtime::Span<executorch::runtime::EValue*>’
  485 |   (*func)(context, kernels);
      |                    ^~~~~~~
      |                    |
      |                    executorch::runtime::EValue**
[ 67%] Building CXX object kernels/portable/CMakeFiles/portable_kernels.dir/cpu/op_cdist_forward.cpp.o
/home/ssjia/Github/executorch/runtime/kernel/test/operator_registry_test.cpp: In member function ‘virtual void OperatorRegistryTest_ExecutorUsesFallbackKernel_Test::TestBody()’:
/home/ssjia/Github/executorch/runtime/kernel/test/operator_registry_test.cpp:513:20: error: could not convert ‘(executorch::runtime::EValue**)(& kernels)’ from ‘executorch::runtime::EValue**’ to ‘executorch::runtime::Span<executorch::runtime::EValue*>’
  513 |   (*func)(context, kernels);
      |                    ^~~~~~~
      |                    |
      |                    executorch::runtime::EValue**
```


@imported-using-ghimport

Differential Revision: [D80800081](https://our.internmc.facebook.com/intern/diff/D80800081/)
ghstack-source-id: 305143839
@SS-JIA SS-JIA changed the base branch from gh/SS-JIA/295/base to main August 23, 2025 14:01
@SS-JIA SS-JIA force-pushed the gh/SS-JIA/295/head branch from 639f1fd to d743a6c Compare August 23, 2025 14:03
@SS-JIA SS-JIA merged commit 818d095 into main Aug 23, 2025
100 of 101 checks passed
@SS-JIA SS-JIA deleted the gh/SS-JIA/295/head branch August 23, 2025 14:03
SS-JIA added a commit that referenced this pull request Aug 23, 2025
@SS-JIA
[ET-VK][ez] Consolidate tensor metadata calculation + buffer binding …
4d095f9 
…code (#13594)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* #13595
* __->__ #13594
* #13593
* #13600
* #13599
* #13598

Differential Revision:
[D80800085](https://our.internmc.facebook.com/intern/diff/D80800085)

Co-authored-by: ssjia <[email protected]>
SS-JIA added a commit that referenced this pull request Aug 23, 2025
@SS-JIA
[ET-VK] Introduce BufferMetadata GLSL struct to abstract tensor lay…
916c207 
…out (#13595)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* __->__ #13595
* #13594
* #13593
* #13600
* #13599
* #13598

Differential Revision:
[D80800082](https://our.internmc.facebook.com/intern/diff/D80800082)

Co-authored-by: ssjia <[email protected]>
SS-JIA added a commit that referenced this pull request Aug 23, 2025
@SS-JIA
[ET-VK][ez] Allow high dimensional tensors (for buffer storage) (#13596)
24d8fb4 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* __->__ #13596
* #13595
* #13594
* #13593
* #13600
* #13599
* #13598

Differential Revision:
[D80800083](https://our.internmc.facebook.com/intern/diff/D80800083)

Co-authored-by: ssjia <[email protected]>
SS-JIA added a commit that referenced this pull request Aug 23, 2025
@SS-JIA
[ET-VK] High dim tensor support for view, unsqueeze, squeeze, clone (#…
ed8cbc0 
…13597)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* __->__ #13597
* #13596
* #13595
* #13594
* #13593
* #13600
* #13599
* #13598

Differential Revision:
[D80800084](https://our.internmc.facebook.com/intern/diff/D80800084)

Co-authored-by: ssjia <[email protected]>
agrima1304 pushed a commit to agrima1304/executorch that referenced this pull request Aug 26, 2025
@SS-JIA @agrima1304
[ET-VK][ez] Fix partitioner logic of finding keepdim arg of reduce ops (
0d4fd84 
pytorch#13598)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* pytorch#13597
* pytorch#13596
* pytorch#13595
* pytorch#13594
* pytorch#13593
* pytorch#13600
* pytorch#13599
* __->__ pytorch#13598

Title says it all. For reduce ops, their signature are not all alike so
some extra legwork needs to be done to identify specific arguments that
need to be checked.

Also included a small update to partitioner logging to improve
debuggability.

Differential Revision:
[D80741737](https://our.internmc.facebook.com/intern/diff/D80741737/)

---------

Co-authored-by: ssjia <[email protected]>
agrima1304 pushed a commit to agrima1304/executorch that referenced this pull request Aug 26, 2025
@SS-JIA @agrima1304
[ET-VK][ez] Support grouped convolutions (pytorch#13599)
bb0ec6e 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* pytorch#13597
* pytorch#13596
* pytorch#13595
* pytorch#13594
* pytorch#13593
* pytorch#13600
* __->__ pytorch#13599
* pytorch#13598

Title says it all!

Differential Revision:
[D80741734](https://our.internmc.facebook.com/intern/diff/D80741734/)

---------

Co-authored-by: ssjia <[email protected]>
agrima1304 pushed a commit to agrima1304/executorch that referenced this pull request Aug 26, 2025
@SS-JIA @agrima1304
[ET-VK][ez] Use XNNPACK's FuseBatchNorm pass (pytorch#13600)
e98da6d 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* pytorch#13597
* pytorch#13596
* pytorch#13595
* pytorch#13594
* pytorch#13593
* __->__ pytorch#13600
* pytorch#13599
* pytorch#13598

As title. Use XNNPACK's FuseBatchNorm pass since it can fuse into linear
layers as well.

Differential Revision:
[D80741735](https://our.internmc.facebook.com/intern/diff/D80741735/)

Co-authored-by: ssjia <[email protected]>
agrima1304 pushed a commit to agrima1304/executorch that referenced this pull request Aug 26, 2025
@SS-JIA @agrima1304
[ET-VK][testing] Add scripts to facilitate operator testiing (pytorch…
67b48c3 
…#13593)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* pytorch#13597
* pytorch#13596
* pytorch#13595
* pytorch#13594
* __->__ pytorch#13593
* pytorch#13600
* pytorch#13599
* pytorch#13598

Differential Revision:
[D80800081](https://our.internmc.facebook.com/intern/diff/D80800081)

Co-authored-by: ssjia <[email protected]>
agrima1304 pushed a commit to agrima1304/executorch that referenced this pull request Aug 26, 2025
@SS-JIA @agrima1304
[ET-VK][ez] Consolidate tensor metadata calculation + buffer binding …
fb99e23 
…code (pytorch#13594)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* pytorch#13597
* pytorch#13596
* pytorch#13595
* __->__ pytorch#13594
* pytorch#13593
* pytorch#13600
* pytorch#13599
* pytorch#13598

Differential Revision:
[D80800085](https://our.internmc.facebook.com/intern/diff/D80800085)

Co-authored-by: ssjia <[email protected]>
agrima1304 pushed a commit to agrima1304/executorch that referenced this pull request Aug 26, 2025
@SS-JIA @agrima1304
[ET-VK] Introduce BufferMetadata GLSL struct to abstract tensor lay…
3a8edfd 
…out (pytorch#13595)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* pytorch#13597
* pytorch#13596
* __->__ pytorch#13595
* pytorch#13594
* pytorch#13593
* pytorch#13600
* pytorch#13599
* pytorch#13598

Differential Revision:
[D80800082](https://our.internmc.facebook.com/intern/diff/D80800082)

Co-authored-by: ssjia <[email protected]>
agrima1304 pushed a commit to agrima1304/executorch that referenced this pull request Aug 26, 2025
@SS-JIA @agrima1304
[ET-VK][ez] Allow high dimensional tensors (for buffer storage) (pyto…
1653dbf 
…rch#13596)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* pytorch#13597
* __->__ pytorch#13596
* pytorch#13595
* pytorch#13594
* pytorch#13593
* pytorch#13600
* pytorch#13599
* pytorch#13598

Differential Revision:
[D80800083](https://our.internmc.facebook.com/intern/diff/D80800083)

Co-authored-by: ssjia <[email protected]>
agrima1304 pushed a commit to agrima1304/executorch that referenced this pull request Aug 26, 2025
@SS-JIA @agrima1304
[ET-VK] High dim tensor support for view, unsqueeze, squeeze, clone (p…
4f7871a 
…ytorch#13597)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* __->__ pytorch#13597
* pytorch#13596
* pytorch#13595
* pytorch#13594
* pytorch#13593
* pytorch#13600
* pytorch#13599
* pytorch#13598

Differential Revision:
[D80800084](https://our.internmc.facebook.com/intern/diff/D80800084)

Co-authored-by: ssjia <[email protected]>
kimishpatel pushed a commit that referenced this pull request Sep 2, 2025
@SS-JIA @kimishpatel
[ET-VK][ez] Fix partitioner logic of finding keepdim arg of reduce ops (
b072ea2 
#13598)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* #13595
* #13594
* #13593
* #13600
* #13599
* __->__ #13598

Title says it all. For reduce ops, their signature are not all alike so
some extra legwork needs to be done to identify specific arguments that
need to be checked.

Also included a small update to partitioner logging to improve
debuggability.

Differential Revision:
[D80741737](https://our.internmc.facebook.com/intern/diff/D80741737/)

---------

Co-authored-by: ssjia <[email protected]>
kimishpatel pushed a commit that referenced this pull request Sep 2, 2025
@SS-JIA @kimishpatel
[ET-VK][ez] Support grouped convolutions (#13599)
2c991db 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* #13595
* #13594
* #13593
* #13600
* __->__ #13599
* #13598

Title says it all!

Differential Revision:
[D80741734](https://our.internmc.facebook.com/intern/diff/D80741734/)

---------

Co-authored-by: ssjia <[email protected]>
kimishpatel pushed a commit that referenced this pull request Sep 2, 2025
@SS-JIA @kimishpatel
[ET-VK][ez] Use XNNPACK's FuseBatchNorm pass (#13600)
708c90e 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* #13595
* #13594
* #13593
* __->__ #13600
* #13599
* #13598

As title. Use XNNPACK's FuseBatchNorm pass since it can fuse into linear
layers as well.

Differential Revision:
[D80741735](https://our.internmc.facebook.com/intern/diff/D80741735/)

Co-authored-by: ssjia <[email protected]>
kimishpatel pushed a commit that referenced this pull request Sep 2, 2025
@SS-JIA @kimishpatel
[ET-VK][testing] Add scripts to facilitate operator testiing (#13593)
4e7d7dd 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* #13595
* #13594
* __->__ #13593
* #13600
* #13599
* #13598

Differential Revision:
[D80800081](https://our.internmc.facebook.com/intern/diff/D80800081)

Co-authored-by: ssjia <[email protected]>
kimishpatel pushed a commit that referenced this pull request Sep 2, 2025
@SS-JIA @kimishpatel
[ET-VK][ez] Consolidate tensor metadata calculation + buffer binding …
90c6b9e 
…code (#13594)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* #13595
* __->__ #13594
* #13593
* #13600
* #13599
* #13598

Differential Revision:
[D80800085](https://our.internmc.facebook.com/intern/diff/D80800085)

Co-authored-by: ssjia <[email protected]>
kimishpatel pushed a commit that referenced this pull request Sep 2, 2025
@SS-JIA @kimishpatel
[ET-VK] Introduce BufferMetadata GLSL struct to abstract tensor lay…
7f6d0b9 
…out (#13595)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* #13596
* __->__ #13595
* #13594
* #13593
* #13600
* #13599
* #13598

Differential Revision:
[D80800082](https://our.internmc.facebook.com/intern/diff/D80800082)

Co-authored-by: ssjia <[email protected]>
kimishpatel pushed a commit that referenced this pull request Sep 2, 2025
@SS-JIA @kimishpatel
[ET-VK][ez] Allow high dimensional tensors (for buffer storage) (#13596)
2c87a78 
Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* #13597
* __->__ #13596
* #13595
* #13594
* #13593
* #13600
* #13599
* #13598

Differential Revision:
[D80800083](https://our.internmc.facebook.com/intern/diff/D80800083)

Co-authored-by: ssjia <[email protected]>
kimishpatel pushed a commit that referenced this pull request Sep 2, 2025
@SS-JIA @kimishpatel
[ET-VK] High dim tensor support for view, unsqueeze, squeeze, clone (#…
56bcd73 
…13597)

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at
bottom):
* __->__ #13597
* #13596
* #13595
* #13594
* #13593
* #13600
* #13599
* #13598

Differential Revision:
[D80800084](https://our.internmc.facebook.com/intern/diff/D80800084)

Co-authored-by: ssjia <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@manuelcandales manuelcandales manuelcandales approved these changes

@larryliu0820 larryliu0820 Awaiting requested review from larryliu0820 larryliu0820 is a code owner

@kirklandsign kirklandsign Awaiting requested review from kirklandsign kirklandsign is a code owner

Assignees

No one assigned

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

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@SS-JIA @facebook-github-bot @manuelcandales