Skip to content

Conversation

@mansnils
Copy link
Collaborator

@mansnils mansnils commented Nov 4, 2025

New setup option is added: --install-mlsdk-deps-with-pip
For Linux/Windows x86 machines, PyPi packages of MLSDK repository for VGF backend may be used.
This will eventually be the default. Reason it is not yet default is because of a limitation of model-converter to handle large models. The new option will decrease setup time, which can enable VGF backend testing in github.

Co-authored-by: Per Held <per.held@arm.com>, Ryan O'Shea <ryan.oshea3@arm.com>

cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai

For Linux/Windows x86 machines, PyPi packages of
MLSDK repository for VGF backend may be used.
This will eventually be the default.
Reason it is not yet default is because of a limitation of
model-converter to handle large models.

Signed-off-by: Måns Nilsson <mans.nilsson@arm.com>
Co-authored-by: Per Held <per.held@arm.com>, Ryan O'Shea <ryan.oshea3@arm.com>
Change-Id: I292bf74a3db9c129ac9bc7550575cfae6f85e9a0
@mansnils mansnils added partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm ciflow/trunk release notes: arm Changes to the ARM backend delegate labels Nov 4, 2025
@pytorch-bot
Copy link

pytorch-bot bot commented Nov 4, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15551

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

❌ 1 Cancelled Job, 5 Unrelated Failures

As of commit 3a7584f with merge base dcc9a91 (image):

CANCELLED JOB - The following job was cancelled. Please retry:

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

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

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 Nov 4, 2025
@zingo
Copy link
Collaborator

zingo commented Nov 4, 2025

Hi @SS-JIA this is a PR you might want to test internally if you tests VGF backend.

@zingo
Copy link
Collaborator

zingo commented Nov 6, 2025

@SS-JIA Some background: This is needed to be able to add test for VGF backend, currently installing and building VGF tools from source take too long on GitHub to be useful (e.g. jobs times out), but with this we can install a pip packages for most of it and we hope it will be fast enough (like minutes or even seconds) to be able to start adding unit/trunk tests and maybe even the new backend suit tests for VGF. :)

@zingo
Copy link
Collaborator

zingo commented Nov 7, 2025

Failed tests are unrelated

@zingo zingo merged commit 0bd635e into pytorch:main Nov 7, 2025
291 of 299 checks passed
metascroy added a commit that referenced this pull request Nov 7, 2025
metascroy added a commit that referenced this pull request Nov 7, 2025
…#15681)

Reverts #15551

This is causing internal test failures:

* Error outside of ExecuTorch: ModuleNotFoundError: No module named
'executorch.backends.arm.vgf.model_converter'

Errors inside of ExecuTorch:
* buck test '@fbcode//mode/opt' fbcode//executorch/backends/arm/test:cos
* buck test '@fbcode//mode/opt'
fbcode//executorch/backends/arm/test:custom_partition
* buck test '@fbcode//mode/opt'
fbcode//executorch/backends/arm/test:debug_hook
* buck test '@fbcode//mode/opt'
fbcode//executorch/backends/arm/test:decompose_avg_pool2d_pass
* buck test '@fbcode//mode/opt'
fbcode//executorch/backends/arm/test:decompose_cosine_similarity_pass
* buck test '@fbcode//mode/opt'
fbcode//executorch/backends/arm/test:decompose_div_pass
* buck test '@fbcode//mode/opt'
fbcode//executorch/backends/arm/test:decompose_layernorm_pass
* buck test '@fbcode//mode/opt'
fbcode//executorch/backends/arm/test:decompose_linalg_vector_norm_pass
@SS-JIA
Copy link
Contributor

SS-JIA commented Nov 7, 2025

@mansnils @zingo Unfortunately seems like I was wrong, this PR did break some internal tests. Would you guys mind creating the PR once more, and I'll import + see what needs to be done to fix the failures!

@zingo
Copy link
Collaborator

zingo commented Nov 7, 2025

Go ahead we have not merged the followup PRs that start using this yet so it will probably not be that messy, e.g. only need to rever this so get stuff back to a working state and we reinvestigte, sorry it broke stuff.

@zingo
Copy link
Collaborator

zingo commented Nov 7, 2025

Thanks a lot @metascroy for adding the internal fails to the revert PR, with a bit of luck it gives some help resloving this.
I really like it.

This is causing internal test failures:

Error outside of ExecuTorch: ModuleNotFoundError: No module named 'executorch.backends.arm.vgf.model_converter'
Errors inside of ExecuTorch:

buck test '@fbcode//mode/opt' fbcode//executorch/backends/arm/test:cos
buck test '@fbcode//mode/opt' fbcode//executorch/backends/arm/test:custom_partition
buck test '@fbcode//mode/opt' fbcode//executorch/backends/arm/test:debug_hook
buck test '@fbcode//mode/opt' fbcode//executorch/backends/arm/test:decompose_avg_pool2d_pass
buck test '@fbcode//mode/opt' fbcode//executorch/backends/arm/test:decompose_cosine_similarity_pass
buck test '@fbcode//mode/opt' fbcode//executorch/backends/arm/test:decompose_div_pass
buck test '@fbcode//mode/opt' fbcode//executorch/backends/arm/test:decompose_layernorm_pass
buck test '@fbcode//mode/opt' fbcode//executorch/backends/arm/test:decompose_linalg_vector_norm_pass

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

Labels

ciflow/trunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm release notes: arm Changes to the ARM backend delegate

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants