Arm backend: Add VGF check environment#19911
Merged
Merged
Conversation
Signed-off-by: Elena Zhelezina <elena.zhelezina@arm.com> Change-Id: I02b655802bcc9b76423d76e7fa3d7e17086dafd7
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19911
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
Bot
added
the
CLA Signed
wwwind
added
partner: arm
Collaborator
Author
|
@digantdesai Could you please review this PR ? |
Collaborator
|
@wwwind the added files might be needed to be added the buck2 files? |
digantdesai
reviewed
Jun 3, 2026
Comment on lines
+127
to
+129
| _check_tosa_serializer(), | ||
| _check_model_converter(), | ||
| _check_model_converter_lib_dir(), |
Contributor
There was a problem hiding this comment.
This is OK, but I would prefer these to be naturally in the the dependent python module, as opposed to a seperate script. The rationale is now someone has to make sure that this script and actual consumers are always in sync, i.e. you don't want to be in a situation where this scripts says check passes but the actual user fails because the new dep isn't part of the sync, for example.
digantdesai
approved these changes
Jun 3, 2026
digantdesai
left a comment
digantdesai
left a comment
Contributor
There was a problem hiding this comment.
Stamping to unblock.
Collaborator
Author
|
Arm smaller_stories_llama fail is known and unrelated and beeing worked on |
Gasoonjia
pushed a commit
that referenced
this pull request
Jun 8, 2026
The VGF backend provides a preflight helper that can be run before export or runtime execution: ```bash python -m executorch.backends.arm.vgf.check_env --aot python -m executorch.backends.arm.vgf.check_env --runtime python -m executorch.backends.arm.vgf.check_env --host-emulator python -m executorch.backends.arm.vgf.check_env --source-build --build-dir cmake-out ``` Use `--aot` before export. It checks that the TOSA serializer and ML SDK model converter are available and that the converter can be launched. Use `--runtime` when debugging Python runtime availability. It checks whether the ExecuTorch runtime backend registry reports VgfBackend as available. Use `--host-emulator` before host-based emulator runs. It checks runtime availability plus Vulkan SDK and ML emulation layer environment variables. Use `--source-build --build-dir <dir>` when debugging a source build. It checks for VGF runtime build prerequisites such as `libvgf` and CMake options including `EXECUTORCH_BUILD_VGF` and `EXECUTORCH_BUILD_VULKAN`. For CI logs or bug reports, add `--json`: ```bash python -m executorch.backends.arm.vgf.check_env --aot --json ``` cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani --------- Signed-off-by: Elena Zhelezina <elena.zhelezina@arm.com>
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.
The VGF backend provides a preflight helper that can be run before export or runtime execution:
Use
--aotbefore export. It checks that the TOSA serializer and ML SDK model converter are available and that the converter can be launched.Use
--runtimewhen debugging Python runtime availability. It checks whether the ExecuTorch runtime backend registry reports VgfBackend as available.Use
--host-emulatorbefore host-based emulator runs. It checks runtime availability plus Vulkan SDK and ML emulation layer environment variables.Use
--source-build --build-dir <dir>when debugging a source build. It checks for VGF runtime build prerequisites such aslibvgfand CMake options includingEXECUTORCH_BUILD_VGFandEXECUTORCH_BUILD_VULKAN.For CI logs or bug reports, add
--json:cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani