Arm backend: Update examples/arm/README.md#19756
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19756
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (3 Unrelated Failures)As of commit ba894af with merge base ee4c90a ( 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. |
|
|
@pytorchbot label ciflow/trunk |
|
@pytorchbot label "partner: arm" |
|
@pytorchbot label "release notes: arm" |
There was a problem hiding this comment.
Pull request overview
This PR streamlines the Arm examples documentation by making examples/arm/README.md more concise (setup/run usage, example notebooks/apps/utilities) and relocating broader “getting started” documentation links into the Arm backend README.
Changes:
- Rewrote
examples/arm/README.mdto focus onsetup.sh/run.shusage and to index notebooks, applications, and helper scripts. - Updated
backends/arm/README.mdto point to the hosted Arm backend tutorials/overview pages and to link the Ethos-U porting guide.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| examples/arm/README.md | Condenses setup/run guidance and adds a curated index of example notebooks/apps/utilities. |
| backends/arm/README.md | Replaces local doc paths with hosted documentation links and adds a porting guide link. |
Comments suppressed due to low confidence (5)
examples/arm/README.md:20
setup.shgenerates setup-path scripts atarm-scratch/setup_path.{sh|fish}(see setup.sh log message). The README currently says it generatessetup_path.shscripts, which is slightly inaccurate and may hide the fish variant. Consider referencingsetup_path.{sh|fish}orsetup_path.sh/setup_path.fishexplicitly.
`setup.sh` downloads the Arm cross-compilation toolchain and Corstone FVP
simulators, installs the Python dependencies for TOSA, Ethos-U Vela, and
Cortex-M/CMSIS-NN, and generates `setup_path.sh` scripts for adding those tools
to your environment. Optional flags also install VGF/MLSDK and Vulkan
dependencies.
examples/arm/README.md:80
- Markdown list formatting looks off here: the nested "-" plus the following continuation lines are inconsistently indented, which can render as a separate list item/paragraph. Consider using the same "- link - description" pattern as the other entries and wrap the description with proper indentation.
- [image_classification_example_ethos_u](image_classification_example_ethos_u/)
- End-to-end DEiT-Tiny image classification flow for Ethos-U, including
model fine-tuning, export, bare-metal runtime build, and Corstone-320 FVP
execution.
- [image_classification_example_vgf](image_classification_example_vgf/) -
examples/arm/README.md:34
- Docs wording may be misleading here:
run.shinvokes the Arm AOT compiler viapython3 -m backends.arm.scripts.aot_arm_compiler(see run.sh), whileexamples/arm/aot_arm_compiler.pyexists only as a deprecated compatibility wrapper. Consider calling out the canonical module/path to avoid steering users to the deprecated wrapper.
`run.sh` is an end-to-end helper for building and executing an Arm backend
example. It sources the `setup_path.sh` script generated by `setup.sh`, runs
`aot_arm_compiler.py` to convert the selected model to a `.pte` or `.bpte`,
builds the matching runner with CMake, and starts the simulator or runtime for
examples/arm/README.md:83
- Link style inconsistency: this list uses trailing slashes for other directories (e.g.,
image_classification_example_vgf/) butsuper_resolution_example_vgfis linked without/. Using a consistent directory link style avoids confusion and works more reliably across different Markdown renderers.
- [image_classification_example_vgf](image_classification_example_vgf/) -
DEiT-Tiny image classification flow for VGF host execution.
- [super_resolution_example_vgf](super_resolution_example_vgf) - Swin2SR image
super-resolution.
examples/arm/README.md:94
- Broken link:
composable_quantizer_example.pyis referenced here, but there is no such file underexamples/arm/(and a repo-wide search only finds this mention). Either add the script or update/remove the link to point at the correct location.
- [export_standalone_tosa_graph.py](export_standalone_tosa_graph.py) -
Example of exporting a standalone TOSA graph with multiple outputs.
- [composable_quantizer_example.py](composable_quantizer_example.py) - Minimal
script showing experimental composable quantizer use.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| targets (using TOSA) but you can also use the Ethos-U example runner as an example | ||
| on Cortex-M if you do not delegate the model. | ||
| This directory contains documentation and scripts to | ||
| help you setup and run a PyTorch model on the Arm backend |
| - [Arm Ethos-U tutorial](https://docs.pytorch.org/executorch/stable/backends/arm-ethos-u/tutorials/ethos-u-getting-started.html) | ||
| - [Arm VGF tutorial](https://docs.pytorch.org/executorch/stable/backends/arm-vgf/tutorials/vgf-getting-started.html) | ||
| - [Arm Cortex-M backend overview](https://docs.pytorch.org/executorch/stable/backends/arm-cortex-m/arm-cortex-m-overview.html) | ||
| - [Ethos-U porting guide](https://github.com/pytorch/executorch/blob/main/examples/arm/ethos-u-porting-guide.md) |
Make the README concise for setup, run.sh usage, example notebooks, applications, and helper scripts. Move broader backend documentation links to the backend README. Signed-off-by: Martin Lindström <Martin.Lindstroem@arm.com> Change-Id: I6ec93eb0e0afcacc7bc114a7593366683a85f3fb
d40f6f1 to
ba894af
Compare
Make the README concise for setup, run.sh usage, example notebooks, applications, and helper scripts. Move broader backend documentation links to the backend README.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani