From 6ad01449060db47eaa3a923574798a63e0805007 Mon Sep 17 00:00:00 2001 From: "Christoffer J.L" Date: Wed, 13 May 2026 13:31:51 +0000 Subject: [PATCH] Arm backend: Fix stale docgen generation Update the Ethos-U docgen template to point to the correct tutorial path. This keeps pre-push from regenerating docs with the stale tutorial URL. Signed-off-by: Christoffer J.L Change-Id: I102d9b3b14b6e81a691146731645801a54d2ac69 --- .../docgen/ethos-u/backends-arm-ethos-u-overview.md.in | 4 ++-- .../ethos-u/ethos-u-getting-started-tutorial.md.in | 10 +++++++--- .../backends/arm-ethos-u/arm-ethos-u-overview.md | 4 ++-- .../arm-ethos-u/tutorials/ethos-u-getting-started.md | 1 - 4 files changed, 11 insertions(+), 8 deletions(-) diff --git a/backends/arm/scripts/docgen/ethos-u/backends-arm-ethos-u-overview.md.in b/backends/arm/scripts/docgen/ethos-u/backends-arm-ethos-u-overview.md.in index 1990bc6d946..bb1165f0de6 100644 --- a/backends/arm/scripts/docgen/ethos-u/backends-arm-ethos-u-overview.md.in +++ b/backends/arm/scripts/docgen/ethos-u/backends-arm-ethos-u-overview.md.in @@ -4,7 +4,7 @@ The Arm® Ethos™-U backend targets Edge/IoT-type AI use-cases by enabli [Arm® Ethos™-U55 NPU](https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u55), [Arm® Ethos™-U65 NPU](https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u65), and [Arm® Ethos™-U85 NPU](https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u85), leveraging [TOSA](https://www.mlplatform.org/tosa/) and the [ethos-u-vela](https://pypi.org/project/ethos-u-vela/) graph compiler. This document is a technical reference for using the Ethos-U backend, for a top level view with code examples -please refer to the [Arm Ethos-U Backend Tutorial](https://docs.pytorch.org/executorch/stable/tutorial-arm-ethos-u.html). +please refer to the [Arm Ethos-U Backend Tutorial](tutorials/ethos-u-getting-started.md). ## Features @@ -55,7 +55,7 @@ For more information on quantization, see [Quantization](arm-ethos-u-quantizatio ## Runtime Integration -An example runtime application is available in [examples/arm/executor_runner](https://github.com/pytorch/executorch/blob/main/examples/arm/executor_runner/), and the steps requried for building and deploying it on a FVP it is explained in the previously mentioned [Arm Ethos-U Backend Tutorial](https://docs.pytorch.org/executorch/stable/tutorial-arm-ethos-u.html). +An example runtime application is available in [examples/arm/executor_runner](https://github.com/pytorch/executorch/blob/main/examples/arm/executor_runner/), and the steps requried for building and deploying it on a FVP it is explained in the previously mentioned [Arm Ethos-U Backend Tutorial](tutorials/ethos-u-getting-started.md). The example application is recommended to use for testing basic functionality of your lowered models, as well as a starting point for developing runtime integrations for your own targets. For an in-depth explanation of the architecture of the executor_runner and the steps required for doing such an integration, please refer to [Ethos-U porting guide](https://github.com/pytorch/executorch/blob/main/examples/arm/ethos-u-porting-guide.md). diff --git a/backends/arm/scripts/docgen/ethos-u/ethos-u-getting-started-tutorial.md.in b/backends/arm/scripts/docgen/ethos-u/ethos-u-getting-started-tutorial.md.in index 68b73755317..256cb5756a3 100644 --- a/backends/arm/scripts/docgen/ethos-u/ethos-u-getting-started-tutorial.md.in +++ b/backends/arm/scripts/docgen/ethos-u/ethos-u-getting-started-tutorial.md.in @@ -123,10 +123,14 @@ The example application is by default built with an input of ones, so the expect ## Takeaways In this tutorial you have learned how to use ExecuTorch to export a PyTorch model to an executable that can run on an embedded target, and then run that executable on simulated hardware. -To learn more, check out these learning paths: +To learn more, check out the [ExecuTorch on Arm Practical Labs](https://github.com/arm-education/executorch_on_arm_labs) series. This series provides a structured entry-point to developing with ExecuTorch on Arm, across both CPU and Ethos-U NPU. -https://learn.arm.com/learning-paths/embedded-and-microcontrollers/rpi-llama3/ -https://learn.arm.com/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/ +For quick learning paths showcasing short tutorials: + +- [Run Llama3 on Raspberry Pi 5 with ExecuTorch](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/rpi-llama3/) +- [Visualize Ethos-U NPU Performance on FVP](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/visualizing-ethos-u-performance/) +- [Image Classification with ExecuTorch on NXP i.MX 93 (Ethos-U65)](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/observing-ethos-u-on-nxp/) +- [Image Classification with ExecuTorch on Alif E8 DevKit (Ethos-U85)](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/) ## FAQs diff --git a/docs/source/backends/arm-ethos-u/arm-ethos-u-overview.md b/docs/source/backends/arm-ethos-u/arm-ethos-u-overview.md index faffedece35..a6e53dce000 100644 --- a/docs/source/backends/arm-ethos-u/arm-ethos-u-overview.md +++ b/docs/source/backends/arm-ethos-u/arm-ethos-u-overview.md @@ -4,7 +4,7 @@ The Arm® Ethos™-U backend targets Edge/IoT-type AI use-cases by enabli [Arm® Ethos™-U55 NPU](https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u55), [Arm® Ethos™-U65 NPU](https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u65), and [Arm® Ethos™-U85 NPU](https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u85), leveraging [TOSA](https://www.mlplatform.org/tosa/) and the [ethos-u-vela](https://pypi.org/project/ethos-u-vela/) graph compiler. This document is a technical reference for using the Ethos-U backend, for a top level view with code examples -please refer to the [Arm Ethos-U Backend Tutorial](tutorials/ethos-u-getting-started.md). +please refer to the [Arm Ethos-U Backend Tutorial](tutorials/ethos-u-getting-started.md). ## Features @@ -111,7 +111,7 @@ For more information on quantization, see [Quantization](arm-ethos-u-quantizatio ## Runtime Integration -An example runtime application is available in [examples/arm/executor_runner](https://github.com/pytorch/executorch/blob/main/examples/arm/executor_runner/), and the steps requried for building and deploying it on a FVP it is explained in the previously mentioned [Arm Ethos-U Backend Tutorial](tutorials/ethos-u-getting-started.md). +An example runtime application is available in [examples/arm/executor_runner](https://github.com/pytorch/executorch/blob/main/examples/arm/executor_runner/), and the steps requried for building and deploying it on a FVP it is explained in the previously mentioned [Arm Ethos-U Backend Tutorial](tutorials/ethos-u-getting-started.md). The example application is recommended to use for testing basic functionality of your lowered models, as well as a starting point for developing runtime integrations for your own targets. For an in-depth explanation of the architecture of the executor_runner and the steps required for doing such an integration, please refer to [Ethos-U porting guide](https://github.com/pytorch/executorch/blob/main/examples/arm/ethos-u-porting-guide.md). diff --git a/docs/source/backends/arm-ethos-u/tutorials/ethos-u-getting-started.md b/docs/source/backends/arm-ethos-u/tutorials/ethos-u-getting-started.md index 841827cff9b..fe189a945ee 100644 --- a/docs/source/backends/arm-ethos-u/tutorials/ethos-u-getting-started.md +++ b/docs/source/backends/arm-ethos-u/tutorials/ethos-u-getting-started.md @@ -196,7 +196,6 @@ The example application is by default built with an input of ones, so the expect ## Takeaways In this tutorial you have learned how to use ExecuTorch to export a PyTorch model to an executable that can run on an embedded target, and then run that executable on simulated hardware. - To learn more, check out the [ExecuTorch on Arm Practical Labs](https://github.com/arm-education/executorch_on_arm_labs) series. This series provides a structured entry-point to developing with ExecuTorch on Arm, across both CPU and Ethos-U NPU. For quick learning paths showcasing short tutorials: