diff --git a/backends/vulkan/README.md b/backends/vulkan/README.md index b428333c91..2cfff6a6eb 100644 --- a/backends/vulkan/README.md +++ b/backends/vulkan/README.md @@ -1,4 +1,4 @@ -# ExecuTorch Vulkan Delegate +# Vulkan Backend The ExecuTorch Vulkan delegate is a native GPU delegate for ExecuTorch that is built on top of the cross-platform Vulkan GPU API standard. It is primarily diff --git a/docs/source/concepts.md b/docs/source/concepts.md index 289ecda6d8..4cef25c606 100644 --- a/docs/source/concepts.md +++ b/docs/source/concepts.md @@ -1,4 +1,4 @@ -# ExecuTorch Concepts +# Concepts This page provides an overview of key concepts and terms used throughout the ExecuTorch documentation. It is intended to help readers understand the terminology and concepts used in PyTorch Edge and ExecuTorch. ## Concepts Map diff --git a/docs/source/debug-backend-delegate.md b/docs/source/debug-backend-delegate.md index 68914aaed9..86dddd7586 100644 --- a/docs/source/debug-backend-delegate.md +++ b/docs/source/debug-backend-delegate.md @@ -1,4 +1,4 @@ -# Debug Backend Delegate +# Debugging Delegation We provide a list of util functions to give users insights on what happened to the graph modules during the `to_backend()` stage. diff --git a/docs/source/getting-started-architecture.md b/docs/source/getting-started-architecture.md index 937b5b389f..2472b3547f 100644 --- a/docs/source/getting-started-architecture.md +++ b/docs/source/getting-started-architecture.md @@ -1,4 +1,4 @@ -# High-level Architecture and Components of ExecuTorch +# Architecture and Components This page describes the technical architecture of ExecuTorch and its individual components. This document is targeted towards engineers who are deploying PyTorch model onto edge devices. diff --git a/docs/source/index.rst b/docs/source/index.rst index bcabb5797e..4c42b2d235 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -81,83 +81,53 @@ Topics in this section will help you get started with ExecuTorch. .. toctree:: :glob: :maxdepth: 1 - :caption: Getting Started + :caption: Usage :hidden: getting-started - export-overview - runtime-build-and-cross-compilation - getting-started-faqs + using-executorch-export + using-executorch-android + using-executorch-ios + using-executorch-cpp + using-executorch-troubleshooting .. toctree:: :glob: :maxdepth: 1 - :caption: Tutorials + :caption: Backends :hidden: - tutorials/export-to-executorch-tutorial - running-a-model-cpp-tutorial - extension-module - extension-tensor - tutorials/devtools-integration-tutorial - apple-runtime - demo-apps-ios - demo-apps-android - examples-end-to-end-to-lower-model-to-delegate - tutorial-xnnpack-delegate-lowering - build-run-vulkan - .. - Alphabetical by backend name. Be sure to keep the same order in the - customcarditem entries below. - executorch-arm-delegate-tutorial - build-run-coreml - build-run-mediatek-backend - build-run-mps - build-run-qualcomm-ai-engine-direct-backend - build-run-xtensa - -.. toctree:: - :glob: - :maxdepth: 2 - :caption: Working with LLMs - :hidden: - - Llama - Llama on Android - Llama on iOS - Llama on Android via Qualcomm backend - Intro to LLMs in Executorch - -.. toctree:: - :glob: - :maxdepth: 1 - :caption: API Reference - :hidden: - - export-to-executorch-api-reference - executorch-runtime-api-reference - runtime-python-api-reference - api-life-cycle + native-delegates-executorch-xnnpack-delegate + native-delegates-executorch-coreml-delegate + native-delegates-executorch-mps-delegate + native-delegates-executorch-vulkan-delegate + native-delegates-executorch-arm-ethos-u-delegate + native-delegates-executorch-qualcomm-delegate + native-delegates-executorch-mediatek-delegate + native-delegates-executorch-cadence-delegate .. toctree:: :glob: :maxdepth: 1 - :caption: IR Specification + :caption: Tutorials :hidden: - ir-exir - ir-ops-set-definition - .. toctree:: :glob: :maxdepth: 1 - :caption: Compiler Entry Points + :caption: Developer Tools :hidden: - compiler-delegate-and-partitioner - compiler-backend-dialect - compiler-custom-compiler-passes - compiler-memory-planning + devtools-overview + bundled-io + etrecord + etdump + runtime-profiling + model-debugging + model-inspector + memory-planning-inspection + delegate-debugging + devtools-tutorial .. toctree:: :glob: @@ -171,6 +141,17 @@ Topics in this section will help you get started with ExecuTorch. portable-cpp-programming pte-file-format +.. toctree:: + :glob: + :maxdepth: 1 + :caption: API Reference + :hidden: + + export-to-executorch-api-reference + executorch-runtime-api-reference + runtime-python-api-reference + api-life-cycle + .. toctree:: :glob: :maxdepth: 1 @@ -189,14 +170,24 @@ Topics in this section will help you get started with ExecuTorch. kernel-library-custom-aten-kernel kernel-library-selective-build +.. toctree:: + :glob: + :maxdepth: 2 + :caption: Working with LLMs + :hidden: + + Llama + Llama on Android + Llama on iOS + Llama on Android via Qualcomm backend + Intro to LLMs in Executorch + .. toctree:: :glob: :maxdepth: 1 - :caption: Backend Delegates + :caption: Backend Development :hidden: - native-delegates-executorch-xnnpack-delegate - native-delegates-executorch-vulkan-delegate backend-delegates-integration backend-delegates-dependencies debug-backend-delegate @@ -204,19 +195,22 @@ Topics in this section will help you get started with ExecuTorch. .. toctree:: :glob: :maxdepth: 1 - :caption: Developer Tools + :caption: IR Specification :hidden: - devtools-overview - bundled-io - etrecord - etdump - runtime-profiling - model-debugging - model-inspector - memory-planning-inspection - delegate-debugging - devtools-tutorial + ir-exir + ir-ops-set-definition + +.. toctree:: + :glob: + :maxdepth: 1 + :caption: Compiler Entry Points + :hidden: + + compiler-delegate-and-partitioner + compiler-backend-dialect + compiler-custom-compiler-passes + compiler-memory-planning .. toctree:: :glob: diff --git a/docs/source/native-delegates-executorch-arm-ethos-u-delegate.md b/docs/source/native-delegates-executorch-arm-ethos-u-delegate.md new file mode 100644 index 0000000000..3c48607c18 --- /dev/null +++ b/docs/source/native-delegates-executorch-arm-ethos-u-delegate.md @@ -0,0 +1,3 @@ +# ARM Ethos-U Backend + +Placeholder \ No newline at end of file diff --git a/docs/source/native-delegates-executorch-cadence-delegate.md b/docs/source/native-delegates-executorch-cadence-delegate.md new file mode 100644 index 0000000000..984133e717 --- /dev/null +++ b/docs/source/native-delegates-executorch-cadence-delegate.md @@ -0,0 +1,3 @@ +# Cadence Backend + +Placeholder \ No newline at end of file diff --git a/docs/source/native-delegates-executorch-coreml-delegate.md b/docs/source/native-delegates-executorch-coreml-delegate.md new file mode 100644 index 0000000000..49d05b8fee --- /dev/null +++ b/docs/source/native-delegates-executorch-coreml-delegate.md @@ -0,0 +1,3 @@ +# Core ML Backend + +Placeholder for Core ML delegate docs \ No newline at end of file diff --git a/docs/source/native-delegates-executorch-mediatek-delegate.md b/docs/source/native-delegates-executorch-mediatek-delegate.md new file mode 100644 index 0000000000..da7ab97f2d --- /dev/null +++ b/docs/source/native-delegates-executorch-mediatek-delegate.md @@ -0,0 +1,3 @@ +# MediaTek Backend + +Placeholder \ No newline at end of file diff --git a/docs/source/native-delegates-executorch-mps-delegate.md b/docs/source/native-delegates-executorch-mps-delegate.md new file mode 100644 index 0000000000..e9f8e4e5b2 --- /dev/null +++ b/docs/source/native-delegates-executorch-mps-delegate.md @@ -0,0 +1,3 @@ +# MPS Backend + +Placeholder \ No newline at end of file diff --git a/docs/source/native-delegates-executorch-qualcomm-delegate.md b/docs/source/native-delegates-executorch-qualcomm-delegate.md new file mode 100644 index 0000000000..d39a386345 --- /dev/null +++ b/docs/source/native-delegates-executorch-qualcomm-delegate.md @@ -0,0 +1,3 @@ +# Qualcomm Backend + +Placeholder \ No newline at end of file diff --git a/docs/source/native-delegates-executorch-xnnpack-delegate.md b/docs/source/native-delegates-executorch-xnnpack-delegate.md index 6bfbfa6be3..3e7b737c06 100644 --- a/docs/source/native-delegates-executorch-xnnpack-delegate.md +++ b/docs/source/native-delegates-executorch-xnnpack-delegate.md @@ -1,4 +1,4 @@ -# ExecuTorch XNNPACK delegate +# XNNPACK Backend This is a high-level overview of the ExecuTorch XNNPACK backend delegate. This high performance delegate is aimed to reduce CPU inference latency for ExecuTorch models. We will provide a brief introduction to the XNNPACK library and explore the delegate’s overall architecture and intended use cases. diff --git a/docs/source/tutorials_source/bundled_program.bp b/docs/source/tutorials_source/bundled_program.bp new file mode 100644 index 0000000000..2587278e47 Binary files /dev/null and b/docs/source/tutorials_source/bundled_program.bp differ diff --git a/docs/source/using-executorch-android.md b/docs/source/using-executorch-android.md new file mode 100644 index 0000000000..0af96283f2 --- /dev/null +++ b/docs/source/using-executorch-android.md @@ -0,0 +1,3 @@ +# Using ExecuTorch on Android + +Placeholder for top-level Android documentation \ No newline at end of file diff --git a/docs/source/using-executorch-cpp.md b/docs/source/using-executorch-cpp.md new file mode 100644 index 0000000000..12728a6f57 --- /dev/null +++ b/docs/source/using-executorch-cpp.md @@ -0,0 +1,3 @@ +# Using ExecuTorch with C++ + +Placeholder for top-level C++ documentation \ No newline at end of file diff --git a/docs/source/using-executorch-export.md b/docs/source/using-executorch-export.md new file mode 100644 index 0000000000..1776cf3409 --- /dev/null +++ b/docs/source/using-executorch-export.md @@ -0,0 +1,3 @@ +# Model Export + +Placeholder for top-level export documentation \ No newline at end of file diff --git a/docs/source/using-executorch-ios.md b/docs/source/using-executorch-ios.md new file mode 100644 index 0000000000..79443127e7 --- /dev/null +++ b/docs/source/using-executorch-ios.md @@ -0,0 +1,3 @@ +# Using ExecuTorch on iOS + +Placeholder for top-level iOS documentation \ No newline at end of file diff --git a/docs/source/using-executorch-troubleshooting.md b/docs/source/using-executorch-troubleshooting.md new file mode 100644 index 0000000000..b2549dee57 --- /dev/null +++ b/docs/source/using-executorch-troubleshooting.md @@ -0,0 +1,3 @@ +# Troubleshooting, Profiling, and Optimization + +Placeholder for top-level troubleshooting, profiling, and devtool docs \ No newline at end of file