Merge branch 'release/0.6' into cherry-pick-10176-by-pytorch_bot_bot_

metascroy · web-flow · commit a97b80885235 · 2025-04-15T09:56:22.000-07:00
diff --git a/backends/cadence/README.md b/backends/cadence/README.md
@@ -6,7 +6,7 @@
 
 ## Tutorial
 
-Please follow the [tutorial](https://pytorch.org/executorch/main/build-run-xtensa.html) for more information on how to run models on Cadence/Xtensa DSPs.
+Please follow the [tutorial](https://pytorch.org/executorch/main/backends-cadence) for more information on how to run models on Cadence/Xtensa DSPs.
 
 ## Directory Structure
 
diff --git a/backends/qualcomm/README.md b/backends/qualcomm/README.md
@@ -6,9 +6,9 @@ we reserve the right to modify interfaces and implementations.
 
 This backend is implemented on the top of
 [Qualcomm AI Engine Direct SDK](https://developer.qualcomm.com/software/qualcomm-ai-engine-direct-sdk).
-Please follow [tutorial](../../docs/source/build-run-qualcomm-ai-engine-direct-backend.md) to setup environment, build, and run executorch models by this backend (Qualcomm AI Engine Direct is also referred to as QNN in the source and documentation).
+Please follow [tutorial](../../docs/source/backends-qualcomm.md) to setup environment, build, and run executorch models by this backend (Qualcomm AI Engine Direct is also referred to as QNN in the source and documentation).
 
-A website version of the tutorial is [here](https://pytorch.org/executorch/stable/build-run-qualcomm-ai-engine-direct-backend.html).
+A website version of the tutorial is [here](https://pytorch.org/executorch/main/backends-qualcomm).
 
 ## Delegate Options
 
diff --git a/backends/qualcomm/setup.md b/backends/qualcomm/setup.md
@@ -1,6 +1,6 @@
 # Setting up QNN Backend
 
-Please refer to [Building and Running ExecuTorch with Qualcomm AI Engine Direct Backend](../../docs/source/build-run-qualcomm-ai-engine-direct-backend.md).
+Please refer to [Building and Running ExecuTorch with Qualcomm AI Engine Direct Backend](../../docs/source/backends-qualcomm.md).
 
 That is a tutorial for building and running Qualcomm AI Engine Direct backend,
 including compiling a model on a x64 host and running the inference
diff --git a/backends/xnnpack/README.md b/backends/xnnpack/README.md
@@ -132,5 +132,5 @@ create an issue on [github](https://www.github.com/pytorch/executorch/issues).
 
 ## See Also
 For more information about the XNNPACK Backend, please check out the following resources:
-- [XNNPACK Backend](https://pytorch.org/executorch/main/backends-xnnpack.html)
-- [XNNPACK Backend Internals](https://pytorch.org/executorch/main/backend-delegates-xnnpack-reference.html)
+- [XNNPACK Backend](https://pytorch.org/executorch/main/backends-xnnpack)
+- [XNNPACK Backend Internals](https://pytorch.org/executorch/main/backend-delegates-xnnpack-reference)
diff --git a/docs/README.md b/docs/README.md
@@ -130,7 +130,7 @@ Use the
 to contribute to the documentation.
 
 In addition to that, see
-[Markdown in Sphinx Tips and Tricks](https://pytorch.org/executorch/markdown-sphinx-tips-tricks.html)
+[Markdown in Sphinx Tips and Tricks](source/markdown-sphinx-tips-tricks.md)
 for tips on how to author high-quality markdown pages with Myst Parser.
 
 ## Adding Tutorials
diff --git a/docs/source/llm/getting-started.md b/docs/source/llm/getting-started.md
@@ -588,7 +588,7 @@ The delegated model should be noticeably faster compared to the non-delegated mo
 
 For more information regarding backend delegation, see the ExecuTorch guides
 for the [XNNPACK Backend](../backends-xnnpack.md),  [Core ML
-Backend](../backends-coreml.md) and [Qualcomm AI Engine Direct Backend](build-run-llama3-qualcomm-ai-engine-direct-backend.md).
+Backend](../backends-coreml.md) and [Qualcomm AI Engine Direct Backend](../backends-qualcomm.md).
 
 ## Quantization
 
diff --git a/docs/source/tutorials_source/README.txt b/docs/source/tutorials_source/README.txt
@@ -3,4 +3,4 @@ Tutorials
 
 1. tutorials/*
        Getting Started Tutorials
-       https://pytorch.org/executorch/tutorials/template_tutorial.html
+       https://github.com/pytorch/executorch/blob/main/docs/source/tutorials_source/template_tutorial.py
diff --git a/examples/README.md b/examples/README.md
@@ -71,7 +71,7 @@ You will find demos of [ExecuTorch QNN Backend](./qualcomm) in the [`qualcomm/`]
 
 ### Cadence HiFi4 DSP
 
-The [`Cadence/`](./cadence) directory hosts a demo that showcases the process of exporting and executing a model on Xtensa Hifi4 DSP. You can utilize [this tutorial](../docs/source/build-run-xtensa.md) to guide you in configuring the demo and running it.
+The [`Cadence/`](./cadence) directory hosts a demo that showcases the process of exporting and executing a model on Xtensa Hifi4 DSP. You can utilize [this tutorial](../docs/source/backends-cadence.md) to guide you in configuring the demo and running it.
 
 ## Dependencies
 
diff --git a/examples/arm/README.md b/examples/arm/README.md
@@ -34,6 +34,6 @@ $ executorch/examples/arm/run.sh --model_name=mv2 --target=ethos-u85-128 [--scra
 
 ### Online Tutorial
 
-We also have a [tutorial](https://pytorch.org/executorch/stable/executorch-arm-delegate-tutorial.html) explaining the steps performed in these
+We also have a [tutorial](https://pytorch.org/executorch/main/backends-arm-ethos-u) explaining the steps performed in these
 scripts, expected results, possible problems and more. It is a step-by-step guide
 you can follow to better understand this delegate.
diff --git a/examples/models/efficient_sam/README.md b/examples/models/efficient_sam/README.md
@@ -12,7 +12,7 @@ Follow the [tutorial](https://pytorch.org/executorch/main/getting-started-setup#
 
 ### Exporting to Core ML
 
-Make sure to install the [required dependencies](https://pytorch.org/executorch/main/build-run-coreml.html#setting-up-your-developer-environment) for Core ML export.
+Make sure to install the [required dependencies](https://pytorch.org/executorch/main/backends-coreml#development-requirements) for Core ML export.
 
 To export the model to Core ML, run the following command:
 
diff --git a/examples/models/llama/UTILS.md b/examples/models/llama/UTILS.md
@@ -25,7 +25,7 @@ From `executorch` root:
 ## Smaller model delegated to other backends
 
 Currently we supported lowering the stories model to other backends, including, CoreML, MPS and QNN. Please refer to the instruction
-for each backend ([CoreML](https://pytorch.org/executorch/main/build-run-coreml.html), [MPS](https://pytorch.org/executorch/main/build-run-mps.html), [QNN](https://pytorch.org/executorch/main/build-run-qualcomm-ai-engine-direct-backend.html)) before trying to lower them. After the backend library is installed, the script to export a lowered model is
+for each backend ([CoreML](https://pytorch.org/executorch/main/backends-coreml), [MPS](https://pytorch.org/executorch/main/backends-mps), [QNN](https://pytorch.org/executorch/main/backends-qualcomm)) before trying to lower them. After the backend library is installed, the script to export a lowered model is
 
 - Lower to CoreML: `python -m examples.models.llama.export_llama -kv --disable_dynamic_shape --coreml -c stories110M.pt -p params.json `
 - MPS: `python -m examples.models.llama.export_llama -kv --disable_dynamic_shape --mps -c stories110M.pt -p params.json `
diff --git a/examples/models/phi-3-mini-lora/README.md b/examples/models/phi-3-mini-lora/README.md
@@ -16,8 +16,9 @@ To see how you can use the model exported for training in a fully involved finet
 python export_model.py
 ```
 
-2. Run the inference model using an example runtime. For more detailed steps on this, check out [Build & Run](https://pytorch.org/executorch/stable/getting-started-setup.html#build-run).
+2. Run the inference model using an example runtime. For more detailed steps on this, check out [Building from Source](https://pytorch.org/executorch/main/using-executorch-building-from-source).
 ```
+
 # Clean and configure the CMake build system. Compiled programs will appear in the executorch/cmake-out directory we create here.
 ./install_executorch.sh --clean
 (mkdir cmake-out && cd cmake-out && cmake ..)
diff --git a/examples/qualcomm/README.md b/examples/qualcomm/README.md
@@ -24,13 +24,13 @@ Here are some general information and limitations.
 
 Please finish tutorial [Setting up executorch](https://pytorch.org/executorch/stable/getting-started-setup).
 
-Please finish [setup QNN backend](../../docs/source/build-run-qualcomm-ai-engine-direct-backend.md).
+Please finish [setup QNN backend](../../docs/source/backends-qualcomm.md).
 
 ## Environment
 
 Please set up `QNN_SDK_ROOT` environment variable.
 Note that this version should be exactly same as building QNN backend.
-Please check [setup](../../docs/source/build-run-qualcomm-ai-engine-direct-backend.md).
+Please check [setup](../../docs/source/backends-qualcomm.md).
 
 Please set up `LD_LIBRARY_PATH` to `$QNN_SDK_ROOT/lib/x86_64-linux-clang`.
 Or, you could put QNN libraries to default search path of the dynamic linker.
diff --git a/examples/qualcomm/oss_scripts/llama/README.md b/examples/qualcomm/oss_scripts/llama/README.md
@@ -28,7 +28,7 @@ Hybrid Mode: Hybrid mode leverages the strengths of both AR-N model and KV cache
 
 ### Step 1: Setup
 1. Follow the [tutorial](https://pytorch.org/executorch/main/getting-started-setup) to set up ExecuTorch.
-2. Follow the [tutorial](https://pytorch.org/executorch/stable/build-run-qualcomm-ai-engine-direct-backend.html) to build Qualcomm AI Engine Direct Backend.
+2. Follow the [tutorial](https://pytorch.org/executorch/main/backends-qualcomm) to build Qualcomm AI Engine Direct Backend.
 
 ### Step 2: Prepare Model
 
diff --git a/examples/qualcomm/qaihub_scripts/llama/README.md b/examples/qualcomm/qaihub_scripts/llama/README.md
@@ -12,7 +12,7 @@ Note that the pre-compiled context binaries could not be futher fine-tuned for o
 ### Instructions
 #### Step 1: Setup
 1. Follow the [tutorial](https://pytorch.org/executorch/main/getting-started-setup) to set up ExecuTorch.
-2. Follow the [tutorial](https://pytorch.org/executorch/stable/build-run-qualcomm-ai-engine-direct-backend.html) to build Qualcomm AI Engine Direct Backend.
+2. Follow the [tutorial](https://pytorch.org/executorch/main/backends-qualcomm) to build Qualcomm AI Engine Direct Backend.
 
 #### Step2: Prepare Model
 1. Create account for https://aihub.qualcomm.com/
@@ -40,7 +40,7 @@ Note that the pre-compiled context binaries could not be futher fine-tuned for o
 ### Instructions
 #### Step 1: Setup
 1. Follow the [tutorial](https://pytorch.org/executorch/main/getting-started-setup) to set up ExecuTorch.
-2. Follow the [tutorial](https://pytorch.org/executorch/stable/build-run-qualcomm-ai-engine-direct-backend.html) to build Qualcomm AI Engine Direct Backend.
+2. Follow the [tutorial](https://pytorch.org/executorch/main/backends-qualcomm) to build Qualcomm AI Engine Direct Backend.
 
 #### Step2: Prepare Model
 1. Create account for https://aihub.qualcomm.com/
diff --git a/examples/qualcomm/qaihub_scripts/stable_diffusion/README.md b/examples/qualcomm/qaihub_scripts/stable_diffusion/README.md
@@ -11,7 +11,7 @@ The model architecture, scheduler, and time embedding are from the [stabilityai/
 ### Instructions
 #### Step 1: Setup
 1. Follow the [tutorial](https://pytorch.org/executorch/main/getting-started-setup) to set up ExecuTorch.
-2. Follow the [tutorial](https://pytorch.org/executorch/stable/build-run-qualcomm-ai-engine-direct-backend.html) to build Qualcomm AI Engine Direct Backend.
+2. Follow the [tutorial](https://pytorch.org/executorch/main/backends-qualcomm) to build Qualcomm AI Engine Direct Backend.
 
 #### Step2: Prepare Model
 1. Download the context binaries for TextEncoder, UNet, and VAEDecoder under https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/tree/main
diff --git a/examples/qualcomm/qaihub_scripts/utils/README.md b/examples/qualcomm/qaihub_scripts/utils/README.md
@@ -1,6 +1,6 @@
 # CLI Tool for Compile / Deploy Pre-Built QNN Artifacts
 
-An easy-to-use tool for generating / executing .pte program from pre-built model libraries / context binaries from Qualcomm AI Engine Direct. Tool is verified with [host environement](../../../../docs/source/build-run-qualcomm-ai-engine-direct-backend.md#host-os).
+An easy-to-use tool for generating / executing .pte program from pre-built model libraries / context binaries from Qualcomm AI Engine Direct. Tool is verified with [host environement](../../../../docs/source/backends-qualcomm.md#host-os).
 
 ## Description
 
@@ -20,7 +20,7 @@ If users are interested in well-known applications, [Qualcomm AI HUB](https://ai
 ### Dependencies
 
 * Register for Qualcomm AI HUB.
-* Download the corresponding QNN SDK via [link](https://www.qualcomm.com/developer/software/qualcomm-ai-engine-direct-sdk) which your favorite model is compiled with. Ths link will automatically download the latest version at this moment (users should be able to specify version soon, please refer to [this](../../../../docs/source/build-run-qualcomm-ai-engine-direct-backend.md#software) for earlier releases).
+* Download the corresponding QNN SDK via [link](https://www.qualcomm.com/developer/software/qualcomm-ai-engine-direct-sdk) which your favorite model is compiled with. Ths link will automatically download the latest version at this moment (users should be able to specify version soon, please refer to [this](../../../../docs/source/backends-qualcomm.md#software) for earlier releases).
 
 ### Target Model
 
diff --git a/examples/xnnpack/README.md b/examples/xnnpack/README.md
@@ -1,8 +1,8 @@
 # XNNPACK Backend
 
 [XNNPACK](https://github.com/google/XNNPACK) is a library of optimized neural network operators for ARM and x86 CPU platforms. Our delegate lowers models to run using these highly optimized CPU operators. You can try out lowering and running some example models in the demo. Please refer to the following docs for information on the XNNPACK Delegate
-- [XNNPACK Backend Delegate Overview](https://pytorch.org/executorch/stable/native-delegates-executorch-xnnpack-delegate.html)
-- [XNNPACK Delegate Export Tutorial](https://pytorch.org/executorch/stable/tutorial-xnnpack-delegate-lowering.html)
+- [XNNPACK Backend Delegate Overview](https://pytorch.org/executorch/main/backends-xnnpack)
+- [XNNPACK Delegate Export Tutorial](https://pytorch.org/executorch/main/tutorial-xnnpack-delegate-lowering)
 
 
 ## Directory structure
diff --git a/extension/llm/export/partitioner_lib.py b/extension/llm/export/partitioner_lib.py
@@ -57,7 +57,7 @@ def get_mps_partitioner(use_kv_cache: bool = False):
         )
     except ImportError:
         raise ImportError(
-            "Please install the MPS backend follwing https://pytorch.org/executorch/main/build-run-mps.html"
+            "Please install the MPS backend follwing https://pytorch.org/executorch/main/backends-mps"
         )
 
     compile_specs = [CompileSpec("use_fp16", bytes([True]))]
@@ -81,7 +81,7 @@ def get_coreml_partitioner(
         )
     except ImportError:
         raise ImportError(
-            "Please install the CoreML backend follwing https://pytorch.org/executorch/main/build-run-coreml.html"
+            "Please install the CoreML backend follwing https://pytorch.org/executorch/main/backends-coreml"
             + "; for buck users, please add example dependancies: //executorch/backends/apple/coreml:backend, and etc"
         )
 
@@ -195,7 +195,7 @@ def get_qnn_partitioner(
         )
     except ImportError:
         raise ImportError(
-            "Please install the Qualcomm backend following https://pytorch.org/executorch/main/build-run-qualcomm-ai-engine-direct-backend.html"
+            "Please install the Qualcomm backend following https://pytorch.org/executorch/main/backends-qualcomm"
         )
 
     use_fp16 = True
diff --git a/extension/llm/export/quantizer_lib.py b/extension/llm/export/quantizer_lib.py
@@ -158,7 +158,7 @@ def get_qnn_quantizer(
 
     except ImportError:
         raise ImportError(
-            "Please install the Qualcomm backend follwing https://pytorch.org/executorch/main/build-run-qualcomm.html"
+            "Please install the Qualcomm backend follwing https://pytorch.org/executorch/main/backends-qualcomm"
         )
 
     backend, quant_config = pt2e_quantize.split("_")
@@ -217,7 +217,7 @@ def get_coreml_quantizer(pt2e_quantize: str):
         from executorch.backends.apple.coreml.quantizer import CoreMLQuantizer
     except ImportError:
         raise ImportError(
-            "Please install the CoreML backend follwing https://pytorch.org/executorch/main/build-run-coreml.html"
+            "Please install the CoreML backend follwing https://pytorch.org/executorch/main/backends-coreml"
         )
 
     if pt2e_quantize == "coreml_8a_c8w":
