Update base for Update on "[cortex-m] Add scalar c++ op for quantize_per_tensor"

Only buck build for now, CMake is next.
No MVE, scalar only.
Strictly the dtypes we care about update arg_meta to reflect that.

Differential Revision: [D73141767](https://our.internmc.facebook.com/intern/diff/D73141767/)

**NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D73141767/)!

[ghstack-poisoned]

Author: digantdesai

.github/workflows/android-release-artifacts.yml

@@ -11,6 +11,11 @@ on:
         description: Upload the AAR to maven staging repository
         required: false
         type: boolean
+      flavor:
+        type: choice
+        options:
+          - "xnnpack"
+          - "vulkan+xnnpack"
   schedule:
     - cron: 0 10 * * *
 
@@ -86,6 +91,11 @@ jobs:
           sed -i "s/\(coordinates(\"org.pytorch\", \"executorch-android\", \"\)\([0-9]\+.[0-9]\+.[0-9]\+\)\(\")\)/\1$VERSION\3/" extension/android/executorch_android/build.gradle
         fi
 
+        FLAVOR="${{ inputs.flavor }}"
+        if [[ "$FLAVOR" == "vulkan+xnnpack" ]]; then
+          export EXECUTORCH_BUILD_VULKAN=ON
+        fi
+
         # Build AAR Package
         mkdir aar-out
         export BUILD_AAR_DIR=aar-out

.github/workflows/doc-build.yml

@@ -14,6 +14,20 @@ on:
     - cron: '0 0 * * *'
 
 jobs:
+  check-urls:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Check URLs
+        run: bash ./scripts/check_urls.sh
+
+  check-links:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Check Links
+        run: bash ./scripts/check_links.sh
+
   build:
     uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
     permissions:

CONTRIBUTING.md

@@ -45,11 +45,11 @@ executorch
 │   └── <a href="devtools/visualization">visualization</a> - Visualization tools for representing model structure and performance metrics.
 ├── <a href="docs">docs</a> - Static docs tooling and documentation source files.
 ├── <a href="examples">examples</a> - Examples of various user flows, such as model export, delegates, and runtime execution.
-├── <a href="exir">exir</a> - Ahead-of-time library: model capture and lowering APIs. EXport Intermediate Representation (EXIR) is a format for representing the result of <a href="https://pytorch.org/docs/stable/export.html">torch.export</a>. This directory contains utilities and passes for lowering the EXIR graphs into different <a href="/docs/source/ir-exir.md">dialects</a> and eventually suitable to run on target hardware.
+├── <a href="exir">exir</a> - Ahead-of-time library: model capture and lowering APIs. EXport Intermediate Representation (EXIR) is a format for representing the result of <a href="https://pytorch.org/docs/stable/export.html">torch.export</a>. This directory contains utilities and passes for lowering the EXIR graphs into different <a href="docs/source/ir-exir.md">dialects</a> and eventually suitable to run on target hardware.
 │   ├── <a href="exir/_serialize">_serialize</a> - Serialize final export artifact.
 │   ├── <a href="exir/backend">backend</a> - Backend delegate ahead of time APIs.
 │   ├── <a href="exir/capture">capture</a> - Program capture.
-│   ├── <a href="exir/dialects">dialects</a> - Op sets for various dialects in the export process. Please refer to the <a href="/docs/source/ir-exir.md">EXIR spec</a> and the <a href="/docs/source/compiler-backend-dialect.md">backend dialect</a> doc for more details.
+│   ├── <a href="exir/dialects">dialects</a> - Op sets for various dialects in the export process. Please refer to the <a href="docs/source/ir-exir.md">EXIR spec</a> and the <a href="docs/source/compiler-backend-dialect.md">backend dialect</a> doc for more details.
 │   ├── <a href="exir/emit">emit</a> - Conversion from ExportedProgram to ExecuTorch execution instructions.
 │   ├── <a href="exir/operator">operator</a> - Operator node manipulation utilities.
 │   ├── <a href="exir/passes">passes</a> - Built-in compiler passes.
@@ -68,7 +68,7 @@ executorch
 │   ├── <a href="extension/memory_allocator">memory_allocator</a> - 1st party memory allocator implementations.
 │   ├── <a href="extension/module">module</a> - A simplified C++ wrapper for the runtime. An abstraction that deserializes and executes an ExecuTorch artifact (.pte file). Refer to the <a href="docs/source/extension-module.md">module documentation</a> for more information.
 │   ├── <a href="extension/parallel">parallel</a> - C++ threadpool integration.
-│   ├── <a href="extension/pybindings">pybindings</a> - Python API for executorch runtime. This is powering up the <a href="docs/source/runtime-python-api-reference.md">runtime Python API</a> for ExecuTorch.
+│   ├── <a href="extension/pybindings">pybindings</a> - Python API for executorch runtime. This is powering up the <a href="docs/source/runtime-python-api-reference.rst">runtime Python API</a> for ExecuTorch.
 │   ├── <a href="extension/pytree">pytree</a> - C++ and Python flattening and unflattening lib for pytrees.
 │   ├── <a href="extension/runner_util">runner_util</a> - Helpers for writing C++ PTE-execution tools.
 │   ├── <a href="extension/tensor">tensor</a> - Tensor maker and <code>TensorPtr</code>, details in <a href="docs/source/extension-tensor.md">this documentation</a>. For how to use <code>TensorPtr</code> and <code>Module</code>, please refer to the <a href="docs/source/using-executorch-cpp.md">"Using ExecuTorch with C++"</a> doc.
@@ -114,7 +114,7 @@ If you're completely new to open-source projects, GitHub, or ExecuTorch, please
 1. If you've changed APIs or added a new tool or feature, [update the
    documentation](#updating-documentation).
 1. If you added an experimental API or deprecated an existing API, follow the
-   [API Life Cycle and Deprecation Policy](/docs/source/api-life-cycle.md).
+   [API Life Cycle and Deprecation Policy](docs/source/api-life-cycle.md).
 1. Make sure your code follows the [style guides](#coding-style) and passes the
    [lint checks](#lintrunner).
 1. If you haven't already, complete the [Contributor License Agreement ("CLA")](#contributor-license-agreement-cla).

README-wheel.md

@@ -25,6 +25,6 @@ tutorials and documentation. Here are some starting points:
 * [Exporting to ExecuTorch](https://pytorch.org/executorch/main/tutorials/export-to-executorch-tutorial)
   * Learn the fundamentals of exporting a PyTorch `nn.Module` to ExecuTorch, and
     optimizing its performance using quantization and hardware delegation.
-* Running LLaMA on [iOS](docs/source/llm/llama-demo-ios) and [Android](docs/source/llm/llama-demo-android) devices.
+* Running LLaMA on [iOS](docs/source/llm/llama-demo-ios.md) and [Android](docs/source/llm/llama-demo-android.md) devices.
   * Build and run LLaMA in a demo mobile app, and learn how to integrate models
     with your own apps.

backends/apple/coreml/runtime/test/setup.md

@@ -4,18 +4,18 @@ This is a tutorial for setting up tests for the **Core ML** backend.
 
 ## Running tests
 
-1. Follow the instructions described in [Setting Up ExecuTorch](/docs/source/getting-started-setup.md) to set up ExecuTorch environment.
+1. Follow the instructions described in [Setting Up ExecuTorch](../../../../../docs/source/getting-started-setup.rst) to set up ExecuTorch environment.
 
 2. Run `install_requirements.sh` to install dependencies required by the **Core ML** backend.
 
 ```bash
 cd executorch
 
-sh backends/apple/coreml/scripts/install_requirements.sh   
+sh backends/apple/coreml/scripts/install_requirements.sh
 
-``` 
+```
 
-3. Follow the instructions described in [Building with CMake](/docs/source/runtime-build-and-cross-compilation.md#building-with-cmake) to set up CMake build system.
+3. Follow the instructions described in [Building with CMake](../../../../../docs/source/using-executorch-cpp.md#building-with-cmake) to set up CMake build system.
 
 4. Install [Xcode](https://developer.apple.com/xcode/).
 
@@ -26,7 +26,7 @@ sh backends/apple/coreml/scripts/install_requirements.sh
 ```bash
 cd executorch
 
-# Builds macOS universal test bundle. 
+# Builds macOS universal test bundle.
 
 sh backends/apple/coreml/srcipts/build_tests.sh
 
@@ -40,15 +40,15 @@ cd executorch
 sh backends/apple/coreml/srcipts/run_tests.sh
 
 ```
- 
+
 ## Updating tests
 
 1. Open the Xcode workspace.
 
 ```bash
 cd executorch
 
-# Builds macOS universal test bundle. 
+# Builds macOS universal test bundle.
 
 open backends/apple/coreml/runtime/workspace/executorchcoreml.xcworkspace
 
@@ -62,4 +62,4 @@ cd executorch
 # There is no need to build the tests.
 sh backends/apple/coreml/srcipts/run_tests.sh
 
-```
+```

backends/apple/coreml/setup.md

@@ -4,7 +4,7 @@ This is a tutorial for setting up the Core ML backend.
 
 ## AOT Setup
 
-1. Follow the instructions described in [Setting Up ExecuTorch](/docs/source/getting-started-setup.md) to set up ExecuTorch environment.
+1. Follow the instructions described in [Setting Up ExecuTorch](../../../docs/source/getting-started-setup.rst) to set up ExecuTorch environment.
 
 
 2. Run the example script to validate that the **Core ML** backend is set up correctly.
@@ -28,7 +28,7 @@ delegated_program_manager = edge_program_manager.to_backend(CoreMLPartitioner())
 
 ## Integrating Core ML delegate into runtime.
 
-1. Follow the instructions described in [Building with CMake](/docs/source/runtime-build-and-cross-compilation.md#building-with-cmake) to set up CMake build system.
+1. Follow the instructions described in [Building with CMake](../../../docs/source/using-executorch-cpp.md#building-with-cmake) to set up CMake build system.
 
 2. Install [Xcode](https://developer.apple.com/xcode/).
 

backends/apple/mps/setup.md

@@ -12,11 +12,11 @@ The MPS backend device maps machine learning computational graphs and primitives
 :::
 :::{grid-item-card}  Tutorials we recommend you complete before this:
 :class-card: card-prerequisites
-* [Introduction to ExecuTorch](intro-how-it-works.md)
-* [Setting up ExecuTorch](getting-started-setup.md)
-* [Building ExecuTorch with CMake](runtime-build-and-cross-compilation.md)
-* [ExecuTorch iOS Demo App](demo-apps-ios.md)
-* [ExecuTorch iOS LLaMA Demo App](llm/llama-demo-ios.md)
+* [Introduction to ExecuTorch](../../../docs/source/intro-how-it-works.md)
+* [Setting up ExecuTorch](../../../docs/source/getting-started-setup.rst)
+* [Building ExecuTorch with CMake](../../../docs/source/using-executorch-cpp.md#building-with-cmake)
+* [ExecuTorch iOS Demo App](../../../docs/source/demo-apps-ios.md)
+* [ExecuTorch iOS LLaMA Demo App](../../../docs/source/llm/llama-demo-ios.md)
 :::
 ::::
 
@@ -111,12 +111,12 @@ python3 -m examples.apple.mps.scripts.mps_example --model_name="mv3" --no-use_fp
 ```
 
 ### Profiling:
-1. [Optional] Generate an [ETRecord](./etrecord.rst) while you're exporting your model.
+1. [Optional] Generate an [ETRecord](../../../docs/source/etrecord.rst) while you're exporting your model.
 ```bash
 cd executorch
 python3 -m examples.apple.mps.scripts.mps_example --model_name="mv3" --generate_etrecord -b
 ```
-2. Run your Program on the ExecuTorch runtime and generate an [ETDump](./etdump.md).
+2. Run your Program on the ExecuTorch runtime and generate an [ETDump](../../../docs/source/etdump.md).
 ```
 ./cmake-out/examples/apple/mps/mps_executor_runner --model_path mv3_mps_bundled_fp16.pte --bundled_program --dump-outputs
 ```

backends/cadence/aot/pass_utils.py

@@ -35,8 +35,8 @@ class CadencePassAttribute:
 ALL_CADENCE_PASSES: dict[ExportPass, CadencePassAttribute] = {}
 
 
-def get_cadence_pass_attribute(p: ExportPass) -> CadencePassAttribute:
-    return ALL_CADENCE_PASSES[p]
+def get_cadence_pass_attribute(p: ExportPass) -> Optional[CadencePassAttribute]:
+    return ALL_CADENCE_PASSES.get(p, None)
 
 
 # A decorator that registers a pass.
@@ -61,7 +61,8 @@ def create_cadence_pass_filter(
     def _filter(p: ExportPass) -> bool:
         pass_attribute = get_cadence_pass_attribute(p)
         return (
-            pass_attribute.opt_level is not None
+            pass_attribute is not None
+            and pass_attribute.opt_level is not None
             and pass_attribute.opt_level <= opt_level
             and (not pass_attribute.debug_pass or debug)
         )

backends/example/README.md

@@ -17,16 +17,16 @@ In the following diagram, we show how to quantize a mobile net v2 model and lowe
 
 We can define patterns based on the operators supported by the backend, which will be used by the quantizer and delegate.
 
-![](./diagrams/quantize_delegate.png)
+![](diagrams/quantize_delegate.png)
 
 ### Partitioner and Backend
 
 The way partitioner and backend is, partitioner will tag the nodes to lower to the backend and backend will will receive all tagged nodes and preprocess them as a delegate.
 
-![](./diagrams/delegate.png)
+![](diagrams/delegate.png)
 
 ### Memory format permute
 
 Some operators may have better performance in the memory format other than contiguous. One way to do that is to insert `to_dim_op` to describe memory format permutation and merge if there two opposite one next to each other.
 
-![](./diagrams/memory_permute.png)
+![](diagrams/memory_permute.png)

backends/qualcomm/README.md

@@ -13,7 +13,7 @@ A website version of the tutorial is [here](https://pytorch.org/executorch/main/
 ## Delegate Options
 
 Please check `generate_qnn_executorch_compiler_spec()` in
-[utils.py](./utils/utils.py) for supported SoC and inference type.
+[utils.py](utils/utils.py) for supported SoC and inference type.
 
 ### Supported Chipset
 - Snapdragon 8 Gen 1

backends/vulkan/docs/android_demo.md

@@ -1,6 +1,6 @@
 # Building and Running ExecuTorch with the Vulkan Backend
 
-The [ExecuTorch Vulkan Delegate](./native-delegates-executorch-vulkan-delegate.md)
+The [ExecuTorch Vulkan Delegate](../../../docs/source/native-delegates-executorch-vulkan-delegate.md)
 is a native GPU delegate for ExecuTorch.
 
 <!----This will show a grid card on the page----->
@@ -12,8 +12,8 @@ is a native GPU delegate for ExecuTorch.
 :::
 :::{grid-item-card}  Prerequisites:
 :class-card: card-prerequisites
-* Follow [**Setting up ExecuTorch**](./getting-started-setup.md)
-* It is also recommended that you read through [**ExecuTorch Vulkan Delegate**](./native-delegates-executorch-vulkan-delegate.md) and follow the example in that page
+* Follow [**Setting up ExecuTorch**](../../../docs/source/getting-started-setup.rst)
+* It is also recommended that you read through [**ExecuTorch Vulkan Delegate**](../../../docs/source/native-delegates-executorch-vulkan-delegate.md) and follow the example in that page
 :::
 ::::
 
@@ -59,7 +59,7 @@ partially lower the Llama model to Vulkan.
 # The files will usually be downloaded to ~/.llama
 python -m examples.models.llama.export_llama \
   --disable_dynamic_shape --vulkan -kv --use_sdpa_with_kv_cache -d fp32 \
-  --model "llama3_2" \ 
+  --model "llama3_2" \
   -c ~/.llama/checkpoints/Llama3.2-1B/consolidated.00.pth \
   -p ~/.llama/checkpoints/Llama3.2-1B/params.json \
   --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}'

devtools/bundled_program/bundled_program.cpp

@@ -33,7 +33,7 @@ using ::executorch::runtime::EValue;
 using ::executorch::runtime::Result;
 
 namespace executorch {
-namespace bundled_program {
+namespace BUNDLED_PROGRAM_NAMESPACE {
 
 namespace {
 
@@ -433,5 +433,5 @@ bool is_bundled_program(void* file_data, ET_UNUSED size_t file_data_len) {
       file_data);
 }
 
-} // namespace bundled_program
+} // namespace BUNDLED_PROGRAM_NAMESPACE
 } // namespace executorch

devtools/bundled_program/bundled_program.h

@@ -10,9 +10,14 @@
 
 #include <executorch/runtime/core/memory_allocator.h>
 #include <executorch/runtime/executor/method.h>
+#ifdef USE_ATEN_LIB
+#define BUNDLED_PROGRAM_NAMESPACE bundled_program::aten
+#else // !USE_ATEN_LIB
+#define BUNDLED_PROGRAM_NAMESPACE bundled_program
+#endif // USE_ATEN_LIB
 
 namespace executorch {
-namespace bundled_program {
+namespace BUNDLED_PROGRAM_NAMESPACE {
 
 /**
  * An opaque pointer to a serialized bundled program.
@@ -94,7 +99,7 @@ ET_DEPRECATED inline bool is_bundled_program(void* file_data) {
   return is_bundled_program(file_data, 128);
 }
 
-} // namespace bundled_program
+} // namespace BUNDLED_PROGRAM_NAMESPACE
 } // namespace executorch
 
 namespace torch {
@@ -103,13 +108,13 @@ namespace bundled_program {
 // TODO(T197294990): Remove these deprecated aliases once all users have moved
 // to the new `::executorch` namespaces.
 using serialized_bundled_program =
-    ::executorch::bundled_program::SerializedBundledProgram;
+    ::executorch::BUNDLED_PROGRAM_NAMESPACE::SerializedBundledProgram;
 
 ET_NODISCARD inline ::executorch::runtime::Error LoadBundledInput(
     Method& method,
     serialized_bundled_program* bundled_program_ptr,
     size_t testset_idx) {
-  return ::executorch::bundled_program::load_bundled_input(
+  return ::executorch::BUNDLED_PROGRAM_NAMESPACE::load_bundled_input(
       method, bundled_program_ptr, testset_idx);
 }
 
@@ -120,7 +125,7 @@ VerifyResultWithBundledExpectedOutput(
     size_t testset_idx,
     double rtol = 1e-5,
     double atol = 1e-8) {
-  return ::executorch::bundled_program::verify_method_outputs(
+  return ::executorch::BUNDLED_PROGRAM_NAMESPACE::verify_method_outputs(
       method, bundled_program_ptr, testset_idx, rtol, atol);
 }
 
@@ -129,13 +134,14 @@ ET_NODISCARD inline ::executorch::runtime::Error GetProgramData(
     size_t file_data_len,
     const void** out_program_data,
     size_t* out_program_data_len) {
-  return ::executorch::bundled_program::get_program_data(
+  return ::executorch::BUNDLED_PROGRAM_NAMESPACE::get_program_data(
       file_data, file_data_len, out_program_data, out_program_data_len);
 }
 
 inline bool IsBundledProgram(void* file_data) {
   // 128 is enough data to contain the identifier in the flatbuffer header.
-  return ::executorch::bundled_program::is_bundled_program(file_data, 128);
+  return ::executorch::BUNDLED_PROGRAM_NAMESPACE::is_bundled_program(
+      file_data, 128);
 }
 } // namespace bundled_program
 } // namespace executor