Merge branch 'main' into pr_model_improve

Author: zingo

.ci/scripts/build_android_instrumentation.sh

@@ -7,7 +7,7 @@
 
 set -e
 
-APP_PATH="examples/demo-apps/apple_ios/ExecuTorchDemo/ExecuTorchDemo"
+APP_PATH="executorch-examples/apple/ExecuTorchDemo/ExecuTorchDemo"
 MODEL_NAME="mv3"
 SIMULATOR_NAME="executorch"
 
@@ -34,6 +34,10 @@ say() {
   echo -e "\033[1m\n\t** $1 **\n\033[0m"
 }
 
+say "Cloning the Demo App"
+
+git clone --depth 1 https://github.com/pytorch-labs/executorch-examples.git
+
 say "Installing CoreML Backend Requirements"
 
 ./backends/apple/coreml/scripts/install_requirements.sh

.ci/scripts/test_ios_ci.sh

@@ -14,7 +14,7 @@ jobs:
     with:
       runner: linux.2xlarge
       docker-image: executorch-ubuntu-22.04-clang12-android
-      submodules: 'true'
+      submodules: 'recursive'
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout: 90
       upload-artifact: android-apps
@@ -36,8 +36,9 @@ jobs:
         cp ${BUILD_AAR_DIR}/executorch.aar $ARTIFACTS_DIR_NAME
 
         mkdir -p ${ARTIFACTS_DIR_NAME}/library_test_dir
-        bash .ci/scripts/build_android_instrumentation.sh
-        cp ${BUILD_AAR_DIR}/executorch_android/build/outputs/apk/androidTest/debug/executorch_android-debug-androidTest.apk "${ARTIFACTS_DIR_NAME}/library_test_dir"
+        bash extension/android/executorch_android/android_test_setup.sh
+        (cd extension/android; ANDROID_HOME="${ANDROID_SDK:-/opt/android/sdk}" ./gradlew :executorch_android:assembleAndroidTest)
+        cp extension/android/executorch_android/build/outputs/apk/androidTest/debug/executorch_android-debug-androidTest.apk "${ARTIFACTS_DIR_NAME}/library_test_dir"
 
         mkdir -p ${ARTIFACTS_DIR_NAME}/fp32-xnnpack-custom
         bash examples/models/llama/install_requirements.sh

.github/workflows/_android.yml

@@ -345,7 +345,7 @@ jobs:
     with:
       runner: linux.2xlarge
       docker-image: executorch-ubuntu-22.04-clang12-android
-      submodules: 'true'
+      submodules: 'recursive'
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       timeout: 90
       upload-artifact: android-apps

.github/workflows/android-perf.yml

@@ -7,6 +7,10 @@ on:
         description: Version name to be uploaded for AAR release
         required: false
         type: string
+      upload_to_maven:
+        description: Upload the AAR to maven staging repository
+        required: false
+        type: boolean
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -31,14 +35,17 @@ jobs:
   build-aar:
     name: build-aar
     needs: check-if-aar-exists
-    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
+    if: ${{ !github.event.pull_request.head.repo.fork }}
+    uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@release/2.7
+    secrets: inherit
     permissions:
       id-token: write
       contents: read
     with:
+      secrets-env: EXECUTORCH_MAVEN_SIGNING_KEYID EXECUTORCH_MAVEN_SIGNING_PASSWORD EXECUTORCH_MAVEN_CENTRAL_PASSWORD EXECUTORCH_MAVEN_CENTRAL_USERNAME EXECUTORCH_MAVEN_SIGNING_GPG_KEY_CONTENTS
       runner: linux.2xlarge
       docker-image: executorch-ubuntu-22.04-clang12-android
-      submodules: 'true'
+      submodules: 'recursive'
       ref: ${{ github.sha }}
       timeout: 90
       upload-artifact: android-apps
@@ -52,6 +59,16 @@ jobs:
         PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh --build-tool buck2
         export ARTIFACTS_DIR_NAME=artifacts-to-be-uploaded
 
+        mkdir -p ~/.gradle
+        touch ~/.gradle/gradle.properties
+        echo "signing.keyId=${SECRET_EXECUTORCH_MAVEN_SIGNING_KEYID}" >> ~/.gradle/gradle.properties
+        echo "signing.password=${SECRET_EXECUTORCH_MAVEN_SIGNING_PASSWORD}" >> ~/.gradle/gradle.properties
+        echo "mavenCentralUsername=${SECRET_EXECUTORCH_MAVEN_CENTRAL_USERNAME}" >> ~/.gradle/gradle.properties
+        echo "mavenCentralPassword=${SECRET_EXECUTORCH_MAVEN_CENTRAL_PASSWORD}" >> ~/.gradle/gradle.properties
+        echo "signing.secretKeyRingFile=/tmp/secring.gpg" >> ~/.gradle/gradle.properties
+
+        echo -n "$SECRET_EXECUTORCH_MAVEN_SIGNING_GPG_KEY_CONTENTS" | base64 -d > /tmp/secring.gpg
+
         # Build AAR Package
         mkdir aar-out
         export BUILD_AAR_DIR=aar-out
@@ -61,6 +78,12 @@ jobs:
 
         shasum -a 256 "${ARTIFACTS_DIR_NAME}/executorch.aar"
 
+        # Publish to maven staging
+        UPLOAD_TO_MAVEN="${{ inputs.upload_to_maven }}"
+        if [[ "$UPLOAD_TO_MAVEN" == "true" ]]; then
+          (cd aar-out; ANDROID_HOME="${ANDROID_SDK:-/opt/android/sdk}" ./gradlew :executorch_android:publishToMavenCentral)
+        fi
+
   upload-release-aar:
     name: upload-release-aar
     needs: build-aar

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

@@ -80,6 +80,9 @@ ignore_missing_imports = True
 [mypy-serializer.*]
 ignore_missing_imports = True
 
+[mypy-tosa_tools.*]
+ignore_missing_imports = True
+
 [mypy-setuptools.*]
 ignore_missing_imports = True
 

.mypy.ini

@@ -1,7 +1,6 @@
 Thank you for your interest in contributing to ExecuTorch! We want to make
 it easy to contribute to this project.
 
- 
 
 ## Dev Install
 
@@ -91,7 +90,7 @@ executorch
 │   └── <a href="runtime/platform">platform</a> - Layer between architecture specific code and portable C++.
 ├── <a href="schema">schema</a> - ExecuTorch PTE file format flatbuffer schemas.
 ├── <a href="scripts">scripts</a> - Utility scripts for building libs, size management, dependency management, etc.
-├── <a href="shim">shim</a> - Compatibility layer between OSS and Internal builds.
+├── <a href="shim_et">shim_et</a> - Compatibility layer between OSS and Internal builds.
 ├── <a href="test">test</a> - Broad scoped end-to-end tests.
 ├── <a href="third-party">third-party</a> - Third-party dependencies.
 ├── <a href="tools">tools</a> - Tools for building ExecuTorch from source, for different built tools (CMake, Buck).
@@ -103,6 +102,8 @@ executorch
 ## Contributing workflow
 We actively welcome your pull requests (PRs).
 
+If you're completely new to open-source projects, GitHub, or ExecuTorch, please see our [New Contributor Guide](./docs/source/new-contributor-guide.md) for a step-by-step walkthrough on making your first contribution. Otherwise, read on.
+
 1. [Claim an issue](#claiming-issues), if present, before starting work. If an
    issue doesn't cover the work you plan to do, consider creating one to provide
    context about it, and to build consensus about the scope and solution.
@@ -192,9 +193,6 @@ in the Github repo.
 
 ## Coding Style
 
-Goal: Encourage standards that make it easier to read, edit, maintain, and debug
-the ExecuTorch code.
-
 ### lintrunner
 
 We use [`lintrunner`](https://pypi.org/project/lintrunner/) to help make sure the
@@ -259,7 +257,7 @@ toolchains, and having access to relatively modern C++ features.
 
 #### C/C++ standard library usage
 
-**Restricted usage of the C++ standard library.**
+**Restricted usage of the C++ standard library**
 
 Rationale: ExecuTorch is intended to be portable to bare-metal systems that lack
 certain features, like dynamic memory, threading, and locking, required by parts
@@ -280,7 +278,7 @@ careful to also manually destroy objects initialized in this way.
 
 #### C++ language features
 
-**Exceptions: Do not use.**
+**Exceptions: Do not use**
 - Rationale: Exceptions are not widely supported on some classes of
   microcontrollers and DSPs, and they can significantly increase binary size.
 
@@ -289,12 +287,12 @@ must work with threading**
 - Rationale: The core runtime must work on systems that do not have threading
   support.
 
-**RTTI, dynamic_cast, and `<typeid>`: Do not use.**
+**RTTI, dynamic_cast, and `<typeid>`: Do not use**
 - Rationale: RTTI adds extra data to every virtual class. ExecuTorch doesn't
   have a strong need for `dynamic_cast` and friends, so it's better to reduce
   the binary size.
 
-**Templates and template metaprogramming: Be careful and avoid if possible.**
+**Templates and template metaprogramming: Be careful and avoid if possible**
 - Rationale: Most templating results in code generation, and is one of the most
   common sources of binary bloat. Some use of templates is fine (e.g. an
   `ArrayRef<T>`, or code that handles multiple `ScalarType` types), but for the
@@ -359,7 +357,7 @@ docs](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/
 for basics.
 
 1. Push your branch to your fork of `pytorch/executorch`. Most people do not
-  have permission to push a branch directoy to the upstream repo.
+  have permission to push a branch directory to the upstream repo.
 1. Create your PR
    - Use the `main` branch as the base.
    - Give the PR a clear and descriptive title. It will become the title of the

CONTRIBUTING.md

@@ -49,9 +49,9 @@ Key value propositions of ExecuTorch are:
 ## Getting Started
 To get started you can:
 
-- Visit the [Step by Step Tutorial](https://pytorch.org/executorch/main/index.html) on getting things running locally and deploy a model to a device
+- Visit the [Step by Step Tutorial](https://pytorch.org/executorch/main/index.html) to get things running locally and deploy a model to a device
 - Use this [Colab Notebook](https://pytorch.org/executorch/stable/getting-started-setup.html#quick-setup-colab-jupyter-notebook-prototype) to start playing around right away
-- Jump straight into LLMs use cases by following specific instructions for [Llama](./examples/models/llama/README.md) and [Llava](./examples/models/llava/README.md)
+- Jump straight into LLM use cases by following specific instructions for [Llama](./examples/models/llama/README.md) and [Llava](./examples/models/llava/README.md)
 
 ## Feedback and Engagement
 

README.md

@@ -7,8 +7,9 @@
 
 from typing import Dict, List
 
-import serializer.tosa_serializer as ts  # type: ignore
 import torch
+
+import tosa_tools.v0_80.serializer.tosa_serializer as ts  # type: ignore
 from executorch.backends.arm.tosa_mapping import TosaArg
 from executorch.backends.arm.tosa_specification import TosaSpecification
 from torch.export import ExportedProgram

backends/arm/operators/node_visitor.py

@@ -9,15 +9,13 @@
 import executorch.backends.arm.tosa_quant_utils as tqutils
 import executorch.backends.arm.tosa_utils as tutils
 
-import serializer.tosa_serializer as ts  # type: ignore
+import tosa_tools.v0_80.serializer.tosa_serializer as ts  # type: ignore
 from executorch.backends.arm.operators.node_visitor import (
     NodeVisitor,
     register_node_visitor,
 )
 from executorch.backends.arm.tosa_mapping import TosaArg
 from executorch.backends.arm.tosa_specification import TosaSpecification
-
-from serializer.tosa_serializer import TosaOp
 from torch.fx import Node
 
 
@@ -70,7 +68,7 @@ def define_node(
 
         # Do the INT32 Abs
         tosa_graph.addOperator(
-            TosaOp.Op().ABS,
+            ts.TosaOp.Op().ABS,
             [
                 rescaled_inputs[0].name,
             ],
@@ -126,7 +124,7 @@ def define_node(
 
             # MI lowering
             tosa_graph.addOperator(
-                TosaOp.Op().ABS,
+                ts.TosaOp.Op().ABS,
                 [inputs[0].name],
                 [output.name],
                 None,

backends/arm/operators/op_abs.py

@@ -10,14 +10,13 @@
 import executorch.backends.arm.tosa_quant_utils as tqutils
 import executorch.backends.arm.tosa_utils as tutils
 
-import serializer.tosa_serializer as ts  # type: ignore
+import tosa_tools.v0_80.serializer.tosa_serializer as ts  # type: ignore
 from executorch.backends.arm.operators.node_visitor import (
     NodeVisitor,
     register_node_visitor,
 )
 from executorch.backends.arm.tosa_mapping import TosaArg
 from executorch.backends.arm.tosa_specification import TosaSpecification
-from serializer.tosa_serializer import TosaOp
 from torch.fx import Node
 
 
@@ -82,7 +81,7 @@ def define_node(
 
         # Do the INT32 Add
         tosa_graph.addOperator(
-            TosaOp.Op().ADD,
+            ts.TosaOp.Op().ADD,
             [input1.name, input2.name],
             [add_output.name],
             None,
@@ -135,7 +134,7 @@ def define_node(
 
             # MI lowering
             tosa_graph.addOperator(
-                TosaOp.Op().ADD,
+                ts.TosaOp.Op().ADD,
                 [input1.name, input2.name],
                 [output.name],
                 None,

backends/arm/operators/op_add.py

@@ -4,14 +4,13 @@
 # LICENSE file in the root directory of this source tree.
 from typing import List
 
-import serializer.tosa_serializer as ts
+import tosa_tools.v0_80.serializer.tosa_serializer as ts
 from executorch.backends.arm._passes.arm_pass_utils import get_first_fake_tensor
 from executorch.backends.arm.operators.node_visitor import (
     NodeVisitor,
     register_node_visitor,
 )
 from executorch.backends.arm.tosa_mapping import TosaArg
-from serializer.tosa_serializer import TosaOp
 from torch.fx import Node
 
 
@@ -48,5 +47,5 @@ def define_node(
         attr.AxisAttribute(input.dim_order.index(dim))
 
         tosa_graph.addOperator(
-            TosaOp.Op().REDUCE_MAX, [input.name], [output.name], attr
+            ts.TosaOp.Op().REDUCE_MAX, [input.name], [output.name], attr
         )

backends/arm/operators/op_amax.py

@@ -4,14 +4,13 @@
 # LICENSE file in the root directory of this source tree.
 from typing import List
 
-import serializer.tosa_serializer as ts
+import tosa_tools.v0_80.serializer.tosa_serializer as ts
 from executorch.backends.arm._passes.arm_pass_utils import get_first_fake_tensor
 from executorch.backends.arm.operators.node_visitor import (
     NodeVisitor,
     register_node_visitor,
 )
 from executorch.backends.arm.tosa_mapping import TosaArg
-from serializer.tosa_serializer import TosaOp
 from torch.fx import Node
 
 
@@ -48,5 +47,5 @@ def define_node(
         attr.AxisAttribute(input.dim_order.index(dim))
 
         tosa_graph.addOperator(
-            TosaOp.Op().REDUCE_MIN, [input.name], [output.name], attr
+            ts.TosaOp.Op().REDUCE_MIN, [input.name], [output.name], attr
         )

backends/arm/operators/op_amin.py

@@ -6,14 +6,13 @@
 # pyre-unsafe
 from typing import cast, List
 
-import serializer.tosa_serializer as ts  # type: ignore
+import tosa_tools.v0_80.serializer.tosa_serializer as ts  # type: ignore
 from executorch.backends.arm.operators.node_visitor import (  # type: ignore
     NodeVisitor,
     register_node_visitor,
 )
 
 from executorch.backends.arm.tosa_mapping import TosaArg  # type: ignore
-from serializer.tosa_serializer import TosaOp
 from torch.fx import Node
 
 
@@ -49,5 +48,5 @@ def define_node(
         attr.AxisAttribute(inputs[0].dim_order.index(dim))
 
         tosa_graph.addOperator(
-            TosaOp.Op().REDUCE_ANY, [inputs[0].name], [output.name], attr
+            ts.TosaOp.Op().REDUCE_ANY, [inputs[0].name], [output.name], attr
         )

backends/arm/operators/op_any.py

@@ -6,9 +6,10 @@
 # pyre-unsafe
 from typing import List
 
-import serializer.tosa_serializer as ts  # type: ignore
 import torch
 
+import tosa_tools.v0_80.serializer.tosa_serializer as ts  # type: ignore
+
 from executorch.backends.arm._passes.fold_qdq_with_annotated_qparams_pass import (
     get_input_qparams,
     get_output_qparams,