Remove Android LlamaDemo

Differential Revision: D82868456

Pull Request resolved: #14450

Author: kirklandsign

.github/workflows/_android.yml

@@ -48,19 +48,6 @@ jobs:
         bash examples/models/llama/install_requirements.sh
         bash ".ci/scripts/test_llama.sh" -model stories110M -build_tool cmake -dtype fp16 -mode portable -upload ${ARTIFACTS_DIR_NAME}/fp32-xnnpack-custom
 
-        mkdir -p examples/demo-apps/android/LlamaDemo/app/libs
-        cp aar-out/executorch.aar examples/demo-apps/android/LlamaDemo/app/libs
-        pushd examples/demo-apps/android/LlamaDemo
-        ANDROID_HOME="${ANDROID_SDK:-/opt/android/sdk}" ./gradlew build assembleAndroidTest
-        popd
-
-        DEMO_APP_DIR="${ARTIFACTS_DIR_NAME}/llm_demo"
-        # The app directory is named using its build flavor as a suffix.
-        mkdir -p "${DEMO_APP_DIR}"
-        # Collect the app and its test suite
-        cp examples/demo-apps/android/LlamaDemo/app/build/outputs/apk/debug/*.apk "${DEMO_APP_DIR}"
-        cp examples/demo-apps/android/LlamaDemo/app/build/outputs/apk/androidTest/debug/*.apk "${DEMO_APP_DIR}"
-
   # Running Android emulator directly on the runner and not using Docker
   run-emulator:
     needs: build-llm-demo
@@ -103,8 +90,6 @@ jobs:
         shell: bash
         run: |
           set -eux
-          curl -O https://gha-artifacts.s3.amazonaws.com/${{ github.repository }}/${{ github.run_id }}/artifacts/llm_demo/app-debug.apk
-          curl -O https://gha-artifacts.s3.amazonaws.com/${{ github.repository }}/${{ github.run_id }}/artifacts/llm_demo/app-debug-androidTest.apk
           curl -O https://gha-artifacts.s3.amazonaws.com/${{ github.repository }}/${{ github.run_id }}/artifacts/fp32-xnnpack-custom/model.zip
           curl -o android-test-debug-androidTest.apk https://gha-artifacts.s3.amazonaws.com/${{ github.repository }}/${{ github.run_id }}/artifacts/library_test_dir/executorch_android-debug-androidTest.apk
           unzip model.zip

.github/workflows/lint.yml

@@ -148,8 +148,6 @@ jobs:
           extension/android/executorch_android/src/main/java/org/pytorch/executorch/extension/llm/*.java \
           extension/android/executorch_android/src/main/java/org/pytorch/executorch/annotations/*.java \
           extension/android/executorch_android/src/androidTest/java/org/pytorch/executorch/*.java \
-          examples/demo-apps/android/LlamaDemo/app/src/main/java/com/example/executorchllamademo/*.java \
-          examples/demo-apps/android/LlamaDemo/app/src/androidTest/java/com/example/executorchllamademo/*.java \
           extension/benchmark/android/benchmark/app/src/main/java/org/pytorch/minibench/*.java \
           extension/benchmark/android/benchmark/app/src/androidTest/java/org/pytorch/minibench/*.java)
         if [ -n "$FILES_NEEDS_FORMAT" ]; then

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 etLLM on [iOS](https://github.com/meta-pytorch/executorch-examples/tree/main/llm/apple) and [Android](docs/source/llm/llama-demo-android.md) devices.
+* Running etLLM on [iOS](https://github.com/meta-pytorch/executorch-examples/tree/main/llm/apple) and [Android](https://github.com/meta-pytorch/executorch-examples/tree/main/llm/android) devices.
   * Build and run LLaMA in a demo mobile app, and learn how to integrate models
     with your own apps.

docs/source/index.md

@@ -93,7 +93,7 @@ ExecuTorch provides support for:
 - [Exporting LLMs](llm/export-llm.md)
 - [Exporting custom LLMs](llm/export-custom-llm.md)
 - [Running with C++](llm/run-with-c-plus-plus.md)
-- [Running on Android (XNNPack)](llm/llama-demo-android.md)
+- [Running on Android (XNNPack)](https://github.com/meta-pytorch/executorch-examples/tree/main/llm/android)
 - [Running on Android (QNN)](llm/build-run-llama3-qualcomm-ai-engine-direct-backend.md)
 - [Running on iOS](llm/run-on-ios.md)
 #### Backend Development
@@ -251,7 +251,7 @@ Getting Started <llm/getting-started>
 Exporting LLMs with export_llm <llm/export-llm>
 Exporting custom LLMs <llm/export-custom-llm>
 Running with C++ <llm/run-with-c-plus-plus>
-Running on Android <XNNPack> <llm/llama-demo-android>
+Running on Android <XNNPack> <https://github.com/meta-pytorch/executorch-examples/tree/main/llm/android>
 Running on Android <QNN> <llm/build-run-llama3-qualcomm-ai-engine-direct-backend>
 Running on iOS <llm/run-on-ios>
 ```

docs/source/llm/getting-started.md

@@ -21,6 +21,6 @@ Deploying LLMs to ExecuTorch can be boiled down to a two-step process: (1) expor
 - [Exporting LLMs](export-llm.md)
 - [Exporting custom LLMs](export-custom-llm.md)
 - [Running with C++](run-with-c-plus-plus.md)
-- [Running on Android (XNNPack)](llama-demo-android.md)
+- [Running on Android (XNNPack)](https://github.com/meta-pytorch/executorch-examples/tree/main/llm/android)
 - [Running on Android (Qualcomm)](build-run-llama3-qualcomm-ai-engine-direct-backend.md)
 - [Running on iOS](https://github.com/meta-pytorch/executorch-examples/tree/main/llm/apple)

docs/source/llm/llama-demo-android.md

@@ -88,7 +88,7 @@ implementation("com.facebook.fbjni:fbjni:0.7.0")
 
 ### Example usage
 
-In your app working directory, such as executorch/examples/demo-apps/android/LlamaDemo,
+In your app working directory, such as executorch-examples/llm/android/LlamaDemo,
 ```
 mkdir -p app/libs
 curl https://ossci-android.s3.amazonaws.com/executorch/release/${executorch_version}/executorch.aar -o app/libs/executorch.aar
@@ -202,7 +202,7 @@ adb push extension/module/test/resources/add.pte /data/local/tmp/
 This example loads an ExecuTorch module, prepares input data, runs inference, and processes the output data.
 
 Please use [DeepLabV3AndroidDemo](https://github.com/meta-pytorch/executorch-examples/tree/main/dl3/android/DeepLabV3Demo)
-and [LlamaDemo](https://github.com/pytorch/executorch/tree/main/examples/demo-apps/android/LlamaDemo) for the code examples
+and [LlamaDemo](https://github.com/meta-pytorch/executorch-examples/tree/main/llm/android/LlamaDemo) for the code examples
 using ExecuTorch AAR package.
 
 ## Java API reference