Update base for Update on "[ET-VK][ez] Add support for buffer backed qparams in int4 linear + add checks for physical limits when allocating"

## Context

Currently, the groupwise quantized int4 linear op implementation forces the scales and zero tensor to be a `Texture3D`. However, for i.e. transformer models that have a logit linear layer, the image extents required may exceed the maximum image extents available on the device.

## Changes

* Add support for the scales and zero tensor being a `Buffer` instead of a `Texture3D`
* Add checks when allocating buffers or images for tensors that the requested resource fits within the physical device limits

Differential Revision: [D72662176](https://our.internmc.facebook.com/intern/diff/D72662176/)

[ghstack-poisoned]

Author: SS-JIA

.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

@@ -154,7 +154,7 @@ run_and_verify() {
         EXPECTED_PREFIX="ASSISTANT: image captures a basketball game in progress, with several players on the court. One of the players is dribbling the ball, while the others are in various"
     else
         # set the expected prefix to be the same as prompt because there's a bug in sdpa_with_kv_cache that causes <unk> tokens.
-        EXPECTED_PREFIX="ASSISTANT:"
+        EXPECTED_PREFIX="ASSISTANT: image"
     fi
     if [[ "${RESULT}" == *"${EXPECTED_PREFIX}"* ]]; then
         echo "Expected result prefix: ${EXPECTED_PREFIX}"

.ci/scripts/test_llava.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
@@ -130,7 +131,8 @@ jobs:
           # https://github.com/ReactiveCircus/android-emulator-runner. The max number
           # of cores we can set is 6, any higher number will be reduced to 6.
           cores: 6
-          ram-size: 12288M
+          ram-size: 16384M
+          heap-size: 12288M
           force-avd-creation: false
           disable-animations: true
           emulator-options: -no-snapshot-save -no-window -gpu swiftshader_indirect -noaudio -no-boot-anim -camera-back none

.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 +7,12 @@ 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
+  schedule:
+    - cron: 0 10 * * *
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -22,6 +28,10 @@ jobs:
         shell: bash
         run: |
           VERSION="${{ inputs.version }}"
+          if [ -z "$VERSION" ]; then
+            echo "No version name specified. Will create a snapshot AAR"
+            exit 0
+          fi
           if curl -I "https://ossci-android.s3.amazonaws.com/executorch/release/${VERSION}/executorch.aar" | grep "200 OK"; then
             echo "AAR already exists at https://ossci-android.s3.amazonaws.com/executorch/release/${VERSION}/executorch.aar"
             echo "Will skip build/upload"
@@ -31,14 +41,17 @@ 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 +65,16 @@ 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 +84,12 @@ 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="${ANDROID_SDK:-/opt/android/sdk}" ./gradlew :executorch_android:publishToMavenCentral)
+        fi
+
   upload-release-aar:
     name: upload-release-aar
     needs: build-aar
@@ -84,6 +113,8 @@ jobs:
           pip install awscli==1.32.18
           AWS_CMD="aws s3 cp"
           VERSION="${{ inputs.version }}"
-          VERSION_NAME="${VERSION:-temp_snapshot}"
-          ${AWS_CMD} executorch.aar s3://ossci-android/executorch/release/${VERSION_NAME}/executorch.aar --acl public-read
-          ${AWS_CMD} executorch.aar.sha256sums s3://ossci-android/executorch/release/${VERSION_NAME}/executorch.aar.sha256sums --acl public-read
+          if [ -z "$VERSION" ]; then
+            VERSION="snapshot-$(date +"%Y%m%d")"
+          fi
+          ${AWS_CMD} executorch.aar s3://ossci-android/executorch/release/${VERSION}/executorch.aar --acl public-read
+          ${AWS_CMD} executorch.aar.sha256sums s3://ossci-android/executorch/release/${VERSION}/executorch.aar.sha256sums --acl public-read

.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