Merge branch 'main' into nil-is-all-patch-5-1

Author: nil-is-all

.ci/scripts/export_model_artifact.sh

@@ -358,7 +358,7 @@ if [ "$MODEL_NAME" = "voxtral_realtime" ]; then
   STREAMING_ARG=""
   PREPROCESSOR_ARGS="--feature_size 128 --output_file ${OUTPUT_DIR}/preprocessor.pte"
   if [ "$USE_STREAMING" = "true" ]; then
-    STREAMING_ARG="--streaming"
+    STREAMING_ARG="--streaming --sliding-window 2048"
     PREPROCESSOR_ARGS="$PREPROCESSOR_ARGS --streaming"
   else
     PREPROCESSOR_ARGS="$PREPROCESSOR_ARGS --stack_output --max_audio_len 300"
@@ -424,6 +424,7 @@ if [ "$MODEL_NAME" = "qwen3_5_moe" ]; then
   test -f "${OUTPUT_DIR}/model.pte"
   test -f "${OUTPUT_DIR}/aoti_cuda_blob.ptd"
   ls -al "${OUTPUT_DIR}"
+
   exit 0
 fi
 

.ci/scripts/setup-openvino.sh

@@ -10,17 +10,41 @@ set -ex
 # shellcheck source=/dev/null
 source "$(dirname "${BASH_SOURCE[0]}")/utils.sh"
 
+# Parse arguments
+USE_NIGHTLY=false
+for arg in "$@"; do
+  case $arg in
+    --nightly) USE_NIGHTLY=true ;;
+  esac
+done
+
 # Download and install OpenVINO from release packages
-OPENVINO_VERSION="2025.3"
-OPENVINO_BUILD="2025.3.0.19807.44526285f24"
-OPENVINO_URL="https://storage.openvinotoolkit.org/repositories/openvino/packages/${OPENVINO_VERSION}/linux/openvino_toolkit_ubuntu22_${OPENVINO_BUILD}_x86_64.tgz"
+OPENVINO_VERSION="2026.0"
+OPENVINO_BUILD="2026.0.0.20965.c6d6a13a886"
+OPENVINO_STABLE_URL="https://storage.openvinotoolkit.org/repositories/openvino/packages/${OPENVINO_VERSION}/linux/openvino_toolkit_ubuntu22_${OPENVINO_BUILD}_x86_64.tgz"
+
+OPENVINO_NIGHTLY_BUILD_ID="2026.1.0-21310-c694fbc2b6d"
+OPENVINO_NIGHTLY_BUILD="2026.1.0.dev20260312"
+OPENVINO_NIGHTLY_URL="https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/${OPENVINO_NIGHTLY_BUILD_ID}/openvino_toolkit_ubuntu22_${OPENVINO_NIGHTLY_BUILD}_x86_64.tgz"
+
+if [ "${USE_NIGHTLY}" = true ]; then
+  OPENVINO_URL="${OPENVINO_NIGHTLY_URL}"
+  OPENVINO_EXTRACTED_DIR="openvino_toolkit_ubuntu22_${OPENVINO_NIGHTLY_BUILD}_x86_64"
+  echo "Using OpenVINO nightly build: ${OPENVINO_NIGHTLY_BUILD_ID}"
+else
+  OPENVINO_URL="${OPENVINO_STABLE_URL}"
+  OPENVINO_EXTRACTED_DIR="openvino_toolkit_ubuntu22_${OPENVINO_BUILD}_x86_64"
+  echo "Using OpenVINO stable release: ${OPENVINO_BUILD}"
+fi
 
 curl -Lo /tmp/openvino_toolkit.tgz --retry 3 --fail ${OPENVINO_URL}
 tar -xzf /tmp/openvino_toolkit.tgz
-mv openvino_toolkit_ubuntu22_${OPENVINO_BUILD}_x86_64 openvino
+mv "${OPENVINO_EXTRACTED_DIR}" openvino
 
+set +u
 source openvino/setupvars.sh
-cd backends/openvino
-pip install -r requirements.txt
-cd scripts
+set -u
+pip install -r backends/openvino/requirements.txt
+pushd backends/openvino/scripts
 ./openvino_build.sh --enable_python
+popd

.ci/scripts/test_backend.sh

@@ -78,6 +78,12 @@ if [[ "$FLOW" == *arm* ]]; then
     fi
 fi
 
+if [[ "$FLOW" == *openvino* ]]; then
+    # Setup OpenVINO environment
+    source .ci/scripts/setup-openvino.sh --nightly
+    EXTRA_BUILD_ARGS+=" -DEXECUTORCH_BUILD_OPENVINO=ON"
+fi
+
 if [[ $IS_MACOS -eq 1 ]]; then
     SETUP_SCRIPT=.ci/scripts/setup-macos.sh
 else

.ci/scripts/test_model_e2e.sh

@@ -354,7 +354,7 @@ EOF
     fi
     ;;
   qwen3_5_moe)
-    RUNNER_ARGS="$RUNNER_ARGS --tokenizer_path ${MODEL_DIR}/$TOKENIZER_FILE --prompt 'What is the capital of France?' --max_new_tokens 32"
+    RUNNER_ARGS="$RUNNER_ARGS --tokenizer_path ${MODEL_DIR}/$TOKENIZER_FILE --prompt 'What is the capital of France?' --max_new_tokens 128 --temperature 0"
     ;;
   voxtral_realtime)
     RUNNER_ARGS="--model_path ${MODEL_DIR}/model.pte --tokenizer_path ${MODEL_DIR}/$TOKENIZER_FILE --preprocessor_path ${MODEL_DIR}/$PREPROCESSOR --audio_path ${MODEL_DIR}/$AUDIO_FILE --temperature 0"

.ci/scripts/test_model_e2e_windows.ps1

@@ -135,7 +135,19 @@ try {
     Write-Host "::group::Check CUDA toolchain"
     $nvccOutput = nvcc --version | Out-String
     Write-Host $nvccOutput
-    nvidia-smi
+    $nvidiaSmiCmd = Get-Command nvidia-smi -ErrorAction SilentlyContinue
+    if ($null -eq $nvidiaSmiCmd) {
+        Write-Host "nvidia-smi not available (command not found; driver may not be installed)"
+    }
+    else {
+        try {
+            nvidia-smi
+        }
+        catch {
+            Write-Host "nvidia-smi failed (driver or GPU issue). Error details:"
+            Write-Host $_
+        }
+    }
     if (-not [string]::IsNullOrWhiteSpace($ExpectedCudaVersion)) {
         $versionMatch = [Regex]::Match($nvccOutput, "release\s+(\d+\.\d+)")
         if (-not $versionMatch.Success) {

.ci/scripts/wheel/test_linux.py

@@ -11,18 +11,25 @@
 from examples.models import Backend, Model
 
 if __name__ == "__main__":
-    # On Linux x86_64 the wheel is built with the Qualcomm backend.
-    # Verify that it was registered correctly.
-    if platform.system() == "Linux" and platform.machine() in ("x86_64", "amd64"):
+    if platform.system() == "Linux":
         from executorch.extension.pybindings.portable_lib import (
             _get_registered_backend_names,
         )
 
         registered = _get_registered_backend_names()
+
+        # QNN backend is only available on x86_64.
+        if platform.machine() in ("x86_64", "amd64"):
+            assert (
+                "QnnBackend" in registered
+            ), f"QnnBackend not found in registered backends: {registered}"
+            print("✓ QnnBackend is registered")
+
+        # OpenVINO backend is available on all Linux architectures.
         assert (
-            "QnnBackend" in registered
-        ), f"QnnBackend not found in registered backends: {registered}"
-        print("✓ QnnBackend is registered")
+            "OpenvinoBackend" in registered
+        ), f"OpenvinoBackend not found in registered backends: {registered}"
+        print("✓ OpenvinoBackend is registered")
 
     test_base.run_tests(
         model_tests=[

.ci/scripts/wheel/test_linux_aarch64.py

@@ -12,6 +12,20 @@
     # coremltools does not support linux aarch64 yet and install from the source fails on runtime
     # https://github.com/apple/coremltools/issues/1254
     # https://github.com/apple/coremltools/issues/2195
+
+    from executorch.extension.pybindings.portable_lib import (
+        _get_registered_backend_names,
+    )
+
+    registered = _get_registered_backend_names()
+
+    # OpenVINO backend uses dlopen (no build-time SDK dependency), so it
+    # is compiled into the wheel on all Linux architectures.
+    assert (
+        "OpenvinoBackend" in registered
+    ), f"OpenvinoBackend not found in registered backends: {registered}"
+    print("✓ OpenvinoBackend is registered")
+
     test_base.run_tests(
         model_tests=[
             test_base.ModelTest(

.github/workflows/_test_backend.yml

@@ -4,7 +4,7 @@ on:
   workflow_call:
     inputs:
       backend:
-        description: 'Backend to test (xnnpack, coreml, vulkan, qnn)'
+        description: 'Backend to test (xnnpack, coreml, vulkan, qnn, openvino)'
         required: true
         type: string
       flows:

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

@@ -145,9 +145,9 @@ jobs:
         export BUILD_AAR_DIR=aar-out
         bash scripts/build_android_library.sh
         mkdir -p "${ARTIFACTS_DIR_NAME}"
-        cp aar-out/executorch.aar "${ARTIFACTS_DIR_NAME}/executorch.aar"
+        cp aar-out/executorch.aar "${ARTIFACTS_DIR_NAME}/executorch-${FLAVOR}.aar"
 
-        shasum -a 256 "${ARTIFACTS_DIR_NAME}/executorch.aar"
+        shasum -a 256 "${ARTIFACTS_DIR_NAME}/executorch-${FLAVOR}.aar"
 
         # Publish to maven staging
         UPLOAD_TO_MAVEN="${{ inputs.upload_to_maven }}"
@@ -165,18 +165,13 @@ jobs:
       contents: read
     steps:
       - name: configure aws credentials
-        uses: aws-actions/configure-aws-credentials@v1.7.0
+        uses: aws-actions/configure-aws-credentials@v4
         with:
           role-to-assume: arn:aws:iam::308535385114:role/gha_executorch_upload-frameworks-android
           aws-region: us-east-1
       - name: Upload AAR RC to AWS S3
         shell: bash
         run: |
-          wget https://gha-artifacts.s3.amazonaws.com/${{ github.repository }}/${{ github.run_id }}/artifacts/executorch.aar
-          shasum -a 256 executorch.aar > executorch.aar.sha256sums
-
-          pip install awscli==1.32.18
-          AWS_CMD="aws s3 cp"
           VERSION="${{ inputs.version }}"
           FLAVOR="${{ inputs.flavor }}"
           if [ -z "$VERSION" ]; then
@@ -185,5 +180,11 @@ jobs:
           if [ -z "$FLAVOR" ]; then
             FLAVOR="xnnpack"
           fi
+          wget https://gha-artifacts.s3.amazonaws.com/${{ github.repository }}/${{ github.run_id }}/artifacts/executorch-${FLAVOR}.aar
+          mv executorch-${FLAVOR}.aar executorch.aar
+          shasum -a 256 executorch.aar > executorch.aar.sha256sums
+
+          pip install awscli==1.32.18
+          AWS_CMD="aws s3 cp"
           ${AWS_CMD} executorch.aar s3://ossci-android/executorch/release/${VERSION}-${FLAVOR}/executorch.aar --acl public-read
           ${AWS_CMD} executorch.aar.sha256sums s3://ossci-android/executorch/release/${VERSION}-${FLAVOR}/executorch.aar.sha256sums --acl public-read

.github/workflows/android-release-on-tag.yml

@@ -6,6 +6,10 @@ on:
       - 'v*.*.*-rc*'
       - 'v*.*.*'
 
+permissions:
+  id-token: write
+  contents: read
+
 jobs:
   prepare:
     runs-on: ubuntu-latest