docs(readme): announce native voice-detect + face-detect backends in Latest News

Add a Latest News entry for the new from-scratch C++/ggml biometric backends
(voice-detect.cpp + face-detect.cpp) that replace the Python insightface and
speaker-recognition backends: no Python/onnxruntime at inference, self-contained
GGUF, bit-exact parity, GPU cuDNN parity. Mirrors the parakeet.cpp /
locate-anything.cpp native-backend news entries. Refs PR #10441.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

.github/backend-matrix.yml

@@ -3723,6 +3723,302 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  # voice-detect
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "8"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-12-voice-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-voice-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-voice-detect'
+    base-image: "ubuntu:24.04"
+    ubuntu-version: '2404'
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-voice-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-voice-detect'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'sycl_f32'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f32-voice-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'sycl_f16'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f16-voice-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-voice-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-voice-detect'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-arm64-voice-detect'
+    base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2204'
+  - build-type: 'hipblas'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-rocm-hipblas-voice-detect'
+    base-image: "rocm/dev-ubuntu-24.04:7.2.1"
+    runs-on: 'ubuntu-latest'
+    skip-drivers: 'false'
+    backend: "voice-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  # face-detect
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "8"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-12-face-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-face-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-face-detect'
+    base-image: "ubuntu:24.04"
+    ubuntu-version: '2404'
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-face-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-face-detect'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'sycl_f32'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f32-face-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'sycl_f16'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f16-face-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-face-detect'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-face-detect'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-arm64-face-detect'
+    base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2204'
+  - build-type: 'hipblas'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-rocm-hipblas-face-detect'
+    base-image: "rocm/dev-ubuntu-24.04:7.2.1"
+    runs-on: 'ubuntu-latest'
+    skip-drivers: 'false'
+    backend: "face-detect"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   # acestep-cpp
   - build-type: ''
     cuda-major-version: ""
@@ -4906,6 +5202,14 @@ includeDarwin:
     tag-suffix: "-metal-darwin-arm64-ced"
     build-type: "metal"
     lang: "go"
+  - backend: "voice-detect"
+    tag-suffix: "-metal-darwin-arm64-voice-detect"
+    build-type: "metal"
+    lang: "go"
+  - backend: "face-detect"
+    tag-suffix: "-metal-darwin-arm64-face-detect"
+    build-type: "metal"
+    lang: "go"
   - backend: "acestep-cpp"
     tag-suffix: "-metal-darwin-arm64-acestep-cpp"
     build-type: "metal"
@@ -4974,12 +5278,6 @@ includeDarwin:
   - backend: "kitten-tts"
     tag-suffix: "-metal-darwin-arm64-kitten-tts"
     build-type: "mps"
-  - backend: "trl"
-    tag-suffix: "-metal-darwin-arm64-trl"
-    build-type: "mps"
-  - backend: "liquid-audio"
-    tag-suffix: "-metal-darwin-arm64-liquid-audio"
-    build-type: "mps"
   - backend: "piper"
     tag-suffix: "-metal-darwin-arm64-piper"
     build-type: "metal"
@@ -4996,10 +5294,6 @@ includeDarwin:
     tag-suffix: "-metal-darwin-arm64-sherpa-onnx"
     build-type: "metal"
     lang: "go"
-  - backend: "supertonic"
-    tag-suffix: "-metal-darwin-arm64-supertonic"
-    build-type: "metal"
-    lang: "go"
   - backend: "local-store"
     tag-suffix: "-metal-darwin-arm64-local-store"
     build-type: "metal"

.github/workflows/backend.yml

@@ -44,7 +44,7 @@ jobs:
       has-merges-singlearch: ${{ steps.set-matrix.outputs['has-merges-singlearch'] }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
 
       - name: Setup Bun
         uses: oven-sh/setup-bun@v2

.github/workflows/backend_build.yml

@@ -101,7 +101,7 @@ jobs:
     steps:
 
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
 

.github/workflows/backend_build_darwin.yml

@@ -57,7 +57,7 @@ jobs:
       HOMEBREW_NO_ANALYTICS: '1'
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
 

.github/workflows/backend_merge.yml

@@ -49,7 +49,7 @@ jobs:
       # Sparse checkout: the merge job needs `.github/scripts/` (for the
       # keepalive cleanup script) but none of the source tree.
       - name: Checkout (.github/scripts only)
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           sparse-checkout: |
             .github/scripts

.github/workflows/backend_pr.yml

@@ -23,7 +23,7 @@ jobs:
       has-merges-singlearch: ${{ steps.set-matrix.outputs['has-merges-singlearch'] }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
 
       - name: Setup Bun
         uses: oven-sh/setup-bun@v2

.github/workflows/base-images.yml

@@ -127,7 +127,7 @@ jobs:
             # the original l4t matrix entry which set skip-drivers: 'true'.
             skip-drivers: 'true'
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           submodules: false
       - name: Free disk space

.github/workflows/build-test.yaml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Set up Go
@@ -25,7 +25,7 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Set up Go
@@ -47,7 +47,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Configure apt mirror on runner

.github/workflows/bump-inference-defaults.yml

@@ -14,7 +14,7 @@ jobs:
   bump:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
 
       - uses: actions/setup-go@v5
         with:

.github/workflows/bump_deps.yaml

@@ -46,6 +46,14 @@ jobs:
             variable: "CED_VERSION"
             branch: "master"
             file: "backend/go/ced/Makefile"
+          - repository: "mudler/voice-detect.cpp"
+            variable: "VOICEDETECT_VERSION"
+            branch: "master"
+            file: "backend/go/voice-detect/Makefile"
+          - repository: "mudler/face-detect.cpp"
+            variable: "FACEDETECT_VERSION"
+            branch: "master"
+            file: "backend/go/face-detect/Makefile"
           - repository: "mudler/depth-anything.cpp"
             variable: "DEPTHANYTHING_VERSION"
             branch: "master"
@@ -92,7 +100,7 @@ jobs:
             file: "backend/go/vibevoice-cpp/Makefile"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
       - name: Bump dependencies 🔧
         id: bump
         run: |
@@ -128,7 +136,7 @@ jobs:
     if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
       - name: Bump vLLM cu130 wheel pin 🔧
         id: bump
         run: |

.github/workflows/bump_docs.yaml

@@ -13,7 +13,7 @@ jobs:
           - repository: "mudler/LocalAI"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
       - name: Bump dependencies 🔧
         run: |
           bash .github/bump_docs.sh ${{ matrix.repository }}

.github/workflows/checksum_checker.yaml

@@ -8,7 +8,7 @@ jobs:
     if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
       - name: Configure apt mirror on runner
         uses: ./.github/actions/configure-apt-mirror
       - name: Install dependencies

.github/workflows/deploy-explorer.yaml

@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - uses: actions/setup-go@v5

.github/workflows/gallery-agent.yaml

@@ -31,7 +31,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
 

.github/workflows/generate_intel_image.yaml

@@ -44,7 +44,7 @@ jobs:
         uses: docker/setup-buildx-action@master
 
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
 
       - name: Cache Intel images
         uses: docker/build-push-action@v7

.github/workflows/gh-pages.yml

@@ -28,7 +28,7 @@ jobs:
       HUGO_VERSION: "0.146.3"
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0  # needed for enableGitInfo
           submodules: true

.github/workflows/image_build.yml

@@ -80,7 +80,7 @@ jobs:
     steps:
 
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
 
       - name: Configure apt mirror on runner
         id: apt_mirror

.github/workflows/image_merge.yml

@@ -36,7 +36,7 @@ jobs:
       # Sparse checkout: needed for .github/scripts/ (the keepalive cleanup
       # script). Skips the rest of the source tree.
       - name: Checkout (.github/scripts only)
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           sparse-checkout: |
             .github/scripts

.github/workflows/lint.yml

@@ -20,7 +20,7 @@ jobs:
   golangci-lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
         with:
           # Full history so golangci-lint's new-from-merge-base can reach
           # origin/master and compute the diff against it.

.github/workflows/release.yaml

@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Set up Go
@@ -28,7 +28,7 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Set up Go
@@ -46,7 +46,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           fetch-depth: 0
       - name: Configure apt mirror on runner

.github/workflows/secscan.yaml

@@ -14,7 +14,7 @@ jobs:
       GO111MODULE: on
     steps:
       - name: Checkout Source
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         if: ${{ github.actor != 'dependabot[bot]' }}
       - name: Run Gosec Security Scanner
         if: ${{ github.actor != 'dependabot[bot]' }}

.github/workflows/test-extra.yml

@@ -50,7 +50,7 @@ jobs:
       parakeet-cpp: ${{ steps.detect.outputs.parakeet-cpp }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
       - name: Setup Bun
         uses: oven-sh/setup-bun@v2
       - name: Install dependencies
@@ -67,7 +67,7 @@ jobs:
   #   runs-on: ubuntu-latest
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v7
+  #       uses: actions/checkout@v6
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -90,7 +90,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -113,7 +113,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -137,7 +137,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -158,7 +158,7 @@ jobs:
   #  runs-on: ubuntu-latest
   #  steps:
   #    - name: Clone
-  #      uses: actions/checkout@v7
+  #      uses: actions/checkout@v6
   #      with:
   #        submodules: true
   #    - name: Dependencies
@@ -178,7 +178,7 @@ jobs:
   #   runs-on: ubuntu-latest
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v7
+  #       uses: actions/checkout@v6
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -240,7 +240,7 @@ jobs:
   #           sudo rm -rf "$AGENT_TOOLSDIRECTORY" || true
   #           df -h
   #     - name: Clone
-  #       uses: actions/checkout@v7
+  #       uses: actions/checkout@v6
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -265,7 +265,7 @@ jobs:
   #   runs-on: ubuntu-latest
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v7
+  #       uses: actions/checkout@v6
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -288,7 +288,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -309,7 +309,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -330,7 +330,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -351,7 +351,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -373,7 +373,7 @@ jobs:
   #   timeout-minutes: 45
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v7
+  #       uses: actions/checkout@v6
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -394,7 +394,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -415,7 +415,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -436,7 +436,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -462,7 +462,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -484,7 +484,7 @@ jobs:
     timeout-minutes: 30
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -513,7 +513,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -530,7 +530,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -552,7 +552,7 @@ jobs:
     timeout-minutes: 20
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -579,7 +579,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -604,7 +604,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -625,7 +625,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -645,7 +645,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -664,7 +664,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -681,7 +681,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -698,7 +698,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -741,7 +741,7 @@ jobs:
   #   timeout-minutes: 90
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v7
+  #       uses: actions/checkout@v6
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -783,7 +783,7 @@ jobs:
   #   timeout-minutes: 90
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v7
+  #       uses: actions/checkout@v6
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -808,7 +808,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -840,7 +840,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -876,7 +876,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -915,7 +915,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -952,7 +952,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -987,7 +987,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -1013,7 +1013,7 @@ jobs:
     timeout-minutes: 150
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -1042,7 +1042,7 @@ jobs:
     timeout-minutes: 60
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go
@@ -1058,7 +1058,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -1091,7 +1091,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -1114,7 +1114,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies
@@ -1140,7 +1140,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies

.github/workflows/test.yml

@@ -21,7 +21,7 @@ jobs:
         go-version: ['1.26.x']
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Free disk space
@@ -84,7 +84,7 @@ jobs:
         go-version: ['1.26.x']
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Setup Go ${{ matrix.go-version }}

.github/workflows/tests-aio.yml

@@ -62,7 +62,7 @@ jobs:
           sudo rm -rfv build || true
           df -h
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Dependencies

.github/workflows/tests-e2e.yml

@@ -21,7 +21,7 @@ jobs:
         go-version: ['1.25.x']
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Configure apt mirror on runner

.github/workflows/tests-pii-ner-e2e.yml

@@ -1,97 +0,0 @@
----
-name: 'PII NER tier E2E (live GGUF, CPU)'
-
-# Runs the real privacy-filter GGUF NER tier end-to-end on CPU — the gap the
-# hermetic tests/e2e suite cannot cover (it only exercises the in-process
-# pattern tier). Heavy (builds the C++ backend image + downloads a ~2.7 GB
-# GGUF), so it is path-filtered on PRs and otherwise runs nightly / on demand.
-#
-# This drives the container-level harness (tests/e2e-backends) via
-# `make test-extra-backend-privacy-filter`: it builds the privacy-filter image,
-# downloads the model, loads it on CPU, and asserts byte-correct, UTF-8-aligned
-# TokenClassify spans. The complementary HTTP-path specs in tests/e2e
-# (e2e_pii_ner_test.go) Skip unless PII_NER_MODEL_GGUF is wired.
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: '0 3 * * *'
-  push:
-    branches:
-      - master
-    paths:
-      - 'backend/cpp/privacy-filter/**'
-      - 'backend/Dockerfile.privacy-filter'
-      - 'core/services/routing/pii/**'
-      - 'core/services/routing/piidetector/**'
-      - 'core/backend/token_classify.go'
-      - 'core/http/endpoints/localai/pii.go'
-      - 'core/schema/pii.go'
-      - 'tests/e2e-backends/**'
-      - 'tests/e2e/e2e_pii_ner_test.go'
-      - 'tests/e2e/e2e_suite_test.go'
-      - '.github/workflows/tests-pii-ner-e2e.yml'
-  pull_request:
-    paths:
-      - 'backend/cpp/privacy-filter/**'
-      - 'backend/Dockerfile.privacy-filter'
-      - 'core/services/routing/pii/**'
-      - 'core/services/routing/piidetector/**'
-      - 'core/backend/token_classify.go'
-      - 'core/http/endpoints/localai/pii.go'
-      - 'core/schema/pii.go'
-      - 'tests/e2e-backends/**'
-      - 'tests/e2e/e2e_pii_ner_test.go'
-      - 'tests/e2e/e2e_suite_test.go'
-      - '.github/workflows/tests-pii-ner-e2e.yml'
-
-concurrency:
-  group: ci-tests-pii-ner-e2e-${{ github.event.pull_request.number || github.sha }}-${{ github.repository }}
-  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
-
-jobs:
-  tests-pii-ner-e2e:
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        go-version: ['1.25.x']
-    steps:
-      - name: Clone
-        uses: actions/checkout@v7
-        with:
-          submodules: true
-      - name: Free disk space
-        run: |
-          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL || true
-          sudo docker image prune --all --force || true
-          df -h
-      - name: Configure apt mirror on runner
-        uses: ./.github/actions/configure-apt-mirror
-      - name: Setup Go ${{ matrix.go-version }}
-        uses: actions/setup-go@v5
-        with:
-          go-version: ${{ matrix.go-version }}
-          cache: false
-      - name: Proto Dependencies
-        run: |
-          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
-          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
-          rm protoc.zip
-          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
-          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
-          PATH="$PATH:$HOME/go/bin" make protogen-go
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y build-essential
-      # Builds local-ai-backend:privacy-filter, downloads the GGUF, loads it on
-      # CPU and runs the token_classify capability spec (byte-offset contract).
-      - name: Run live PII NER backend E2E
-        run: PATH="$PATH:$HOME/go/bin" make test-extra-backend-privacy-filter
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true

.github/workflows/tests-ui-e2e.yml

@@ -23,7 +23,7 @@ jobs:
         go-version: ['1.26.x']
     steps:
       - name: Clone
-        uses: actions/checkout@v7
+        uses: actions/checkout@v6
         with:
           submodules: true
       - name: Configure apt mirror on runner

.github/workflows/update_swagger.yaml

@@ -10,7 +10,7 @@ jobs:
       fail-fast: false
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v7
+      - uses: actions/checkout@v6
       - name: Configure apt mirror on runner
         uses: ./.github/actions/configure-apt-mirror
       - uses: actions/setup-go@v5

.gitignore

@@ -91,6 +91,3 @@ core/http/react-ui/test-results/
 
 # Local worktrees
 .worktrees/
-
-# SDD / brainstorm scratch (agent-driven development)
-.superpowers/

Makefile

@@ -690,16 +690,6 @@ test-extra-backend-llama-cpp-transcription: docker-build-llama-cpp
 	BACKEND_TEST_CTX_SIZE=2048 \
 	$(MAKE) test-extra-backend
 
-## privacy-filter: the PII/NER token-classification backend. Exercises the
-## TokenClassify RPC and asserts byte-correct, UTF-8-aligned span offsets
-## against the openai-privacy-filter multilingual GGUF (CPU-runnable, ~50M
-## active params). This is the live-backend coverage for the PII NER tier.
-test-extra-backend-privacy-filter: docker-build-privacy-filter
-	BACKEND_IMAGE=local-ai-backend:privacy-filter \
-	BACKEND_TEST_MODEL_URL=https://huggingface.co/LocalAI-io/privacy-filter-multilingual-GGUF/resolve/main/privacy-filter-multilingual-f16.gguf \
-	BACKEND_TEST_CAPS=health,load,token_classify \
-	$(MAKE) test-extra-backend
-
 ## vllm is resolved from a HuggingFace model id (no file download) and
 ## exercises Predict + streaming + tool-call extraction via the hermes parser.
 ## Requires a host CPU with the SIMD instructions the prebuilt vllm CPU

README.md

@@ -177,6 +177,7 @@ For more details, see the [Getting Started guide](https://localai.io/basics/gett
 
 ## Latest News
 
+- **June 2026**: New native biometric backends from the LocalAI team: [voice-detect.cpp](https://github.com/mudler/voice-detect.cpp) for speaker recognition and voice analysis (ECAPA-TDNN, WeSpeaker, ERes2Net, CAM++, wav2vec2 age/gender/emotion) and [face-detect.cpp](https://github.com/mudler/face-detect.cpp) for face detection, recognition, demographics and anti-spoofing (SCRFD/ArcFace, YuNet/SFace). Both are from-scratch C++/ggml engines with no Python or onnxruntime at inference, self-contained GGUF weights, bit-exact parity with the reference, and GPU cuDNN parity, replacing the heavier Python `insightface` and `speaker-recognition` backends ([PR #10441](https://github.com/mudler/LocalAI/pull/10441)).
 - **June 2026**: New [realtime voice assistant demo](https://github.com/localai-org/localai-realtime-demo) (a tiny Go client for the Realtime API with a full talk-back voice loop and tool calling), plus [streaming of the realtime LLM / TTS / transcription pipeline stages](https://github.com/mudler/LocalAI/pull/10176) and [configurable WebRTC ICE candidates](https://github.com/mudler/LocalAI/pull/10231).
 - **June 2026**: Big speech push: the [parakeet.cpp](https://github.com/mudler/parakeet.cpp) ASR engine gains [NeMo-faithful segment timestamps](https://github.com/mudler/LocalAI/pull/10207), a [multilingual streaming Nemotron-3.5 model](https://github.com/mudler/LocalAI/pull/10199), [dynamic batching for concurrent transcription](https://github.com/mudler/LocalAI/pull/10112) and [CUDA graphs](https://github.com/mudler/LocalAI/pull/10273); the new [CrispASR backend](https://github.com/mudler/LocalAI/pull/10099) adds multi-architecture ASR + TTS, and [60 Piper TTS voices across 42 languages](https://github.com/mudler/LocalAI/pull/10296) land in the gallery (plus [per-request TTS instructions and params](https://github.com/mudler/LocalAI/pull/10172)).
 - **June 2026**: New backends and models: [locate-anything.cpp](https://github.com/mudler/LocalAI/pull/10264) for open-vocabulary object detection via ggml, [Ideogram4 image generation](https://github.com/mudler/LocalAI/pull/10201) in stablediffusion-ggml, [llama.cpp video input](https://github.com/mudler/LocalAI/pull/10216), and the [Gemma 4 QAT family with MTP speculative-decoding pairs](https://github.com/mudler/LocalAI/pull/10215). Plus an [interactive CLI chat mode](https://github.com/mudler/LocalAI/pull/10226) and [RAG source citations in agent responses](https://github.com/mudler/LocalAI/pull/10228).

backend/Dockerfile.golang

@@ -137,7 +137,7 @@ RUN <<EOT bash
             libcusolver-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION}
         if [ "${CUDA_MAJOR_VERSION}" = "13" ] && [ "arm64" = "$TARGETARCH" ]; then
             apt-get install -y --no-install-recommends \
-            libcufile-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcudnn9-cuda-${CUDA_MAJOR_VERSION} cuda-cupti-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libnvjitlink-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION}
+            libcufile-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libcudnn9-cuda-${CUDA_MAJOR_VERSION} libcudnn9-dev-cuda-${CUDA_MAJOR_VERSION} cuda-cupti-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} libnvjitlink-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION}
         fi
         apt-get clean && \
         rm -rf /var/lib/apt/lists/*

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=d5507e33ae7ee2b7b41475f08044d3bde3b839ee
+IK_LLAMA_VERSION?=6c00e87ac84404af588ad2e65935bd6f079c696f
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=8be759e6f70d629638a7eb70db3824cbdcea370b
+LLAMA_VERSION?=e475fa2b5f9fb50c3d6fc3e7c6fdf1e004465b62
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/grpc-server.cpp

@@ -37,7 +37,6 @@
 #include "backend.pb.h"
 #include "backend.grpc.pb.h"
 #include "common.h"
-#include "arg.h"
 #include "chat-auto-parser.h"
 #include <getopt.h>
 #include <grpcpp/ext/proto_server_reflection_plugin.h>
@@ -593,10 +592,6 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
     params.checkpoint_min_step = 256;
 #endif
 
-    // Raw upstream llama-server flags collected from any option entry that
-    // starts with '-'. Applied once after the loop via common_params_parse.
-    std::vector<std::string> extra_argv;
-
      // decode options. Options are in form optname:optvale, or if booleans only optname.
     for (int i = 0; i < request->options_size(); i++) {
         std::string opt = request->options(i);
@@ -1085,31 +1080,6 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                 } catch (...) {}
             }
 
-        // --- main model MoE on CPU (upstream --cpu-moe / --n-cpu-moe) ---
-        } else if (!strcmp(optname, "cpu_moe")) {
-            // Bool-style flag: keep all MoE expert weights on CPU.
-            const bool enable = (optval == NULL) ||
-                optval_str == "true" || optval_str == "1" || optval_str == "yes" ||
-                optval_str == "on" || optval_str == "enabled";
-            if (enable) {
-                params.tensor_buft_overrides.push_back(llm_ffn_exps_cpu_override());
-            }
-        } else if (!strcmp(optname, "n_cpu_moe")) {
-            if (optval != NULL) {
-                try {
-                    int n = std::stoi(optval_str);
-                    if (n < 0) n = 0;
-                    // Keep override-name storage alive for the lifetime of the
-                    // params struct (mirrors upstream arg.cpp's function-local static).
-                    static std::list<std::string> buft_overrides_main;
-                    for (int i = 0; i < n; ++i) {
-                        buft_overrides_main.push_back(llm_ffn_exps_block_regex(i));
-                        params.tensor_buft_overrides.push_back(
-                            {buft_overrides_main.back().c_str(), ggml_backend_cpu_buffer_type()});
-                    }
-                } catch (...) {}
-            }
-
         // --- draft model tensor buffer overrides (upstream --spec-draft-override-tensor) ---
         } else if (!strcmp(optname, "draft_override_tensor") || !strcmp(optname, "spec_draft_override_tensor")) {
             // Format: <tensor regex>=<buffer type>,<tensor regex>=<buffer type>,...
@@ -1141,30 +1111,6 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                 else { cur.push_back(c); }
             }
             if (!cur.empty()) flush(cur);
-
-        // --- generic passthrough: any entry starting with '-' is a raw
-        //     upstream llama-server flag, forwarded verbatim to the parser. ---
-        } else if (optname[0] == '-') {
-            std::string flag = optname;
-            // These flags make upstream's parser exit() (printing usage /
-            // completion), which would kill the backend process. Skip them.
-            if (flag == "-h" || flag == "--help" || flag == "--usage" ||
-                flag == "--version" || flag == "--license" ||
-                flag == "--list-devices" || flag == "-cl" ||
-                flag == "--cache-list" ||
-                flag.rfind("--completion", 0) == 0) {
-                fprintf(stderr,
-                    "[llama-cpp] ignoring passthrough flag that would exit: %s\n",
-                    flag.c_str());
-            } else {
-                extra_argv.push_back(flag);
-                // Preserve the whole value after the first ':' so embedded
-                // colons (e.g. host:port) survive strtok's truncation of optval.
-                auto colon = opt.find(':');
-                if (colon != std::string::npos) {
-                    extra_argv.push_back(opt.substr(colon + 1));
-                }
-            }
         }
     }
 
@@ -1200,6 +1146,27 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
         }
     }
 
+    if (!params.kv_overrides.empty()) {
+        params.kv_overrides.emplace_back();
+        params.kv_overrides.back().key[0] = 0;
+    }
+
+    // tensor_buft_overrides sentinel termination (mirrors upstream common/arg.cpp).
+    // Real entries are pushed during option parsing; here we pad/terminate so the
+    // model loader sees back().pattern == nullptr (GGML_ASSERT at common.cpp:1543)
+    // and so llama_params_fit has the placeholder slots it requires.
+    {
+        const size_t ntbo = llama_max_tensor_buft_overrides();
+        while (params.tensor_buft_overrides.size() < ntbo) {
+            params.tensor_buft_overrides.push_back({nullptr, nullptr});
+        }
+    }
+    // Terminate the draft tensor_buft_overrides list with a sentinel, mirroring
+    // the main-model handling above.
+    if (!params.speculative.draft.tensor_buft_overrides.empty()) {
+        params.speculative.draft.tensor_buft_overrides.push_back({nullptr, nullptr});
+    }
+
     // TODO: Add yarn
 
     if (!request->tensorsplit().empty()) {
@@ -1292,69 +1259,6 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
             params.sampling.grammar_triggers.push_back(std::move(trigger));
         }
     }
-
-    // Apply any raw upstream flags last so an explicit passthrough flag wins
-    // over the LocalAI-resolved field it maps to (e.g. --ctx-size beats
-    // context_size). This is the same parser llama-server itself uses.
-    if (!extra_argv.empty()) {
-        // common_params_parser_init resets a few fields for the SERVER example
-        // (n_parallel -> -1, use_color). Snapshot n_parallel so an unrelated
-        // passthrough flag can't silently clobber LocalAI's resolved value.
-        const int saved_n_parallel = params.n_parallel;
-
-        std::vector<char *> argv;
-        std::string prog = "llama-server";
-        argv.push_back(prog.data());
-        for (auto & a : extra_argv) {
-            argv.push_back(a.data());
-        }
-
-        // ctx_arg.params is a reference, so this overlays the given flags onto
-        // `params` in place. Returns false on a recoverable parse error (and
-        // self-restores params); may exit() on a hard error, exactly as
-        // passing the same bad flag to llama-server would.
-        if (!common_params_parse((int)argv.size(), argv.data(), params,
-                                 LLAMA_EXAMPLE_SERVER)) {
-            fprintf(stderr,
-                "[llama-cpp] failed to parse passthrough options; ignoring them\n");
-        }
-
-        // Restore n_parallel unless a passthrough flag explicitly set it
-        // (parser_init's reset sentinel for SERVER is -1).
-        if (params.n_parallel == -1) {
-            params.n_parallel = saved_n_parallel;
-        }
-    }
-
-    // Terminate/pad the override vectors only after BOTH the named-option loop
-    // and the generic passthrough (common_params_parse above) have pushed their
-    // real entries, so back() is the null sentinel the model loader asserts on.
-    // Running these before the passthrough let a passthrough flag (--cpu-moe,
-    // --override-tensor, --override-kv, ...) append a real entry after the
-    // sentinel: a GGML_ASSERT crash for tensor_buft_overrides, a silent drop for
-    // kv_overrides. Double-termination is harmless (the while is a no-op if the
-    // passthrough parse already padded; an extra trailing null is ignored).
-
-    if (!params.kv_overrides.empty()) {
-        params.kv_overrides.emplace_back();
-        params.kv_overrides.back().key[0] = 0;
-    }
-
-    // tensor_buft_overrides sentinel termination (mirrors upstream common/arg.cpp).
-    // Real entries are pushed during option parsing; here we pad/terminate so the
-    // model loader sees back().pattern == nullptr (GGML_ASSERT at common.cpp:1543)
-    // and so llama_params_fit has the placeholder slots it requires.
-    {
-        const size_t ntbo = llama_max_tensor_buft_overrides();
-        while (params.tensor_buft_overrides.size() < ntbo) {
-            params.tensor_buft_overrides.push_back({nullptr, nullptr});
-        }
-    }
-    // Terminate the draft tensor_buft_overrides list with a sentinel, mirroring
-    // the main-model handling above.
-    if (!params.speculative.draft.tensor_buft_overrides.empty()) {
-        params.speculative.draft.tensor_buft_overrides.push_back({nullptr, nullptr});
-    }
 }
 
 

backend/go/acestep-cpp/Makefile

@@ -117,8 +117,7 @@ libgoacestepcpp-custom: CMakeLists.txt cpp/goacestepcpp.cpp cpp/goacestepcpp.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target goacestepcpp && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgoacestepcpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgoacestepcpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgoacestepcpp.so ./$(SO_TARGET)
 
 test: acestep-cpp
 	@echo "Running acestep-cpp tests..."

backend/go/acestep-cpp/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -23,11 +22,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("ACESTEP_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgoacestepcpp-fallback.dylib"
-		} else {
-			libName = "./libgoacestepcpp-fallback.so"
-		}
+		libName = "./libgoacestepcpp-fallback.so"
 	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/acestep-cpp/package.sh

@@ -13,7 +13,6 @@ mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/acestep-cpp $CURDIR/package/
 cp -fv $CURDIR/libgoacestepcpp-*.so $CURDIR/package/
-cp -fv $CURDIR/libgoacestepcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/acestep-cpp/run.sh

@@ -12,19 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single library variant (Metal or Accelerate). The goacestepcpp
-	# target is built as a CMake MODULE, which emits a .dylib for a SHARED
-	# build but a .so for a MODULE build on Apple, so prefer .dylib and fall
-	# back to .so.
-	LIBRARY="$CURDIR/libgoacestepcpp-fallback.dylib"
-	if [ ! -e "$LIBRARY" ]; then
-		LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
-	fi
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
+LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgoacestepcpp-avx.so ]; then
@@ -46,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgoacestepcpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export ACESTEP_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/ced/Makefile

@@ -57,7 +57,6 @@ libced.so: sources/ced.cpp
 	cmake -B sources/ced.cpp/build-shared -S sources/ced.cpp $(CMAKE_ARGS)
 	cmake --build sources/ced.cpp/build-shared --config Release -j$(JOBS)
 	cp -fv sources/ced.cpp/build-shared/libced.so* ./ 2>/dev/null || true
-	cp -fv sources/ced.cpp/build-shared/libced.dylib ./ 2>/dev/null || true
 	cp -fv sources/ced.cpp/include/ced_capi.h ./
 
 ced-grpc: libced.so main.go goced.go

backend/go/ced/main.go

@@ -12,7 +12,6 @@ import (
 	"flag"
 	"fmt"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,11 +27,7 @@ type libFunc struct {
 func main() {
 	libName := os.Getenv("CED_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "libced.dylib"
-		} else {
-			libName = "libced.so"
-		}
+		libName = "libced.so"
 	}
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/ced/package.sh

@@ -15,12 +15,10 @@ mkdir -p "$CURDIR/package/lib"
 cp -avf "$CURDIR/ced-grpc" "$CURDIR/package/"
 cp -avf "$CURDIR/run.sh" "$CURDIR/package/"
 
-cp -avf "$CURDIR"/libced.so* "$CURDIR/package/lib/" 2>/dev/null || true
-cp -avf "$CURDIR"/libced.dylib "$CURDIR/package/lib/" 2>/dev/null || true
-if ! ls "$CURDIR"/package/lib/libced.* >/dev/null 2>&1; then
-	echo "ERROR: libced shared library not found in $CURDIR, run 'make' first" >&2
+cp -avf "$CURDIR"/libced.so* "$CURDIR/package/lib/" 2>/dev/null || {
+	echo "ERROR: libced.so not found in $CURDIR, run 'make' first" >&2
 	exit 1
-fi
+}
 
 if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
     echo "Detected x86_64 architecture, copying x86_64 libraries..."

backend/go/ced/run.sh

@@ -3,12 +3,7 @@ set -e
 
 CURDIR=$(dirname "$(realpath "$0")")
 
-if [ "$(uname)" = "Darwin" ]; then
-	export DYLD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${DYLD_LIBRARY_PATH:-}"
-	export CED_LIBRARY="$CURDIR/lib/libced.dylib"
-else
-	export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
-fi
+export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
 
 # If a self-contained ld.so was packaged, route through it so the packaged
 # libc / libstdc++ are used instead of the host's (matches the sibling backends).

backend/go/crispasr/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # CrispASR version (release tag)
 CRISPASR_REPO?=https://github.com/CrispStrobe/CrispASR
-CRISPASR_VERSION?=96b2a6ee31d30389fed8a7ef1a54239b75231ddc
+CRISPASR_VERSION?=d745bda4386ae0f9d1d2f23fff8ec95d76428221
 SO_TARGET?=libgocrispasr.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -75,8 +75,7 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgocrispasr-avx.so libgocrispasr-avx2.so libgocrispasr-avx512.so libgocrispasr-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
-	VARIANT_TARGETS = libgocrispasr-fallback.dylib
+	VARIANT_TARGETS = libgocrispasr-fallback.so
 endif
 
 crispasr: main.go gocrispasr.go $(VARIANT_TARGETS)
@@ -88,7 +87,7 @@ package: crispasr
 build: package
 
 clean: purge
-	rm -rf libgocrispasr*.so libgocrispasr*.dylib package sources/CrispASR crispasr
+	rm -rf libgocrispasr*.so package sources/CrispASR crispasr
 
 purge:
 	rm -rf build*
@@ -119,21 +118,13 @@ libgocrispasr-fallback.so: sources/CrispASR
 	SO_TARGET=libgocrispasr-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgocrispasr-custom
 	rm -rfv build*
 
-# Build fallback variant as a dylib (Darwin)
-libgocrispasr-fallback.dylib: sources/CrispASR
-	$(MAKE) purge
-	$(info ${GREEN}I crispasr build info:fallback (dylib)${RESET})
-	SO_TARGET=libgocrispasr-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgocrispasr-custom
-	rm -rfv build*
-
 libgocrispasr-custom: CMakeLists.txt cpp/crispasr_shim.cpp cpp/crispasr_shim.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgocrispasr.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgocrispasr.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgocrispasr.so ./$(SO_TARGET)
 
 test: crispasr
 	CGO_ENABLED=0 $(GOCMD) test -v ./...

backend/go/crispasr/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("CRISPASR_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgocrispasr-fallback.dylib"
-		} else {
-			libName = "./libgocrispasr-fallback.so"
-		}
+		libName = "./libgocrispasr-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/crispasr/package.sh

@@ -12,8 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/crispasr $CURDIR/package/
-cp -fv $CURDIR/libgocrispasr-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgocrispasr-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgocrispasr-*.so $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/crispasr/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgocrispasr-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgocrispasr-fallback.so"
+LIBRARY="$CURDIR/libgocrispasr-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgocrispasr-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgocrispasr-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export CRISPASR_LIBRARY=$LIBRARY
 
 # Point piper's espeak-ng phonemizer at the bundled voice data. The variable

backend/go/depth-anything-cpp/Makefile

@@ -77,7 +77,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libdepthanythingcpp-avx.so libdepthanythingcpp-avx2.so libdepthanythingcpp-avx512.so libdepthanythingcpp-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = libdepthanythingcpp-fallback.dylib
+	VARIANT_TARGETS = libdepthanythingcpp-fallback.so
 endif
 
 depth-anything-cpp: main.go godepthanythingcpp.go $(VARIANT_TARGETS)
@@ -89,7 +89,7 @@ package: depth-anything-cpp
 build: package
 
 clean: purge
-	rm -rf libdepthanythingcpp*.so libdepthanythingcpp*.dylib depth-anything-cpp package sources
+	rm -rf libdepthanythingcpp*.so depth-anything-cpp package sources
 
 purge:
 	rm -rf build*
@@ -116,19 +116,11 @@ libdepthanythingcpp-avx512.so: sources/depth-anything.cpp
 endif
 
 # Build fallback variant (all platforms)
-ifeq ($(UNAME_S),Darwin)
-libdepthanythingcpp-fallback.dylib: sources/depth-anything.cpp
-	rm -rfv build-$@
-	$(info ${GREEN}I depth-anything-cpp build info:fallback${RESET})
-	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libdepthanythingcpp-custom
-	rm -rfv build-$@
-else
 libdepthanythingcpp-fallback.so: sources/depth-anything.cpp
 	rm -rfv build-$@
 	$(info ${GREEN}I depth-anything-cpp build info:fallback${RESET})
 	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libdepthanythingcpp-custom
 	rm -rfv build-$@
-endif
 
 libdepthanythingcpp-custom: CMakeLists.txt
 	mkdir -p build-$(SO_TARGET) && \
@@ -136,8 +128,7 @@ libdepthanythingcpp-custom: CMakeLists.txt
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libdepthanything.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libdepthanything.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libdepthanything.so ./$(SO_TARGET)
 
 all: depth-anything-cpp package
 

backend/go/depth-anything-cpp/main.go

@@ -9,7 +9,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,11 +27,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("DEPTHANYTHING_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libdepthanythingcpp-fallback.dylib"
-		} else {
-			libName = "./libdepthanythingcpp-fallback.so"
-		}
+		libName = "./libdepthanythingcpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/depth-anything-cpp/package.sh

@@ -10,8 +10,7 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -fv $CURDIR/libdepthanythingcpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libdepthanythingcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -avf $CURDIR/libdepthanythingcpp-*.so $CURDIR/package/
 cp -avf $CURDIR/depth-anything-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/depth-anything-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libdepthanythingcpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libdepthanythingcpp-fallback.so"
+LIBRARY="$CURDIR/libdepthanythingcpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libdepthanythingcpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libdepthanythingcpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export DEPTHANYTHING_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/face-detect/.gitignore

@@ -0,0 +1,18 @@
+# Fetched upstream sources
+sources/
+
+# CMake build directories
+build*/
+
+# build artifacts staged in-tree by the Makefile (cp from sources/) or
+# symlinked for local dev; the real sources live in face-detect.cpp upstream.
+*.so
+*.so.*
+facedetect_capi.h
+compile_commands.json
+
+# Compiled backend binary
+face-detect-grpc
+
+# Packaging output
+package/

backend/go/face-detect/Makefile

@@ -0,0 +1,110 @@
+# face-detect backend Makefile.
+#
+# Upstream pin lives below as FACEDETECT_VERSION?=6107a24... (.github/bump_deps.sh
+# can find and update it - matches the voice-detect / parakeet.cpp / whisper.cpp
+# convention).
+#
+# Local dev shortcut: if you already have an out-of-tree face-detect.cpp build,
+# symlink the .so + header into this directory and skip the clone/cmake steps:
+#
+#   ln -sf /path/to/face-detect.cpp/build-shared/libfacedetect.so .
+#   ln -sf /path/to/face-detect.cpp/include/facedetect_capi.h .
+#   go build -o face-detect-grpc .
+#
+# The default target below does the proper clone-at-pin + cmake build so CI does
+# not need a side-checkout.
+
+FACEDETECT_VERSION?=6107a2414fdaccc9ce8650b762f9436d20541cbe
+FACEDETECT_REPO?=https://github.com/mudler/face-detect.cpp
+
+GOCMD?=go
+GO_TAGS?=
+JOBS?=$(shell nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)
+
+BUILD_TYPE?=
+NATIVE?=false
+
+# Resolve the target arch. The backend matrix / Docker build pass TARGETARCH
+# (amd64|arm64); fall back to uname -m (aarch64|x86_64) for a local build.
+RECON_ARCH?=$(or $(TARGETARCH),$(shell uname -m))
+
+# Build ggml + the vendored libjpeg-turbo statically into libfacedetect.so (PIC)
+# so the shared lib is self-contained: dlopen needs no libggml*.so alongside it,
+# only system libs (libstdc++/libgomp/libc) the runtime image already provides.
+# The vendored jpeg symbols are hidden via -Wl,--exclude-libs,ALL on the C++
+# side, so only the facedetect_capi_* surface is exported.
+CMAKE_ARGS?=-DCMAKE_BUILD_TYPE=Release -DFACEDETECT_SHARED=ON -DFACEDETECT_BUILD_CLI=OFF -DFACEDETECT_BUILD_TESTS=OFF -DBUILD_SHARED_LIBS=OFF -DCMAKE_POSITION_INDEPENDENT_CODE=ON
+
+ifeq ($(NATIVE),false)
+	CMAKE_ARGS+=-DGGML_NATIVE=OFF
+endif
+
+# face-detect.cpp gates its GGML backends behind FACEDETECT_GGML_* options and
+# does set(GGML_CUDA ${FACEDETECT_GGML_CUDA} CACHE BOOL "" FORCE), so a bare
+# -DGGML_CUDA=ON is overwritten back to OFF. Forward the FACEDETECT_GGML_*
+# options instead. (openblas is not gated, so -DGGML_BLAS passes through.)
+ifeq ($(BUILD_TYPE),cublas)
+	CMAKE_ARGS+=-DFACEDETECT_GGML_CUDA=ON
+	# Opt-in cuDNN implicit-GEMM conv path (kills im2col on GPU, SCRFD 2.3x
+	# vs torch-cuDNN parity). Only the arm64 + CUDA 13 image (GB10/Jetson/L4T)
+	# ships libcudnn9 + the -dev headers, so gate cuDNN to that variant.
+	# x86 CUDA images carry no cuDNN -> enabling it there is a link failure.
+	ifeq ($(CUDA_MAJOR_VERSION),13)
+	ifneq (,$(filter arm64 aarch64,$(RECON_ARCH)))
+		CMAKE_ARGS+=-DFACEDETECT_GGML_CUDNN=ON
+	endif
+	endif
+else ifeq ($(BUILD_TYPE),openblas)
+	CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+else ifeq ($(BUILD_TYPE),hipblas)
+	CMAKE_ARGS+=-DFACEDETECT_GGML_HIP=ON
+else ifeq ($(BUILD_TYPE),vulkan)
+	CMAKE_ARGS+=-DFACEDETECT_GGML_VULKAN=ON
+else ifeq ($(BUILD_TYPE),metal)
+	CMAKE_ARGS+=-DFACEDETECT_GGML_METAL=ON
+endif
+
+.PHONY: face-detect-grpc package build clean purge test all
+
+all: face-detect-grpc
+
+# Clone the upstream face-detect.cpp source at the pinned commit. Directory acts
+# as the target so make only re-clones when missing. After a FACEDETECT_VERSION
+# bump, run 'make purge && make' to refetch.
+sources/face-detect.cpp:
+	mkdir -p sources/face-detect.cpp
+	cd sources/face-detect.cpp && \
+	git init -q && \
+	git remote add origin $(FACEDETECT_REPO) && \
+	git fetch --depth 1 origin $(FACEDETECT_VERSION) && \
+	git checkout FETCH_HEAD && \
+	git submodule update --init --recursive --depth 1 --single-branch
+
+# Build the shared lib + header out-of-tree, then stage them next to the Go
+# sources so purego.Dlopen("libfacedetect.so") and the cgo-less build both pick
+# them up.
+libfacedetect.so: sources/face-detect.cpp
+	cmake -B sources/face-detect.cpp/build-shared -S sources/face-detect.cpp $(CMAKE_ARGS)
+	cmake --build sources/face-detect.cpp/build-shared --config Release -j$(JOBS) --target facedetect
+	cp -fv sources/face-detect.cpp/build-shared/libfacedetect.so* ./ 2>/dev/null || true
+	cp -fv sources/face-detect.cpp/include/facedetect_capi.h ./
+
+face-detect-grpc: libfacedetect.so main.go gofacedetect.go options.go
+	CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o face-detect-grpc .
+
+package: face-detect-grpc
+	bash package.sh
+
+build: package
+
+# Test target. The embed/detect/verify/analyze smoke specs are gated on
+# FACEDETECT_BACKEND_TEST_MODEL + FACEDETECT_BACKEND_TEST_IMAGE; without them the
+# heavy specs auto-skip and only the pure-Go parsing specs run.
+test:
+	LD_LIBRARY_PATH=$(CURDIR):$$LD_LIBRARY_PATH $(GOCMD) test ./... -count=1
+
+clean: purge
+	rm -rf libfacedetect.so* facedetect_capi.h package face-detect-grpc
+
+purge:
+	rm -rf sources/face-detect.cpp

backend/go/face-detect/gofacedetect.go

@@ -0,0 +1,431 @@
+package main
+
+import (
+	"encoding/base64"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"math"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+	"unsafe"
+
+	"github.com/mudler/LocalAI/pkg/grpc/base"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/mudler/xlog"
+)
+
+// purego-bound entry points from libfacedetect.so. Names match
+// facedetect_capi.h exactly so a `nm libfacedetect.so | grep facedetect_capi`
+// is enough to spot drift.
+//
+// The opaque ctx and the malloc'd char*/float* return values are declared as
+// uintptr so we get the raw pointer back and can release it via the matching
+// capi free function. purego's native string/[]float32 returns would copy and
+// forget the original pointer, leaking the C-owned buffer on every call.
+var (
+	CppAbiVersion  func() int32
+	CppLoad        func(ggufPath string) uintptr
+	CppFree        func(ctx uintptr)
+	CppLastError   func(ctx uintptr) string
+	CppFreeString  func(s uintptr)
+	CppFreeVec     func(v uintptr)
+	CppEmbedPath   func(ctx uintptr, imagePath string, outVec, outDim unsafe.Pointer) int32
+	CppEmbedRGB    func(ctx uintptr, rgb []byte, width, height int32, outVec, outDim unsafe.Pointer) int32
+	CppDetectJSON  func(ctx uintptr, imagePath string) uintptr
+	CppVerifyPaths func(ctx uintptr, a, b string, threshold float32, antiSpoof int32, outDistance, outVerified unsafe.Pointer) int32
+	CppAnalyzeJSON func(ctx uintptr, imagePath string) uintptr
+)
+
+// FaceDetect implements the face-recognition (biometric) subset of the Backend
+// gRPC service over libfacedetect.so. The C side keeps a single loaded model
+// pack plus a per-ctx last-error buffer and is not reentrant, so
+// base.SingleThread serializes every call.
+type FaceDetect struct {
+	base.SingleThread
+	opts   loadOptions
+	ctxPtr uintptr
+}
+
+func (f *FaceDetect) Load(opts *pb.ModelOptions) error {
+	model := opts.ModelFile
+	if model == "" {
+		model = opts.ModelPath
+	}
+	if !filepath.IsAbs(model) && opts.ModelPath != "" {
+		model = filepath.Join(opts.ModelPath, model)
+	}
+	if model == "" {
+		return errors.New("face-detect: ModelFile is required")
+	}
+
+	f.opts = parseOptions(opts.Options)
+	if f.opts.modelName == "" {
+		f.opts.modelName = filepath.Base(model)
+	}
+
+	// Propagate LocalAI's per-model thread budget to the engine. LocalAI spawns
+	// one backend process per model and serves requests concurrently, so the
+	// engine's own min(hardware_concurrency, 8) default can oversubscribe cores.
+	// FACEDETECT_THREADS is read by the engine at backend construction, so it
+	// must be set before the capi load. A non-positive Threads means "unset":
+	// leave the env alone so the engine keeps its sane default.
+	threads := opts.Threads
+	if threads > 0 {
+		if err := os.Setenv("FACEDETECT_THREADS", strconv.Itoa(int(threads))); err != nil {
+			return fmt.Errorf("face-detect: set FACEDETECT_THREADS: %w", err)
+		}
+		xlog.Info("face-detect: applying LocalAI thread budget", "threads", threads)
+	}
+
+	xlog.Info("face-detect: loading model", "model", model,
+		"verify_threshold", f.opts.verifyThreshold, "abi", CppAbiVersion())
+
+	ctx := CppLoad(model)
+	if ctx == 0 {
+		// The last-error buffer lives on the ctx that was never returned, so
+		// surface the path the operator tried to load instead.
+		return fmt.Errorf("face-detect: facedetect_capi_load failed for %q", model)
+	}
+	f.ctxPtr = ctx
+	return nil
+}
+
+// Embeddings returns the L2-normalized ArcFace embedding of the primary face in
+// the supplied image. Mirroring the Python face backend, the image is read from
+// Images[0] as a base64 payload; materializeImage decodes it to a temp file so
+// the path-based C-API can run its own decode (cv2.imread parity). The gRPC
+// server wraps the returned slice in an EmbeddingResult.
+func (f *FaceDetect) Embeddings(req *pb.PredictOptions) ([]float32, error) {
+	if f.ctxPtr == 0 {
+		return nil, errors.New("face-detect: model not loaded")
+	}
+	if len(req.Images) == 0 || req.Images[0] == "" {
+		return nil, errors.New("face-detect: Embedding requires Images[0] to be a base64 image")
+	}
+
+	path, cleanup, err := materializeImage(req.Images[0])
+	if err != nil {
+		return nil, err
+	}
+	defer cleanup()
+
+	return f.embedPath(path)
+}
+
+func (f *FaceDetect) embedPath(path string) ([]float32, error) {
+	var vec uintptr
+	var dim int32
+	rc := CppEmbedPath(f.ctxPtr, path, unsafe.Pointer(&vec), unsafe.Pointer(&dim))
+	if rc != 0 || vec == 0 || dim <= 0 {
+		return nil, f.lastErr("embed", path)
+	}
+	defer CppFreeVec(vec)
+	// Copy out of the C-owned malloc'd buffer before freeing it. The
+	// uintptr->Pointer conversion trips vet's unsafeptr check, which can't tell
+	// a C heap pointer from Go-managed memory; safe here, the GC neither tracks
+	// nor moves this buffer and we copy immediately.
+	src := unsafe.Slice((*float32)(unsafe.Pointer(vec)), int(dim)) //nolint:govet // C-owned malloc'd vector, copied out before free
+	out := make([]float32, int(dim))
+	copy(out, src)
+	return out, nil
+}
+
+// Detect runs SCRFD over the image and returns one Detection per face. The
+// C-API emits a box as [x1,y1,x2,y2] in pixels; the proto carries x/y plus
+// width/height, so the corners are converted. The 5 facial landmarks the engine
+// also returns are dropped: the Detection message has no field for them.
+func (f *FaceDetect) Detect(req *pb.DetectOptions) (pb.DetectResponse, error) {
+	if f.ctxPtr == 0 {
+		return pb.DetectResponse{}, errors.New("face-detect: model not loaded")
+	}
+	if req.Src == "" {
+		return pb.DetectResponse{}, errors.New("face-detect: src image is required")
+	}
+
+	path, cleanup, err := materializeImage(req.Src)
+	if err != nil {
+		return pb.DetectResponse{}, err
+	}
+	defer cleanup()
+
+	faces, err := f.detectFaces(path)
+	if err != nil {
+		return pb.DetectResponse{}, err
+	}
+
+	dets := make([]*pb.Detection, 0, len(faces))
+	for _, fc := range faces {
+		if req.Threshold > 0 && fc.Score < req.Threshold {
+			continue
+		}
+		x, y, w, h := fc.xywh()
+		dets = append(dets, &pb.Detection{
+			X:          x,
+			Y:          y,
+			Width:      w,
+			Height:     h,
+			Confidence: fc.Score,
+			ClassName:  "face",
+		})
+	}
+	return pb.DetectResponse{Detections: dets}, nil
+}
+
+// FaceVerify embeds the primary face in each image and reports whether they are
+// the same identity by cosine distance against a threshold. A request threshold
+// <= 0 falls back to the model-configured default (verify_threshold option,
+// 0.35 if unset). When anti_spoofing is set, the C-API applies a MiniFASNet
+// veto internally (verified forced false on a spoof); the per-image liveness
+// scores are not exposed by the verify entry point, so img*_is_real /
+// img*_antispoof_score stay at their zero values.
+func (f *FaceDetect) FaceVerify(req *pb.FaceVerifyRequest) (pb.FaceVerifyResponse, error) {
+	if f.ctxPtr == 0 {
+		return pb.FaceVerifyResponse{}, errors.New("face-detect: model not loaded")
+	}
+	if req.Img1 == "" || req.Img2 == "" {
+		return pb.FaceVerifyResponse{}, errors.New("face-detect: img1 and img2 are required")
+	}
+
+	path1, cleanup1, err := materializeImage(req.Img1)
+	if err != nil {
+		return pb.FaceVerifyResponse{}, err
+	}
+	defer cleanup1()
+	path2, cleanup2, err := materializeImage(req.Img2)
+	if err != nil {
+		return pb.FaceVerifyResponse{}, err
+	}
+	defer cleanup2()
+
+	threshold := req.Threshold
+	if threshold <= 0 {
+		threshold = f.opts.verifyThreshold
+	}
+
+	antiSpoof := int32(0)
+	if req.AntiSpoofing {
+		antiSpoof = 1
+	}
+
+	started := time.Now()
+	var distance float32
+	var verified int32
+	rc := CppVerifyPaths(f.ctxPtr, path1, path2, threshold, antiSpoof,
+		unsafe.Pointer(&distance), unsafe.Pointer(&verified))
+	if rc != 0 {
+		return pb.FaceVerifyResponse{}, f.lastErr("verify", req.Img1[:min(8, len(req.Img1))]+"...")
+	}
+	elapsedMs := float32(time.Since(started).Seconds() * 1000.0)
+
+	// Confidence decays linearly from 100 at distance 0 to 0 at the threshold,
+	// matching the Python face backend's reporting.
+	confidence := float32(0)
+	if threshold > 0 {
+		confidence = float32(math.Max(0, math.Min(100, (1.0-float64(distance)/float64(threshold))*100.0)))
+	}
+
+	return pb.FaceVerifyResponse{
+		Verified:         verified != 0,
+		Distance:         distance,
+		Threshold:        threshold,
+		Confidence:       confidence,
+		Model:            f.opts.modelName,
+		Img1Area:         f.bestArea(path1),
+		Img2Area:         f.bestArea(path2),
+		ProcessingTimeMs: elapsedMs,
+	}, nil
+}
+
+// FaceAnalyze runs the genderage head on every detected face. The C-API returns
+// "M"/"F" gender labels and a rounded age; the labels are normalized to the
+// "Man"/"Woman" values the proto documents.
+func (f *FaceDetect) FaceAnalyze(req *pb.FaceAnalyzeRequest) (pb.FaceAnalyzeResponse, error) {
+	if f.ctxPtr == 0 {
+		return pb.FaceAnalyzeResponse{}, errors.New("face-detect: model not loaded")
+	}
+	if req.Img == "" {
+		return pb.FaceAnalyzeResponse{}, errors.New("face-detect: img is required")
+	}
+
+	path, cleanup, err := materializeImage(req.Img)
+	if err != nil {
+		return pb.FaceAnalyzeResponse{}, err
+	}
+	defer cleanup()
+
+	ptr := CppAnalyzeJSON(f.ctxPtr, path)
+	if ptr == 0 {
+		return pb.FaceAnalyzeResponse{}, f.lastErr("analyze", path)
+	}
+	defer CppFreeString(ptr)
+
+	faces, err := parseAnalyzeJSON(goStringFromCPtr(ptr))
+	if err != nil {
+		return pb.FaceAnalyzeResponse{}, fmt.Errorf("face-detect: analyze JSON: %w", err)
+	}
+	return pb.FaceAnalyzeResponse{Faces: faces}, nil
+}
+
+// faceBox is one entry of the detect/analyze JSON documents the engine emits.
+type faceBox struct {
+	Score  float32   `json:"score"`
+	Box    []float32 `json:"box"`
+	Age    float32   `json:"age"`
+	Gender string    `json:"gender"`
+}
+
+// xywh converts the engine's [x1,y1,x2,y2] box into the x/y/width/height the
+// proto carries. A short or missing box yields zeros.
+func (b faceBox) xywh() (x, y, w, h float32) {
+	if len(b.Box) < 4 {
+		return 0, 0, 0, 0
+	}
+	return b.Box[0], b.Box[1], b.Box[2] - b.Box[0], b.Box[3] - b.Box[1]
+}
+
+type facesJSON struct {
+	Faces []faceBox `json:"faces"`
+}
+
+func (f *FaceDetect) detectFaces(path string) ([]faceBox, error) {
+	ptr := CppDetectJSON(f.ctxPtr, path)
+	if ptr == 0 {
+		return nil, f.lastErr("detect", path)
+	}
+	defer CppFreeString(ptr)
+
+	var doc facesJSON
+	if err := json.Unmarshal([]byte(goStringFromCPtr(ptr)), &doc); err != nil {
+		return nil, fmt.Errorf("face-detect: detect JSON: %w", err)
+	}
+	return doc.Faces, nil
+}
+
+// bestArea returns the FacialArea of the highest-scoring face in an image, or an
+// empty area when detection fails or finds nothing. Best-effort: verify already
+// succeeded, so a missing region must not turn a valid match into an error.
+func (f *FaceDetect) bestArea(path string) *pb.FacialArea {
+	faces, err := f.detectFaces(path)
+	if err != nil || len(faces) == 0 {
+		return &pb.FacialArea{}
+	}
+	best := faces[0]
+	for _, fc := range faces[1:] {
+		if fc.Score > best.Score {
+			best = fc
+		}
+	}
+	x, y, w, h := best.xywh()
+	return &pb.FacialArea{X: x, Y: y, W: w, H: h}
+}
+
+// parseAnalyzeJSON maps the engine's analyze document onto FaceAnalysis entries.
+// The engine reports gender as "M"/"F"; both the dominant label and the score
+// map are filled with the "Man"/"Woman" form the proto documents.
+func parseAnalyzeJSON(doc string) ([]*pb.FaceAnalysis, error) {
+	var parsed facesJSON
+	if err := json.Unmarshal([]byte(doc), &parsed); err != nil {
+		return nil, err
+	}
+
+	out := make([]*pb.FaceAnalysis, 0, len(parsed.Faces))
+	for _, fc := range parsed.Faces {
+		x, y, w, h := fc.xywh()
+		fa := &pb.FaceAnalysis{
+			Region:         &pb.FacialArea{X: x, Y: y, W: w, H: h},
+			FaceConfidence: fc.Score,
+			Age:            fc.Age,
+		}
+		if label := normalizeGender(fc.Gender); label != "" {
+			fa.DominantGender = label
+			fa.Gender = map[string]float32{label: 1.0}
+		}
+		out = append(out, fa)
+	}
+	return out, nil
+}
+
+// normalizeGender maps the engine's "M"/"F" code to the "Man"/"Woman" labels the
+// proto documents. Unknown codes pass through unchanged.
+func normalizeGender(g string) string {
+	switch strings.ToUpper(strings.TrimSpace(g)) {
+	case "M":
+		return "Man"
+	case "F":
+		return "Woman"
+	case "":
+		return ""
+	default:
+		return g
+	}
+}
+
+// materializeImage decodes a base64 image payload into a temp file and returns
+// its path plus a cleanup func. As a convenience for callers that already pass a
+// filesystem path (e.g. a test fixture), an existing path is used as-is with a
+// no-op cleanup. data: URI prefixes are stripped before decoding.
+func materializeImage(src string) (path string, cleanup func(), err error) {
+	noop := func() {}
+	if src == "" {
+		return "", noop, errors.New("face-detect: empty image input")
+	}
+	if _, statErr := os.Stat(src); statErr == nil {
+		return src, noop, nil
+	}
+
+	payload := src
+	if i := strings.Index(payload, ","); strings.HasPrefix(payload, "data:") && i >= 0 {
+		payload = payload[i+1:]
+	}
+	data, decErr := base64.StdEncoding.DecodeString(strings.TrimSpace(payload))
+	if decErr != nil || len(data) == 0 {
+		return "", noop, errors.New("face-detect: image is neither an existing path nor valid base64")
+	}
+
+	tmp, createErr := os.CreateTemp("", "face-detect-*.img")
+	if createErr != nil {
+		return "", noop, fmt.Errorf("face-detect: create temp image: %w", createErr)
+	}
+	cleanup = func() { _ = os.Remove(tmp.Name()) }
+	if _, wErr := tmp.Write(data); wErr != nil {
+		_ = tmp.Close()
+		cleanup()
+		return "", noop, fmt.Errorf("face-detect: write temp image: %w", wErr)
+	}
+	if cErr := tmp.Close(); cErr != nil {
+		cleanup()
+		return "", noop, fmt.Errorf("face-detect: close temp image: %w", cErr)
+	}
+	return tmp.Name(), cleanup, nil
+}
+
+// lastErr wraps the C-API's per-ctx last-error buffer into a Go error.
+func (f *FaceDetect) lastErr(op, subject string) error {
+	msg := strings.TrimSpace(CppLastError(f.ctxPtr))
+	if msg == "" {
+		msg = "no error detail"
+	}
+	return fmt.Errorf("face-detect: %s failed for %q: %s", op, subject, msg)
+}
+
+// goStringFromCPtr copies a NUL-terminated C string into Go memory. cptr is a
+// malloc'd buffer the caller owns; release it via CppFreeString after the copy.
+//
+// The uintptr->Pointer conversion trips vet's unsafeptr check, which can't tell
+// a C heap pointer from Go-managed memory. Safe here: the GC neither tracks nor
+// moves the buffer and we dereference it immediately to copy the bytes out.
+func goStringFromCPtr(cptr uintptr) string {
+	if cptr == 0 {
+		return ""
+	}
+	p := unsafe.Pointer(cptr) //nolint:govet // C-owned malloc'd buffer, not Go-GC memory (see doc above)
+	n := 0
+	for *(*byte)(unsafe.Add(p, n)) != 0 {
+		n++
+	}
+	return string(unsafe.Slice((*byte)(p), n))
+}

backend/go/face-detect/gofacedetect_test.go

@@ -0,0 +1,230 @@
+package main
+
+import (
+	"encoding/base64"
+	"os"
+	"sync"
+	"testing"
+
+	"github.com/ebitengine/purego"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+func TestFaceDetect(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "face-detect Backend Suite")
+}
+
+var (
+	libLoadOnce sync.Once
+	libLoadErr  error
+)
+
+// ensureLibLoaded mirrors main.go's bootstrap so a Go test can drive the C-API
+// bridge without spinning up the gRPC server. Records the error (the smoke
+// specs skip themselves) when libfacedetect.so is not loadable from cwd
+// (LD_LIBRARY_PATH or a symlink in ./).
+func ensureLibLoaded() error {
+	libLoadOnce.Do(func() {
+		libName := os.Getenv("FACEDETECT_LIBRARY")
+		if libName == "" {
+			libName = "libfacedetect.so"
+		}
+		lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+		if err != nil {
+			libLoadErr = err
+			return
+		}
+		purego.RegisterLibFunc(&CppAbiVersion, lib, "facedetect_capi_abi_version")
+		purego.RegisterLibFunc(&CppLoad, lib, "facedetect_capi_load")
+		purego.RegisterLibFunc(&CppFree, lib, "facedetect_capi_free")
+		purego.RegisterLibFunc(&CppLastError, lib, "facedetect_capi_last_error")
+		purego.RegisterLibFunc(&CppFreeString, lib, "facedetect_capi_free_string")
+		purego.RegisterLibFunc(&CppFreeVec, lib, "facedetect_capi_free_vec")
+		purego.RegisterLibFunc(&CppEmbedPath, lib, "facedetect_capi_embed_path")
+		purego.RegisterLibFunc(&CppEmbedRGB, lib, "facedetect_capi_embed_rgb")
+		purego.RegisterLibFunc(&CppDetectJSON, lib, "facedetect_capi_detect_path_json")
+		purego.RegisterLibFunc(&CppVerifyPaths, lib, "facedetect_capi_verify_paths")
+		purego.RegisterLibFunc(&CppAnalyzeJSON, lib, "facedetect_capi_analyze_path_json")
+	})
+	return libLoadErr
+}
+
+var _ = Describe("parseOptions", func() {
+	It("defaults verify_threshold to 0.35", func() {
+		o := parseOptions(nil)
+		Expect(o.verifyThreshold).To(Equal(float32(0.35)))
+		Expect(o.modelName).To(Equal(""))
+	})
+
+	It("parses verify_threshold, threshold alias and model_name", func() {
+		o := parseOptions([]string{"verify_threshold:0.4", "model_name:buffalo_l", "unknown:x"})
+		Expect(o.verifyThreshold).To(Equal(float32(0.4)))
+		Expect(o.modelName).To(Equal("buffalo_l"))
+
+		o2 := parseOptions([]string{"threshold:0.3"})
+		Expect(o2.verifyThreshold).To(Equal(float32(0.3)))
+	})
+
+	It("ignores non-positive thresholds and keeps the default", func() {
+		o := parseOptions([]string{"verify_threshold:0", "threshold:-1"})
+		Expect(o.verifyThreshold).To(Equal(float32(0.35)))
+	})
+})
+
+var _ = Describe("normalizeGender", func() {
+	It("maps M/F codes to Man/Woman", func() {
+		Expect(normalizeGender("M")).To(Equal("Man"))
+		Expect(normalizeGender("f")).To(Equal("Woman"))
+		Expect(normalizeGender(" m ")).To(Equal("Man"))
+	})
+
+	It("passes empty and unknown codes through", func() {
+		Expect(normalizeGender("")).To(Equal(""))
+		Expect(normalizeGender("nonbinary")).To(Equal("nonbinary"))
+	})
+})
+
+var _ = Describe("faceBox.xywh", func() {
+	It("converts an [x1,y1,x2,y2] box to x/y/width/height", func() {
+		b := faceBox{Box: []float32{10, 20, 50, 80}}
+		x, y, w, h := b.xywh()
+		Expect(x).To(Equal(float32(10)))
+		Expect(y).To(Equal(float32(20)))
+		Expect(w).To(Equal(float32(40)))
+		Expect(h).To(Equal(float32(60)))
+	})
+
+	It("returns zeros for a short box", func() {
+		x, y, w, h := faceBox{Box: []float32{1, 2}}.xywh()
+		Expect([]float32{x, y, w, h}).To(Equal([]float32{0, 0, 0, 0}))
+	})
+})
+
+var _ = Describe("parseAnalyzeJSON", func() {
+	It("maps region, age and gender for each face", func() {
+		doc := `{"faces":[
+			{"score":0.997,"box":[10,20,50,80],"age":31,"gender":"M"},
+			{"score":0.81,"box":[0,0,40,40],"age":24,"gender":"F"}]}`
+		faces, err := parseAnalyzeJSON(doc)
+		Expect(err).ToNot(HaveOccurred())
+		Expect(faces).To(HaveLen(2))
+
+		Expect(faces[0].FaceConfidence).To(BeNumerically("~", 0.997, 1e-4))
+		Expect(faces[0].Age).To(BeNumerically("~", 31, 1e-4))
+		Expect(faces[0].DominantGender).To(Equal("Man"))
+		Expect(faces[0].Gender).To(HaveKeyWithValue("Man", float32(1.0)))
+		Expect(faces[0].Region.W).To(Equal(float32(40)))
+		Expect(faces[0].Region.H).To(Equal(float32(60)))
+
+		Expect(faces[1].DominantGender).To(Equal("Woman"))
+	})
+
+	It("tolerates a missing gender field", func() {
+		faces, err := parseAnalyzeJSON(`{"faces":[{"score":0.5,"box":[0,0,10,10],"age":40}]}`)
+		Expect(err).ToNot(HaveOccurred())
+		Expect(faces).To(HaveLen(1))
+		Expect(faces[0].DominantGender).To(Equal(""))
+		Expect(faces[0].Gender).To(BeEmpty())
+	})
+
+	It("returns no faces for an empty document", func() {
+		faces, err := parseAnalyzeJSON(`{"faces":[]}`)
+		Expect(err).ToNot(HaveOccurred())
+		Expect(faces).To(BeEmpty())
+	})
+
+	It("returns an error on malformed JSON", func() {
+		_, err := parseAnalyzeJSON(`{not-json`)
+		Expect(err).To(HaveOccurred())
+	})
+})
+
+var _ = Describe("materializeImage", func() {
+	It("decodes a base64 payload to a temp file", func() {
+		payload := base64.StdEncoding.EncodeToString([]byte("\xff\xd8\xff\xe0fake-jpeg"))
+		path, cleanup, err := materializeImage(payload)
+		Expect(err).ToNot(HaveOccurred())
+		defer cleanup()
+		data, rerr := os.ReadFile(path)
+		Expect(rerr).ToNot(HaveOccurred())
+		Expect(data).To(Equal([]byte("\xff\xd8\xff\xe0fake-jpeg")))
+	})
+
+	It("strips a data: URI prefix before decoding", func() {
+		payload := "data:image/png;base64," + base64.StdEncoding.EncodeToString([]byte("hello"))
+		path, cleanup, err := materializeImage(payload)
+		Expect(err).ToNot(HaveOccurred())
+		defer cleanup()
+		data, rerr := os.ReadFile(path)
+		Expect(rerr).ToNot(HaveOccurred())
+		Expect(data).To(Equal([]byte("hello")))
+	})
+
+	It("uses an existing path as-is", func() {
+		tmp, err := os.CreateTemp("", "face-detect-fixture-*.bin")
+		Expect(err).ToNot(HaveOccurred())
+		defer func() { _ = os.Remove(tmp.Name()) }()
+		Expect(tmp.Close()).To(Succeed())
+
+		path, cleanup, err := materializeImage(tmp.Name())
+		Expect(err).ToNot(HaveOccurred())
+		defer cleanup()
+		Expect(path).To(Equal(tmp.Name()))
+	})
+
+	It("errors on input that is neither a path nor base64", func() {
+		_, _, err := materializeImage("not base64!!!")
+		Expect(err).To(HaveOccurred())
+	})
+})
+
+// The specs below exercise the real C-API end to end. They run only when both a
+// model GGUF and a test image are provided, and skip cleanly otherwise so the
+// suite stays green without large assets.
+var _ = Describe("FaceDetect end-to-end", Ordered, func() {
+	var (
+		f         *FaceDetect
+		modelPath = os.Getenv("FACEDETECT_BACKEND_TEST_MODEL")
+		imagePath = os.Getenv("FACEDETECT_BACKEND_TEST_IMAGE")
+	)
+
+	BeforeAll(func() {
+		if modelPath == "" || imagePath == "" {
+			Skip("set FACEDETECT_BACKEND_TEST_MODEL and FACEDETECT_BACKEND_TEST_IMAGE to run the e2e specs")
+		}
+		if err := ensureLibLoaded(); err != nil {
+			Skip("libfacedetect.so not loadable: " + err.Error())
+		}
+		f = &FaceDetect{}
+		Expect(f.Load(&pb.ModelOptions{ModelFile: modelPath})).To(Succeed())
+	})
+
+	It("embeds the primary face in an image", func() {
+		emb, err := f.Embeddings(&pb.PredictOptions{Images: []string{imagePath}})
+		Expect(err).ToNot(HaveOccurred())
+		Expect(emb).ToNot(BeEmpty())
+	})
+
+	It("detects at least one face", func() {
+		resp, err := f.Detect(&pb.DetectOptions{Src: imagePath})
+		Expect(err).ToNot(HaveOccurred())
+		Expect(resp.Detections).ToNot(BeEmpty())
+		Expect(resp.Detections[0].ClassName).To(Equal("face"))
+	})
+
+	It("verifies an image against itself as the same identity", func() {
+		resp, err := f.FaceVerify(&pb.FaceVerifyRequest{Img1: imagePath, Img2: imagePath})
+		Expect(err).ToNot(HaveOccurred())
+		Expect(resp.Verified).To(BeTrue())
+		Expect(resp.Distance).To(BeNumerically("<=", resp.Threshold))
+	})
+
+	It("analyzes age/gender for each face", func() {
+		resp, err := f.FaceAnalyze(&pb.FaceAnalyzeRequest{Img: imagePath})
+		Expect(err).ToNot(HaveOccurred())
+		Expect(resp.Faces).ToNot(BeEmpty())
+	})
+})

backend/go/face-detect/main.go

@@ -0,0 +1,65 @@
+package main
+
+// Started internally by LocalAI - one gRPC server per loaded model.
+//
+// Loads libfacedetect.so via purego and registers the flat C-API entry points
+// declared in facedetect_capi.h. The library name can be overridden with
+// FACEDETECT_LIBRARY (mirrors the VOICEDETECT_LIBRARY / PARAKEET_LIBRARY
+// convention in the sibling backends); the default looks for the .so next to
+// this binary (resolved via LD_LIBRARY_PATH by run.sh).
+import (
+	"flag"
+	"fmt"
+	"os"
+
+	"github.com/ebitengine/purego"
+	grpc "github.com/mudler/LocalAI/pkg/grpc"
+)
+
+var (
+	addr = flag.String("addr", "localhost:50051", "the address to connect to")
+)
+
+type LibFuncs struct {
+	FuncPtr any
+	Name    string
+}
+
+func main() {
+	libName := os.Getenv("FACEDETECT_LIBRARY")
+	if libName == "" {
+		libName = "libfacedetect.so"
+	}
+
+	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+	if err != nil {
+		panic(fmt.Errorf("face-detect: dlopen %q: %w", libName, err))
+	}
+
+	// Bound 1:1 to facedetect_capi.h. char*/float* returns are registered as
+	// uintptr so the raw pointer can be freed via the matching capi free fn.
+	libFuncs := []LibFuncs{
+		{&CppAbiVersion, "facedetect_capi_abi_version"},
+		{&CppLoad, "facedetect_capi_load"},
+		{&CppFree, "facedetect_capi_free"},
+		{&CppLastError, "facedetect_capi_last_error"},
+		{&CppFreeString, "facedetect_capi_free_string"},
+		{&CppFreeVec, "facedetect_capi_free_vec"},
+		{&CppEmbedPath, "facedetect_capi_embed_path"},
+		{&CppEmbedRGB, "facedetect_capi_embed_rgb"},
+		{&CppDetectJSON, "facedetect_capi_detect_path_json"},
+		{&CppVerifyPaths, "facedetect_capi_verify_paths"},
+		{&CppAnalyzeJSON, "facedetect_capi_analyze_path_json"},
+	}
+	for _, lf := range libFuncs {
+		purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
+	}
+
+	fmt.Fprintf(os.Stderr, "[face-detect] ABI=%d\n", CppAbiVersion())
+
+	flag.Parse()
+
+	if err := grpc.StartServer(*addr, &FaceDetect{}); err != nil {
+		panic(err)
+	}
+}

backend/go/face-detect/options.go

@@ -0,0 +1,47 @@
+package main
+
+import (
+	"strconv"
+	"strings"
+)
+
+// defaultVerifyThreshold is the cosine-distance cutoff used when a request does
+// not set one. Matches the insightface buffalo_l ArcFace R50 default the Python
+// face backend ships with so the two implementations agree on verdicts out of
+// the box.
+const defaultVerifyThreshold float32 = 0.35
+
+// loadOptions holds the parsed model-level options for face-detect.
+type loadOptions struct {
+	verifyThreshold float32
+	modelName       string
+}
+
+func splitOption(o string) (key, value string, ok bool) {
+	i := strings.Index(o, ":")
+	if i < 0 {
+		return "", "", false
+	}
+	return strings.TrimSpace(o[:i]), strings.TrimSpace(o[i+1:]), true
+}
+
+// parseOptions reads the backend "key:value" option slice. Unknown keys are
+// ignored. Defaults: verify_threshold 0.35, model_name derived from the file.
+func parseOptions(opts []string) loadOptions {
+	o := loadOptions{verifyThreshold: defaultVerifyThreshold}
+	for _, oo := range opts {
+		key, value, ok := splitOption(oo)
+		if !ok {
+			continue
+		}
+		switch key {
+		case "verify_threshold", "threshold":
+			if f, err := strconv.ParseFloat(value, 32); err == nil && f > 0 {
+				o.verifyThreshold = float32(f)
+			}
+		case "model_name":
+			o.modelName = value
+		}
+	}
+	return o
+}

backend/go/face-detect/package.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+#
+# Bundle the face-detect-grpc binary, libfacedetect.so, the core runtime libs
+# (libc/libstdc++/libgomp + ld.so) and the GPU runtime for the active BUILD_TYPE
+# so the package is self-contained. Mirrors backend/go/voice-detect/package.sh;
+# run.sh routes the (CGO_ENABLED=0) binary through lib/ld.so so the packaged libc
+# is used instead of the host's.
+
+set -e
+
+CURDIR=$(dirname "$(realpath "$0")")
+REPO_ROOT="${CURDIR}/../../.."
+
+mkdir -p "$CURDIR/package/lib"
+
+cp -avf "$CURDIR/face-detect-grpc" "$CURDIR/package/"
+cp -avf "$CURDIR/run.sh" "$CURDIR/package/"
+
+# libfacedetect.so + any soname symlinks. purego.Dlopen resolves it via
+# LD_LIBRARY_PATH, which run.sh points at lib/.
+cp -avf "$CURDIR"/libfacedetect.so* "$CURDIR/package/lib/" 2>/dev/null || {
+	echo "ERROR: libfacedetect.so not found in $CURDIR, run 'make' first" >&2
+	exit 1
+}
+
+# Detect architecture and copy the core runtime libs libfacedetect.so links
+# against, plus the matching dynamic loader as lib/ld.so.
+if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
+    echo "Detected x86_64 architecture, copying x86_64 libraries..."
+    cp -arfLv /lib64/ld-linux-x86-64.so.2 "$CURDIR/package/lib/ld.so"
+    cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 "$CURDIR/package/lib/libc.so.6"
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 "$CURDIR/package/lib/libgcc_s.so.1"
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 "$CURDIR/package/lib/libstdc++.so.6"
+    cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 "$CURDIR/package/lib/libm.so.6"
+    cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 "$CURDIR/package/lib/libgomp.so.1"
+    cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 "$CURDIR/package/lib/libdl.so.2"
+    cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 "$CURDIR/package/lib/librt.so.1"
+    cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 "$CURDIR/package/lib/libpthread.so.0"
+elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
+    echo "Detected ARM64 architecture, copying ARM64 libraries..."
+    cp -arfLv /lib/ld-linux-aarch64.so.1 "$CURDIR/package/lib/ld.so"
+    cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 "$CURDIR/package/lib/libc.so.6"
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 "$CURDIR/package/lib/libgcc_s.so.1"
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 "$CURDIR/package/lib/libstdc++.so.6"
+    cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 "$CURDIR/package/lib/libm.so.6"
+    cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 "$CURDIR/package/lib/libgomp.so.1"
+    cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 "$CURDIR/package/lib/libdl.so.2"
+    cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 "$CURDIR/package/lib/librt.so.1"
+    cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 "$CURDIR/package/lib/libpthread.so.0"
+elif [ "$(uname -s)" = "Darwin" ]; then
+    echo "Detected Darwin"
+else
+    echo "Error: Could not detect architecture"
+    exit 1
+fi
+
+# Package GPU libraries (CUDA/ROCm/Intel/Vulkan loader + ICDs + drivers) based on
+# BUILD_TYPE so the backend can reach the GPU without the runtime base image
+# shipping those drivers.
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
+echo "Packaging completed successfully"
+ls -liah "$CURDIR/package/" "$CURDIR/package/lib/"

backend/go/face-detect/run.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath "$0")")
+
+export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
+
+# If a self-contained ld.so was packaged, route through it so the packaged
+# libc / libstdc++ are used instead of the host's (matches the voice-detect /
+# whisper / parakeet backends' runtime layout).
+if [ -f "$CURDIR/lib/ld.so" ]; then
+	echo "Using lib/ld.so"
+	exec "$CURDIR/lib/ld.so" "$CURDIR/face-detect-grpc" "$@"
+fi
+
+exec "$CURDIR/face-detect-grpc" "$@"

backend/go/face-detect/test.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath "$0")")
+cd "$CURDIR"
+
+echo "Running face-detect backend tests..."
+
+# The pure-Go parsing specs always run. The embed/detect/verify/analyze smoke
+# specs run only when a model + image are provided via
+# FACEDETECT_BACKEND_TEST_MODEL and FACEDETECT_BACKEND_TEST_IMAGE; otherwise they
+# auto-skip.
+LD_LIBRARY_PATH="$CURDIR:${LD_LIBRARY_PATH:-}" go test -v -timeout 1200s .
+
+echo "face-detect tests completed."

backend/go/localvqe/Makefile

@@ -67,9 +67,8 @@ $(LIB_SENTINEL): sources/LocalVQE
 	# that the loader picks at runtime. We must build every target — the
 	# default `--target localvqe_shared` drops these. CMAKE_LIBRARY_OUTPUT_DIRECTORY
 	# routes all of them into build/bin; copy them out next to the binary.
-	cp -P build/bin/liblocalvqe.so* . 2>/dev/null || cp -P build/bin/liblocalvqe.dylib . 2>/dev/null || cp -P build/liblocalvqe.so* . 2>/dev/null || cp -P build/liblocalvqe.dylib .
+	cp -P build/bin/liblocalvqe.so* . 2>/dev/null || cp -P build/liblocalvqe.so* .
 	cp -P build/bin/libggml*.so* . 2>/dev/null || true
-	cp -P build/bin/libggml*.dylib . 2>/dev/null || true
 	touch $(LIB_SENTINEL)
 
 liblocalvqe.so: $(LIB_SENTINEL)

backend/go/localvqe/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("LOCALVQE_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./liblocalvqe.dylib"
-		} else {
-			libName = "./liblocalvqe.so"
-		}
+		libName = "./liblocalvqe.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/localvqe/package.sh

@@ -15,9 +15,7 @@ cp -avf $CURDIR/localvqe $CURDIR/package/
 # liblocalvqe.so* (with SOVERSION symlinks) and the libggml-*.so runtime
 # variants — LocalVQE picks the matching CPU variant at load time.
 cp -P $CURDIR/liblocalvqe.so* $CURDIR/package/ 2>/dev/null || true
-cp -P $CURDIR/liblocalvqe.dylib $CURDIR/package/ 2>/dev/null || true
 cp -P $CURDIR/libggml*.so* $CURDIR/package/ 2>/dev/null || true
-cp -P $CURDIR/libggml*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/localvqe/run.sh

@@ -10,19 +10,8 @@ CURDIR=$(dirname "$(realpath $0)")
 # exec'ing the binary.
 cd "$CURDIR"
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: LocalVQE is built as a SHARED library, so dyld needs the .dylib +
-	# DYLD_LIBRARY_PATH. Prefer .dylib and fall back to .so just in case.
-	export DYLD_LIBRARY_PATH=$CURDIR:$CURDIR/lib:$DYLD_LIBRARY_PATH
-	LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.dylib
-	if [ ! -e "$LOCALVQE_LIBRARY" ]; then
-		LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.so
-	fi
-	export LOCALVQE_LIBRARY
-else
-	export LD_LIBRARY_PATH=$CURDIR:$CURDIR/lib:$LD_LIBRARY_PATH
-	export LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.so
-fi
+export LD_LIBRARY_PATH=$CURDIR:$CURDIR/lib:$LD_LIBRARY_PATH
+export LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.so
 
 if [ -f $CURDIR/lib/ld.so ]; then
 	echo "Using lib/ld.so"

backend/go/locate-anything-cpp/Makefile

@@ -70,7 +70,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = liblocateanythingcpp-avx.so liblocateanythingcpp-avx2.so liblocateanythingcpp-avx512.so liblocateanythingcpp-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = liblocateanythingcpp-fallback.dylib
+	VARIANT_TARGETS = liblocateanythingcpp-fallback.so
 endif
 
 locate-anything-cpp: main.go golocateanythingcpp.go $(VARIANT_TARGETS)
@@ -82,7 +82,7 @@ package: locate-anything-cpp
 build: package
 
 clean: purge
-	rm -rf liblocateanythingcpp*.so liblocateanythingcpp*.dylib locate-anything-cpp package sources
+	rm -rf liblocateanythingcpp*.so locate-anything-cpp package sources
 
 purge:
 	rm -rf build*
@@ -109,19 +109,11 @@ liblocateanythingcpp-avx512.so: sources/locate-anything.cpp
 endif
 
 # Build fallback variant (all platforms)
-ifeq ($(UNAME_S),Darwin)
-liblocateanythingcpp-fallback.dylib: sources/locate-anything.cpp
-	rm -rfv build-$@
-	$(info ${GREEN}I locate-anything-cpp build info:fallback${RESET})
-	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) liblocateanythingcpp-custom
-	rm -rfv build-$@
-else
 liblocateanythingcpp-fallback.so: sources/locate-anything.cpp
 	rm -rfv build-$@
 	$(info ${GREEN}I locate-anything-cpp build info:fallback${RESET})
 	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) liblocateanythingcpp-custom
 	rm -rfv build-$@
-endif
 
 liblocateanythingcpp-custom: CMakeLists.txt
 	mkdir -p build-$(SO_TARGET) && \
@@ -129,8 +121,7 @@ liblocateanythingcpp-custom: CMakeLists.txt
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/liblocateanythingcpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/liblocateanythingcpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/liblocateanythingcpp.so ./$(SO_TARGET)
 
 all: locate-anything-cpp package
 

backend/go/locate-anything-cpp/main.go

@@ -9,7 +9,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,11 +27,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("LOCATEANYTHING_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./liblocateanythingcpp-fallback.dylib"
-		} else {
-			libName = "./liblocateanythingcpp-fallback.so"
-		}
+		libName = "./liblocateanythingcpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/locate-anything-cpp/package.sh

@@ -10,8 +10,7 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -fv $CURDIR/liblocateanythingcpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/liblocateanythingcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -avf $CURDIR/liblocateanythingcpp-*.so $CURDIR/package/
 cp -avf $CURDIR/locate-anything-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/locate-anything-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/liblocateanythingcpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/liblocateanythingcpp-fallback.so"
+LIBRARY="$CURDIR/liblocateanythingcpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/liblocateanythingcpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/liblocateanythingcpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export LOCATEANYTHING_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/omnivoice-cpp/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # omnivoice.cpp version
 OMNIVOICE_REPO?=https://github.com/ServeurpersoCom/omnivoice.cpp
-OMNIVOICE_VERSION?=0f37401bebe9b20c0160a888e592108fc1d17607
+OMNIVOICE_VERSION?=96d30169afd5e6bb3fd6a0e9be0eb505bfe81fcd
 SO_TARGET?=libgomnivoicecpp.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -65,8 +65,7 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgomnivoicecpp-avx.so libgomnivoicecpp-avx2.so libgomnivoicecpp-avx512.so libgomnivoicecpp-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
-	VARIANT_TARGETS = libgomnivoicecpp-fallback.dylib
+	VARIANT_TARGETS = libgomnivoicecpp-fallback.so
 endif
 
 omnivoice-cpp: main.go gomnivoicecpp.go $(VARIANT_TARGETS)
@@ -78,7 +77,7 @@ package: omnivoice-cpp
 build: package
 
 clean: purge
-	rm -rf libgomnivoicecpp*.so libgomnivoicecpp*.dylib package sources/omnivoice.cpp omnivoice-cpp
+	rm -rf libgomnivoicecpp*.so package sources/omnivoice.cpp omnivoice-cpp
 
 purge:
 	rm -rf build*
@@ -107,20 +106,13 @@ libgomnivoicecpp-fallback.so: sources/omnivoice.cpp
 	SO_TARGET=libgomnivoicecpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomnivoicecpp-custom
 	rm -rf build-libgomnivoicecpp-fallback.so
 
-# Build fallback variant as a dylib (Darwin)
-libgomnivoicecpp-fallback.dylib: sources/omnivoice.cpp
-	$(info ${GREEN}I omnivoice-cpp build info:fallback (dylib)${RESET})
-	SO_TARGET=libgomnivoicecpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomnivoicecpp-custom
-	rm -rf build-libgomnivoicecpp-fallback.dylib
-
 libgomnivoicecpp-custom: CMakeLists.txt cpp/gomnivoicecpp.cpp cpp/gomnivoicecpp.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target gomnivoicecpp && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgomnivoicecpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgomnivoicecpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgomnivoicecpp.so ./$(SO_TARGET)
 
 test: omnivoice-cpp
 	@echo "Running omnivoice-cpp tests..."

backend/go/omnivoice-cpp/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("OMNIVOICE_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgomnivoicecpp-fallback.dylib"
-		} else {
-			libName = "./libgomnivoicecpp-fallback.so"
-		}
+		libName = "./libgomnivoicecpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/omnivoice-cpp/package.sh

@@ -12,8 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/omnivoice-cpp $CURDIR/package/
-cp -fv $CURDIR/libgomnivoicecpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgomnivoicecpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgomnivoicecpp-*.so $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/omnivoice-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgomnivoicecpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgomnivoicecpp-fallback.so"
+LIBRARY="$CURDIR/libgomnivoicecpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgomnivoicecpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgomnivoicecpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export OMNIVOICE_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/parakeet-cpp/Makefile

@@ -1,6 +1,6 @@
 # parakeet-cpp backend Makefile.
 #
-# Upstream pin lives below as PARAKEET_VERSION?=89f5e2977b4d8bccd45e7bcc6f2ef7c4ed49e89a
+# Upstream pin lives below as PARAKEET_VERSION?=db755a78d39f789bb7d4e3935158a9e8105dbe36
 # (.github/bump_deps.sh) can find and update it - matches the
 # whisper.cpp / ds4 / vibevoice-cpp convention.
 #
@@ -15,7 +15,7 @@
 # That's what the L0 smoke test uses. The default target below does the
 # proper clone-at-pin + cmake build so CI doesn't need a side-checkout.
 
-PARAKEET_VERSION?=89f5e2977b4d8bccd45e7bcc6f2ef7c4ed49e89a
+PARAKEET_VERSION?=db755a78d39f789bb7d4e3935158a9e8105dbe36
 PARAKEET_REPO?=https://github.com/mudler/parakeet.cpp
 
 GOCMD?=go
@@ -74,7 +74,6 @@ libparakeet.so: sources/parakeet.cpp
 	cmake -B sources/parakeet.cpp/build-shared -S sources/parakeet.cpp $(CMAKE_ARGS)
 	cmake --build sources/parakeet.cpp/build-shared --config Release -j$(JOBS)
 	cp -fv sources/parakeet.cpp/build-shared/libparakeet.so* ./ 2>/dev/null || true
-	cp -fv sources/parakeet.cpp/build-shared/libparakeet.dylib ./ 2>/dev/null || true
 	cp -fv sources/parakeet.cpp/include/parakeet_capi.h ./
 
 parakeet-cpp-grpc: libparakeet.so main.go goparakeetcpp.go

backend/go/parakeet-cpp/main.go

@@ -2,17 +2,15 @@ package main
 
 // Started internally by LocalAI - one gRPC server per loaded model.
 //
-// Loads the parakeet shared library via purego and registers the flat
-// C-API entry points declared in parakeet_capi.h. The library name can be
-// overridden with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY /
-// VIBEVOICECPP_LIBRARY convention in the sibling backends); the default
-// looks next to this binary for libparakeet.so on Linux and
-// libparakeet.dylib on macOS.
+// Loads libparakeet.so via purego and registers the flat C-API entry
+// points declared in parakeet_capi.h. The library name can be overridden
+// with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY / VIBEVOICECPP_LIBRARY
+// convention in the sibling backends); the default looks for the .so next
+// to this binary.
 import (
 	"flag"
 	"fmt"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -30,11 +28,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("PARAKEET_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "libparakeet.dylib"
-		} else {
-			libName = "libparakeet.so"
-		}
+		libName = "libparakeet.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/parakeet-cpp/package.sh

@@ -16,15 +16,12 @@ mkdir -p "$CURDIR/package/lib"
 cp -avf "$CURDIR/parakeet-cpp-grpc" "$CURDIR/package/"
 cp -avf "$CURDIR/run.sh" "$CURDIR/package/"
 
-# libparakeet shared lib + any soname symlinks. On Linux this is
-# libparakeet.so[.X.Y]; on macOS it is libparakeet.dylib. purego.Dlopen
-# resolves it via the *_LIBRARY_PATH that run.sh points at lib/.
-cp -avf "$CURDIR"/libparakeet.so* "$CURDIR/package/lib/" 2>/dev/null || true
-cp -avf "$CURDIR"/libparakeet.dylib "$CURDIR/package/lib/" 2>/dev/null || true
-if ! ls "$CURDIR"/package/lib/libparakeet.* >/dev/null 2>&1; then
-	echo "ERROR: libparakeet shared library not found in $CURDIR, run 'make' first" >&2
+# libparakeet.so + any soname symlinks (libparakeet.so.X[.Y]). purego.Dlopen
+# resolves it via LD_LIBRARY_PATH, which run.sh points at lib/.
+cp -avf "$CURDIR"/libparakeet.so* "$CURDIR/package/lib/" 2>/dev/null || {
+	echo "ERROR: libparakeet.so not found in $CURDIR, run 'make' first" >&2
 	exit 1
-fi
+}
 
 # Detect architecture and copy the core runtime libs libparakeet.so links
 # against, plus the matching dynamic loader as lib/ld.so.
@@ -51,7 +48,7 @@ elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
     cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 "$CURDIR/package/lib/librt.so.1"
     cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 "$CURDIR/package/lib/libpthread.so.0"
 elif [ "$(uname -s)" = "Darwin" ]; then
-    echo "Detected Darwin — system frameworks linked dynamically, no bundled libs needed"
+    echo "Detected Darwin"
 else
     echo "Error: Could not detect architecture"
     exit 1

backend/go/parakeet-cpp/run.sh

@@ -3,17 +3,11 @@ set -e
 
 CURDIR=$(dirname "$(realpath "$0")")
 
-if [ "$(uname)" = "Darwin" ]; then
-	export DYLD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${DYLD_LIBRARY_PATH:-}"
-	export PARAKEET_LIBRARY="$CURDIR/lib/libparakeet.dylib"
-else
-	export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
-	export PARAKEET_LIBRARY="$CURDIR/lib/libparakeet.so"
-fi
+export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
 
 # If a self-contained ld.so was packaged, route through it so the
 # packaged libc / libstdc++ are used instead of the host's (matches the
-# whisper backend's runtime layout). Linux only.
+# whisper backend's runtime layout).
 if [ -f "$CURDIR/lib/ld.so" ]; then
 	echo "Using lib/ld.so"
 	exec "$CURDIR/lib/ld.so" "$CURDIR/parakeet-cpp-grpc" "$@"

backend/go/qwen3-tts-cpp/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # qwentts.cpp version
 QWEN3TTS_REPO?=https://github.com/ServeurpersoCom/qwentts.cpp
-QWEN3TTS_CPP_VERSION?=9dbe7ea26a01b30fccb117ae5e86807c1dc23d42
+QWEN3TTS_CPP_VERSION?=4536dcdce27c3764a93a06d6bf64026b124962f5
 SO_TARGET?=libgoqwen3ttscpp.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -65,8 +65,8 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgoqwen3ttscpp-avx.so libgoqwen3ttscpp-avx2.so libgoqwen3ttscpp-avx512.so libgoqwen3ttscpp-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
-	VARIANT_TARGETS = libgoqwen3ttscpp-fallback.dylib
+	# On non-Linux (e.g., Darwin), build only fallback variant
+	VARIANT_TARGETS = libgoqwen3ttscpp-fallback.so
 endif
 
 qwen3-tts-cpp: main.go goqwen3ttscpp.go $(VARIANT_TARGETS)
@@ -78,7 +78,7 @@ package: qwen3-tts-cpp
 build: package
 
 clean: purge
-	rm -rf libgoqwen3ttscpp*.so libgoqwen3ttscpp*.dylib package sources/qwentts.cpp qwen3-tts-cpp
+	rm -rf libgoqwen3ttscpp*.so package sources/qwentts.cpp qwen3-tts-cpp
 
 purge:
 	rm -rf build*
@@ -110,20 +110,13 @@ libgoqwen3ttscpp-fallback.so: sources/qwentts.cpp
 	SO_TARGET=libgoqwen3ttscpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoqwen3ttscpp-custom
 	rm -rf build-libgoqwen3ttscpp-fallback.so
 
-# Build fallback variant as a dylib (Darwin)
-libgoqwen3ttscpp-fallback.dylib: sources/qwentts.cpp
-	$(info ${GREEN}I qwen3-tts-cpp build info:fallback (dylib)${RESET})
-	SO_TARGET=libgoqwen3ttscpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoqwen3ttscpp-custom
-	rm -rf build-libgoqwen3ttscpp-fallback.dylib
-
 libgoqwen3ttscpp-custom: CMakeLists.txt cpp/goqwen3ttscpp.cpp cpp/goqwen3ttscpp.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target goqwen3ttscpp && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgoqwen3ttscpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgoqwen3ttscpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgoqwen3ttscpp.so ./$(SO_TARGET)
 
 test: qwen3-tts-cpp
 	@echo "Running qwen3-tts-cpp tests..."

backend/go/qwen3-tts-cpp/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("QWEN3TTS_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgoqwen3ttscpp-fallback.dylib"
-		} else {
-			libName = "./libgoqwen3ttscpp-fallback.so"
-		}
+		libName = "./libgoqwen3ttscpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/qwen3-tts-cpp/package.sh

@@ -12,8 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/qwen3-tts-cpp $CURDIR/package/
-cp -fv $CURDIR/libgoqwen3ttscpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgoqwen3ttscpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgoqwen3ttscpp-*.so $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/qwen3-tts-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgoqwen3ttscpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgoqwen3ttscpp-fallback.so"
+LIBRARY="$CURDIR/libgoqwen3ttscpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgoqwen3ttscpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgoqwen3ttscpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export QWEN3TTS_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/rfdetr-cpp/Makefile

@@ -71,7 +71,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = librfdetrcpp-avx.so librfdetrcpp-avx2.so librfdetrcpp-avx512.so librfdetrcpp-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = librfdetrcpp-fallback.dylib
+	VARIANT_TARGETS = librfdetrcpp-fallback.so
 endif
 
 rfdetr-cpp: main.go gorfdetrcpp.go $(VARIANT_TARGETS)
@@ -83,7 +83,7 @@ package: rfdetr-cpp
 build: package
 
 clean: purge
-	rm -rf librfdetrcpp*.so librfdetrcpp*.dylib rfdetr-cpp package sources
+	rm -rf librfdetrcpp*.so rfdetr-cpp package sources
 
 purge:
 	rm -rf build*
@@ -110,19 +110,11 @@ librfdetrcpp-avx512.so: sources/rt-detr.cpp
 endif
 
 # Build fallback variant (all platforms)
-ifeq ($(UNAME_S),Darwin)
-librfdetrcpp-fallback.dylib: sources/rt-detr.cpp
-	rm -rfv build-$@
-	$(info ${GREEN}I rfdetr-cpp build info:fallback${RESET})
-	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
-	rm -rfv build-$@
-else
 librfdetrcpp-fallback.so: sources/rt-detr.cpp
 	rm -rfv build-$@
 	$(info ${GREEN}I rfdetr-cpp build info:fallback${RESET})
 	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
 	rm -rfv build-$@
-endif
 
 librfdetrcpp-custom: CMakeLists.txt
 	mkdir -p build-$(SO_TARGET) && \
@@ -130,8 +122,7 @@ librfdetrcpp-custom: CMakeLists.txt
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/librfdetrcpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/librfdetrcpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/librfdetrcpp.so ./$(SO_TARGET)
 
 all: rfdetr-cpp package
 

backend/go/rfdetr-cpp/main.go

@@ -9,7 +9,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,11 +27,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("RFDETR_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./librfdetrcpp-fallback.dylib"
-		} else {
-			libName = "./librfdetrcpp-fallback.so"
-		}
+		libName = "./librfdetrcpp-fallback.so"
 	}
 
 	rfdetrLib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/rfdetr-cpp/package.sh

@@ -10,8 +10,7 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -fv $CURDIR/librfdetrcpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/librfdetrcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -avf $CURDIR/librfdetrcpp-*.so $CURDIR/package/
 cp -avf $CURDIR/rfdetr-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/rfdetr-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/librfdetrcpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/librfdetrcpp-fallback.so"
+LIBRARY="$CURDIR/librfdetrcpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/librfdetrcpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/librfdetrcpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export RFDETR_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/sam3-cpp/Makefile

@@ -66,7 +66,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgosam3-avx.so libgosam3-avx2.so libgosam3-avx512.so libgosam3-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = libgosam3-fallback.dylib
+	VARIANT_TARGETS = libgosam3-fallback.so
 endif
 
 sam3-cpp: main.go gosam3.go $(VARIANT_TARGETS)
@@ -78,7 +78,7 @@ package: sam3-cpp
 build: package
 
 clean: purge
-	rm -rf libgosam3*.so libgosam3*.dylib sam3-cpp package sources
+	rm -rf libgosam3*.so sam3-cpp package sources
 
 purge:
 	rm -rf build*
@@ -105,19 +105,11 @@ libgosam3-avx512.so: sources/sam3.cpp
 endif
 
 # Build fallback variant (all platforms)
-ifeq ($(UNAME_S),Darwin)
-libgosam3-fallback.dylib: sources/sam3.cpp
-	$(MAKE) purge
-	$(info ${GREEN}I sam3-cpp build info:fallback${RESET})
-	SO_TARGET=libgosam3-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgosam3-custom
-	rm -rfv build*
-else
 libgosam3-fallback.so: sources/sam3.cpp
 	$(MAKE) purge
 	$(info ${GREEN}I sam3-cpp build info:fallback${RESET})
 	SO_TARGET=libgosam3-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgosam3-custom
 	rm -rfv build*
-endif
 
 libgosam3-custom: CMakeLists.txt cpp/gosam3.cpp cpp/gosam3.h
 	mkdir -p build-$(SO_TARGET) && \
@@ -125,7 +117,6 @@ libgosam3-custom: CMakeLists.txt cpp/gosam3.cpp cpp/gosam3.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgosam3.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgosam3.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgosam3.so ./$(SO_TARGET)
 
 all: sam3-cpp package

backend/go/sam3-cpp/main.go

@@ -3,7 +3,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("SAM3_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgosam3-fallback.dylib"
-		} else {
-			libName = "./libgosam3-fallback.so"
-		}
+		libName = "./libgosam3-fallback.so"
 	}
 
 	gosamLib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/sam3-cpp/package.sh

@@ -10,8 +10,7 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -fv $CURDIR/libgosam3-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgosam3-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -avf $CURDIR/libgosam3-*.so $CURDIR/package/
 cp -avf $CURDIR/sam3-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/sam3-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgosam3-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgosam3-fallback.so"
+LIBRARY="$CURDIR/libgosam3-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgosam3-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgosam3-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export SAM3_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/sherpa-onnx/backend.go

@@ -7,7 +7,6 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
-	"runtime"
 	"strconv"
 	"strings"
 	"sync"
@@ -239,19 +238,11 @@ func loadSherpaLibs() error {
 func loadSherpaLibsOnce() error {
 	shimLib := os.Getenv("SHERPA_SHIM_LIBRARY")
 	if shimLib == "" {
-		if runtime.GOOS == "darwin" {
-			shimLib = "libsherpa-shim.dylib"
-		} else {
-			shimLib = "libsherpa-shim.so"
-		}
+		shimLib = "libsherpa-shim.so"
 	}
 	capiLib := os.Getenv("SHERPA_ONNX_LIBRARY")
 	if capiLib == "" {
-		if runtime.GOOS == "darwin" {
-			capiLib = "libsherpa-onnx-c-api.dylib"
-		} else {
-			capiLib = "libsherpa-onnx-c-api.so"
-		}
+		capiLib = "libsherpa-onnx-c-api.so"
 	}
 
 	shim, err := purego.Dlopen(shimLib, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/sherpa-onnx/run.sh

@@ -3,13 +3,7 @@ set -ex
 
 CURDIR=$(dirname "$(realpath $0)")
 
-if [ "$(uname)" = "Darwin" ]; then
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-	export SHERPA_SHIM_LIBRARY=$CURDIR/lib/libsherpa-shim.dylib
-	export SHERPA_ONNX_LIBRARY=$CURDIR/lib/libsherpa-onnx-c-api.dylib
-else
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
-fi
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 
 if [ -f $CURDIR/lib/ld.so ]; then
 	echo "Using lib/ld.so"

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=8caa3f908ae6d4a4bef531e73b9a969f266a3d1f
+STABLEDIFFUSION_GGML_VERSION?=b12098f5d09fc83da36e65c784f7bdb16a5a5ebf
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 
@@ -131,7 +131,6 @@ libgosd-custom: CMakeLists.txt cpp/gosd.cpp cpp/gosd.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgosd.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgosd.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgosd.so ./$(SO_TARGET)
 
 all: stablediffusion-ggml package

backend/go/stablediffusion-ggml/main.go

@@ -3,7 +3,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("SD_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgosd-fallback.dylib"
-		} else {
-			libName = "./libgosd-fallback.so"
-		}
+		libName = "./libgosd-fallback.so"
 	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/stablediffusion-ggml/package.sh

@@ -12,7 +12,6 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/libgosd-*.so $CURDIR/package/
-cp -fv $CURDIR/libgosd-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -avf $CURDIR/stablediffusion-ggml $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/stablediffusion-ggml/run.sh

@@ -12,18 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single library variant (Metal or Accelerate). The gosd target is
-	# built as a CMake MODULE, which emits a .dylib for a SHARED build but a
-	# .so for a MODULE build on Apple, so prefer .dylib and fall back to .so.
-	LIBRARY="$CURDIR/libgosd-fallback.dylib"
-	if [ ! -e "$LIBRARY" ]; then
-		LIBRARY="$CURDIR/libgosd-fallback.so"
-	fi
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgosd-fallback.so"
+LIBRARY="$CURDIR/libgosd-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgosd-avx.so ]; then
@@ -45,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgosd-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export SD_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/supertonic/helper.go

@@ -16,7 +16,6 @@ import (
 	"os"
 	"path/filepath"
 	"regexp"
-	"runtime"
 	"strings"
 	"time"
 	"unicode"
@@ -944,13 +943,7 @@ func InitializeONNXRuntime() error {
 			}
 		}
 		if libPath == "" {
-			// LocalAI: default to the platform-native shared library
-			// extension when nothing else is found (dyld vs ld.so).
-			if runtime.GOOS == "darwin" {
-				libPath = "/usr/local/lib/libonnxruntime.dylib"
-			} else {
-				libPath = "/usr/local/lib/libonnxruntime.so"
-			}
+			libPath = "/usr/local/lib/libonnxruntime.so"
 		}
 	}
 	ort.SetSharedLibraryPath(libPath)

backend/go/supertonic/package.sh

@@ -32,10 +32,6 @@ elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
     cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
     cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
     cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
-elif [ $(uname -s) = "Darwin" ]; then
-    # macOS: dyld resolves the bundled .dylib via DYLD_LIBRARY_PATH (set in
-    # run.sh); there is no ld.so loader nor glibc to bundle.
-    echo "Detected Darwin"
 else
     echo "Error: Could not detect architecture"
     exit 1

backend/go/supertonic/run.sh

@@ -3,19 +3,12 @@ set -ex
 
 CURDIR=$(dirname "$(realpath $0)")
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS uses dyld: there is no ld.so loader, and the search path env
-	# var is DYLD_LIBRARY_PATH. ONNX Runtime ships as a .dylib here.
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-	export ONNXRUNTIME_LIB_PATH=$CURDIR/lib/libonnxruntime.dylib
-else
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
-	export ONNXRUNTIME_LIB_PATH=$CURDIR/lib/libonnxruntime.so
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+export ONNXRUNTIME_LIB_PATH=$CURDIR/lib/libonnxruntime.so
 
-	if [ -f $CURDIR/lib/ld.so ]; then
-		echo "Using lib/ld.so"
-		exec $CURDIR/lib/ld.so $CURDIR/supertonic "$@"
-	fi
+if [ -f $CURDIR/lib/ld.so ]; then
+	echo "Using lib/ld.so"
+	exec $CURDIR/lib/ld.so $CURDIR/supertonic "$@"
 fi
 
 exec $CURDIR/supertonic "$@"

backend/go/vibevoice-cpp/Makefile

@@ -70,8 +70,8 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgovibevoicecpp-avx.so libgovibevoicecpp-avx2.so libgovibevoicecpp-avx512.so libgovibevoicecpp-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
-	VARIANT_TARGETS = libgovibevoicecpp-fallback.dylib
+	# On non-Linux (e.g., Darwin), build only fallback variant
+	VARIANT_TARGETS = libgovibevoicecpp-fallback.so
 endif
 
 vibevoice-cpp: main.go govibevoicecpp.go $(VARIANT_TARGETS)
@@ -83,7 +83,7 @@ package: vibevoice-cpp
 build: package
 
 clean: purge
-	rm -rf libgovibevoicecpp*.so libgovibevoicecpp*.dylib package sources/vibevoice.cpp vibevoice-cpp
+	rm -rf libgovibevoicecpp*.so package sources/vibevoice.cpp vibevoice-cpp
 
 purge:
 	rm -rf build*
@@ -119,21 +119,13 @@ libgovibevoicecpp-fallback.so: sources/vibevoice.cpp
 	SO_TARGET=libgovibevoicecpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgovibevoicecpp-custom
 	rm -rfv build*
 
-# Build fallback variant as a dylib (Darwin)
-libgovibevoicecpp-fallback.dylib: sources/vibevoice.cpp
-	$(MAKE) purge
-	$(info ${GREEN}I vibevoice-cpp build info:fallback (dylib)${RESET})
-	SO_TARGET=libgovibevoicecpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgovibevoicecpp-custom
-	rm -rfv build*
-
 libgovibevoicecpp-custom: CMakeLists.txt cpp/govibevoicecpp.cpp cpp/govibevoicecpp.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target govibevoicecpp && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgovibevoicecpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgovibevoicecpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgovibevoicecpp.so ./$(SO_TARGET)
 
 test: vibevoice-cpp
 	@echo "Running vibevoice-cpp tests..."

backend/go/vibevoice-cpp/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("VIBEVOICECPP_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgovibevoicecpp-fallback.dylib"
-		} else {
-			libName = "./libgovibevoicecpp-fallback.so"
-		}
+		libName = "./libgovibevoicecpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/vibevoice-cpp/package.sh

@@ -12,8 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/vibevoice-cpp $CURDIR/package/
-cp -fv $CURDIR/libgovibevoicecpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgovibevoicecpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgovibevoicecpp-*.so $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries