Initial plan

.github/workflows/backend.yml

@@ -14,7 +14,6 @@ concurrency:
 
 jobs:
   backend-jobs:
-    if: github.repository == 'mudler/LocalAI'
     uses: ./.github/workflows/backend_build.yml
     with:
       tag-latest: ${{ matrix.tag-latest }}
@@ -105,58 +104,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: ''
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-cpu-ace-step'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'true'
-            backend: "ace-step"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
-          - build-type: ''
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-cpu-mlx'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'true'
-            backend: "mlx"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
-          - build-type: ''
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-cpu-mlx-vlm'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'true'
-            backend: "mlx-vlm"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
-          - build-type: ''
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-cpu-mlx-audio'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'true'
-            backend: "mlx-audio"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           # CUDA 12 builds
           - build-type: 'cublas'
             cuda-major-version: "12"
@@ -184,19 +131,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "8"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12-nemo'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "nemo"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "8"
@@ -314,19 +248,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "8"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12-ace-step'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "ace-step"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "8"
@@ -379,19 +300,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "8"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12-outetts'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "outetts"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "8"
@@ -418,45 +326,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "8"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12-mlx'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "mlx"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "8"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12-mlx-vlm'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "mlx-vlm"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "8"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-nvidia-cuda-12-mlx-audio'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "mlx-audio"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "8"
@@ -549,19 +418,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             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-nemo'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "nemo"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -653,19 +509,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             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-ace-step'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "ace-step"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'l4t'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -731,45 +574,6 @@ jobs:
             backend: "diffusers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
-          - build-type: 'l4t'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx'
-            runs-on: 'ubuntu-24.04-arm'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            ubuntu-version: '2404'
-            backend: "mlx"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-          - build-type: 'l4t'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx-vlm'
-            runs-on: 'ubuntu-24.04-arm'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            ubuntu-version: '2404'
-            backend: "mlx-vlm"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-          - build-type: 'l4t'
-            cuda-major-version: "13"
-            cuda-minor-version: "0"
-            platforms: 'linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-nvidia-l4t-cuda-13-arm64-mlx-audio'
-            runs-on: 'ubuntu-24.04-arm'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            ubuntu-version: '2404'
-            backend: "mlx-audio"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -835,45 +639,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             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-mlx'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "mlx"
-            dockerfile: "./backend/Dockerfile.python"
-            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-mlx-vlm'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "mlx-vlm"
-            dockerfile: "./backend/Dockerfile.python"
-            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-mlx-audio'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "mlx-audio"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'cublas'
             cuda-major-version: "13"
             cuda-minor-version: "0"
@@ -1018,19 +783,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: 'hipblas'
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-rocm-hipblas-ace-step'
-            runs-on: 'arc-runner-set'
-            base-image: "rocm/dev-ubuntu-24.04:6.4.4"
-            skip-drivers: 'false'
-            backend: "ace-step"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           # ROCm additional backends
           - build-type: 'hipblas'
             cuda-major-version: ""
@@ -1071,19 +823,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: 'hipblas'
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-rocm-hipblas-nemo'
-            runs-on: 'arc-runner-set'
-            base-image: "rocm/dev-ubuntu-24.04:6.4.4"
-            skip-drivers: 'false'
-            backend: "nemo"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'hipblas'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -1241,19 +980,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: 'intel'
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-intel-ace-step'
-            runs-on: 'ubuntu-latest'
-            base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
-            skip-drivers: 'false'
-            backend: "ace-step"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'l4t'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -1319,45 +1045,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2204'
-          - build-type: 'l4t'
-            cuda-major-version: "12"
-            cuda-minor-version: "0"
-            platforms: 'linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-nvidia-l4t-mlx'
-            runs-on: 'ubuntu-24.04-arm'
-            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
-            skip-drivers: 'true'
-            backend: "mlx"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2204'
-          - build-type: 'l4t'
-            cuda-major-version: "12"
-            cuda-minor-version: "0"
-            platforms: 'linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-nvidia-l4t-mlx-vlm'
-            runs-on: 'ubuntu-24.04-arm'
-            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
-            skip-drivers: 'true'
-            backend: "mlx-vlm"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2204'
-          - build-type: 'l4t'
-            cuda-major-version: "12"
-            cuda-minor-version: "0"
-            platforms: 'linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-nvidia-l4t-mlx-audio'
-            runs-on: 'ubuntu-24.04-arm'
-            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
-            skip-drivers: 'true'
-            backend: "mlx-audio"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2204'
           # SYCL additional backends
           - build-type: 'intel'
             cuda-major-version: ""
@@ -1411,19 +1098,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: 'intel'
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-gpu-intel-nemo'
-            runs-on: 'arc-runner-set'
-            base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
-            skip-drivers: 'false'
-            backend: "nemo"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: 'intel'
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -1674,20 +1348,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.golang"
             context: "./"
             ubuntu-version: '2404'
-          # voxtral
-          - build-type: ''
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64,linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-cpu-voxtral'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "voxtral"
-            dockerfile: "./backend/Dockerfile.golang"
-            context: "./"
-            ubuntu-version: '2404'
           #silero-vad
           - build-type: ''
             cuda-major-version: ""
@@ -1863,19 +1523,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: ''
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64,linux/arm64'
-            tag-latest: 'auto'
-            tag-suffix: '-cpu-nemo'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'false'
-            backend: "nemo"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
           - build-type: ''
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -1915,19 +1562,6 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
-          - build-type: ''
-            cuda-major-version: ""
-            cuda-minor-version: ""
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-cpu-outetts'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:24.04"
-            skip-drivers: 'true'
-            backend: "outetts"
-            dockerfile: "./backend/Dockerfile.python"
-            context: "./"
-            ubuntu-version: '2404'
   backend-jobs-darwin:
     uses: ./.github/workflows/backend_build_darwin.yml
     strategy:
@@ -1936,9 +1570,6 @@ jobs:
           - backend: "diffusers"
             tag-suffix: "-metal-darwin-arm64-diffusers"
             build-type: "mps"
-          - backend: "ace-step"
-            tag-suffix: "-metal-darwin-arm64-ace-step"
-            build-type: "mps"
           - backend: "mlx"
             tag-suffix: "-metal-darwin-arm64-mlx"
             build-type: "mps"
@@ -1959,71 +1590,6 @@ jobs:
             tag-suffix: "-metal-darwin-arm64-whisper"
             build-type: "metal"
             lang: "go"
-          - backend: "voxtral"
-            tag-suffix: "-metal-darwin-arm64-voxtral"
-            build-type: "metal"
-            lang: "go"
-          - backend: "vibevoice"
-            tag-suffix: "-metal-darwin-arm64-vibevoice"
-            build-type: "mps"
-          - backend: "qwen-asr"
-            tag-suffix: "-metal-darwin-arm64-qwen-asr"
-            build-type: "mps"
-          - backend: "nemo"
-            tag-suffix: "-metal-darwin-arm64-nemo"
-            build-type: "mps"
-          - backend: "qwen-tts"
-            tag-suffix: "-metal-darwin-arm64-qwen-tts"
-            build-type: "mps"
-          - backend: "voxcpm"
-            tag-suffix: "-metal-darwin-arm64-voxcpm"
-            build-type: "mps"
-          - backend: "pocket-tts"
-            tag-suffix: "-metal-darwin-arm64-pocket-tts"
-            build-type: "mps"
-          - backend: "moonshine"
-            tag-suffix: "-metal-darwin-arm64-moonshine"
-            build-type: "mps"
-          - backend: "whisperx"
-            tag-suffix: "-metal-darwin-arm64-whisperx"
-            build-type: "mps"
-          - backend: "rerankers"
-            tag-suffix: "-metal-darwin-arm64-rerankers"
-            build-type: "mps"
-          - backend: "transformers"
-            tag-suffix: "-metal-darwin-arm64-transformers"
-            build-type: "mps"
-          - backend: "kokoro"
-            tag-suffix: "-metal-darwin-arm64-kokoro"
-            build-type: "mps"
-          - backend: "faster-whisper"
-            tag-suffix: "-metal-darwin-arm64-faster-whisper"
-            build-type: "mps"
-          - backend: "coqui"
-            tag-suffix: "-metal-darwin-arm64-coqui"
-            build-type: "mps"
-          - backend: "rfdetr"
-            tag-suffix: "-metal-darwin-arm64-rfdetr"
-            build-type: "mps"
-          - backend: "kitten-tts"
-            tag-suffix: "-metal-darwin-arm64-kitten-tts"
-            build-type: "mps"
-          - backend: "piper"
-            tag-suffix: "-metal-darwin-arm64-piper"
-            build-type: "metal"
-            lang: "go"
-          - backend: "silero-vad"
-            tag-suffix: "-metal-darwin-arm64-silero-vad"
-            build-type: "metal"
-            lang: "go"
-          - backend: "local-store"
-            tag-suffix: "-metal-darwin-arm64-local-store"
-            build-type: "metal"
-            lang: "go"
-          - backend: "huggingface"
-            tag-suffix: "-metal-darwin-arm64-huggingface"
-            build-type: "metal"
-            lang: "go"
     with:
       backend: ${{ matrix.backend }}
       build-type: ${{ matrix.build-type }}

.github/workflows/bump_deps.yaml

@@ -5,7 +5,6 @@ on:
   workflow_dispatch:
 jobs:
   bump-backends:
-    if: github.repository == 'mudler/LocalAI'
     strategy:
       fail-fast: false
       matrix:
@@ -30,10 +29,6 @@ jobs:
             variable: "PIPER_VERSION"
             branch: "master"
             file: "backend/go/piper/Makefile"
-          - repository: "antirez/voxtral.c"
-            variable: "VOXTRAL_VERSION"
-            branch: "main"
-            file: "backend/go/voxtral/Makefile"
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v6

.github/workflows/bump_docs.yaml

@@ -5,7 +5,6 @@ on:
   workflow_dispatch:
 jobs:
   bump-docs:
-    if: github.repository == 'mudler/LocalAI'
     strategy:
       fail-fast: false
       matrix:

.github/workflows/checksum_checker.yaml

@@ -5,7 +5,6 @@ on:
   workflow_dispatch:
 jobs:
   checksum_check:
-    if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
       - name: Force Install GIT latest

.github/workflows/dependabot_auto.yml

@@ -9,8 +9,8 @@ permissions:
 
 jobs:
   dependabot:
-    if: github.repository == 'mudler/LocalAI' && github.actor == 'dependabot[bot]'
     runs-on: ubuntu-latest
+    if: ${{ github.actor == 'dependabot[bot]' }}
     steps:
       - name: Dependabot metadata
         id: metadata

.github/workflows/deploy-explorer.yaml

@@ -12,7 +12,6 @@ concurrency:
 
 jobs:
   build-linux:
-    if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
       - name: Clone
@@ -34,7 +33,7 @@ jobs:
         run: |
           CGO_ENABLED=0 make build
       - name: rm
-        uses: appleboy/ssh-action@v1.2.5
+        uses: appleboy/ssh-action@v1.2.4
         with:
             host: ${{ secrets.EXPLORER_SSH_HOST }}
             username: ${{ secrets.EXPLORER_SSH_USERNAME }}
@@ -54,7 +53,7 @@ jobs:
             rm: true
             target: ./local-ai
       - name: restarting
-        uses: appleboy/ssh-action@v1.2.5
+        uses: appleboy/ssh-action@v1.2.4
         with:
             host: ${{ secrets.EXPLORER_SSH_HOST }}
             username: ${{ secrets.EXPLORER_SSH_USERNAME }}

.github/workflows/gallery-agent.yaml

@@ -27,7 +27,6 @@ on:
         type: string
 jobs:
   gallery-agent:
-    if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository

.github/workflows/generate_grpc_cache.yaml

@@ -13,7 +13,6 @@ concurrency:
 
 jobs:
   generate_caches:
-    if: github.repository == 'mudler/LocalAI'
     strategy:
       matrix:
         include:

.github/workflows/generate_intel_image.yaml

@@ -12,7 +12,6 @@ concurrency:
 
 jobs:
   generate_caches:
-    if: github.repository == 'mudler/LocalAI'
     strategy:
       matrix:
         include:

.github/workflows/image.yml

@@ -14,7 +14,6 @@
   
   jobs:
     hipblas-jobs:
-      if: github.repository == 'mudler/LocalAI'
       uses: ./.github/workflows/image_build.yml
       with:
         tag-latest: ${{ matrix.tag-latest }}
@@ -51,7 +50,6 @@
               ubuntu-codename: 'noble'
   
     core-image-build:
-      if: github.repository == 'mudler/LocalAI'
       uses: ./.github/workflows/image_build.yml
       with:
         tag-latest: ${{ matrix.tag-latest }}
@@ -138,7 +136,6 @@
               ubuntu-codename: 'noble'
   
     gh-runner:
-      if: github.repository == 'mudler/LocalAI'
       uses: ./.github/workflows/image_build.yml
       with:
         tag-latest: ${{ matrix.tag-latest }}

.github/workflows/localaibot_automerge.yml

@@ -10,8 +10,8 @@ permissions:
   actions: write # to dispatch publish workflow
 jobs:
   dependabot:
-    if: github.repository == 'mudler/LocalAI' && github.actor == 'localai-bot' && !contains(github.event.pull_request.title, 'chore(model gallery):')
     runs-on: ubuntu-latest
+    if: ${{ github.actor == 'localai-bot' && !contains(github.event.pull_request.title, 'chore(model gallery):') }}
     steps:
       - name: Checkout repository
         uses: actions/checkout@v6

.github/workflows/notify-models.yaml

@@ -10,7 +10,7 @@ permissions:
 
 jobs:
   notify-discord:
-    if: github.repository == 'mudler/LocalAI' && (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model'))
+    if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model')) }}
     env:
         MODEL_NAME: gemma-3-12b-it-qat
     runs-on: ubuntu-latest
@@ -90,7 +90,7 @@ jobs:
         connect-timeout-seconds: 180
         limit-access-to-actor: true
   notify-twitter:
-    if: github.repository == 'mudler/LocalAI' && (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model'))
+    if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model')) }}
     env:
         MODEL_NAME: gemma-3-12b-it-qat
     runs-on: ubuntu-latest

.github/workflows/notify-releases.yaml

@@ -6,7 +6,6 @@ on:
 
 jobs:
   notify-discord:
-    if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     env:
         RELEASE_BODY: ${{ github.event.release.body }}

.github/workflows/stalebot.yml

@@ -8,7 +8,6 @@ on:
 
 jobs:
   stale:
-    if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/stale@997185467fa4f803885201cee163a9f38240193d # v9

.github/workflows/test-extra.yml

@@ -323,25 +323,6 @@ jobs:
         run: |
           make --jobs=5 --output-sync=target -C backend/python/qwen-asr
           make --jobs=5 --output-sync=target -C backend/python/qwen-asr test
-  tests-nemo:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clone
-        uses: actions/checkout@v6
-        with:
-          submodules: true
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y build-essential ffmpeg sox
-          sudo apt-get install -y ca-certificates cmake curl patch python3-pip
-          # Install UV
-          curl -LsSf https://astral.sh/uv/install.sh | sh
-          pip install --user --no-cache-dir grpcio-tools==1.64.1
-      - name: Test nemo
-        run: |
-          make --jobs=5 --output-sync=target -C backend/python/nemo
-          make --jobs=5 --output-sync=target -C backend/python/nemo test
   tests-voxcpm:
     runs-on: ubuntu-latest
     steps:
@@ -361,34 +342,3 @@ jobs:
         run: |
           make --jobs=5 --output-sync=target -C backend/python/voxcpm
           make --jobs=5 --output-sync=target -C backend/python/voxcpm test
-  tests-voxtral:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clone
-        uses: actions/checkout@v6
-        with:
-          submodules: true
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y build-essential cmake curl libopenblas-dev ffmpeg
-      - name: Setup Go
-        uses: actions/setup-go@v5
-      # You can test your matrix by printing the current Go version
-      - name: Display Go version
-        run: go version
-      - name: Proto Dependencies
-        run: |
-          # Install protoc
-          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: Build voxtral
-        run: |
-          make --jobs=5 --output-sync=target -C backend/go/voxtral
-      - name: Test voxtral
-        run: |
-          make --jobs=5 --output-sync=target -C backend/go/voxtral test

.github/workflows/update_swagger.yaml

@@ -5,7 +5,6 @@ on:
   workflow_dispatch:
 jobs:
   swagger:
-    if: github.repository == 'mudler/LocalAI'
     strategy:
       fail-fast: false
     runs-on: ubuntu-latest

Makefile

@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/voxtral
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/qwen-asr backends/voxcpm backends/whisperx
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -308,7 +308,6 @@ protogen-go-clean:
 
 prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/transformers
-	$(MAKE) -C backend/python/outetts
 	$(MAKE) -C backend/python/diffusers
 	$(MAKE) -C backend/python/chatterbox
 	$(MAKE) -C backend/python/vllm
@@ -318,14 +317,11 @@ prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/pocket-tts
 	$(MAKE) -C backend/python/qwen-tts
 	$(MAKE) -C backend/python/qwen-asr
-	$(MAKE) -C backend/python/nemo
 	$(MAKE) -C backend/python/voxcpm
 	$(MAKE) -C backend/python/whisperx
-	$(MAKE) -C backend/python/ace-step
 
 test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/transformers test
-	$(MAKE) -C backend/python/outetts test
 	$(MAKE) -C backend/python/diffusers test
 	$(MAKE) -C backend/python/chatterbox test
 	$(MAKE) -C backend/python/vllm test
@@ -335,10 +331,8 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/pocket-tts test
 	$(MAKE) -C backend/python/qwen-tts test
 	$(MAKE) -C backend/python/qwen-asr test
-	$(MAKE) -C backend/python/nemo test
 	$(MAKE) -C backend/python/voxcpm test
 	$(MAKE) -C backend/python/whisperx test
-	$(MAKE) -C backend/python/ace-step test
 
 DOCKER_IMAGE?=local-ai
 DOCKER_AIO_IMAGE?=local-ai-aio
@@ -453,12 +447,10 @@ BACKEND_HUGGINGFACE = huggingface|golang|.|false|true
 BACKEND_SILERO_VAD = silero-vad|golang|.|false|true
 BACKEND_STABLEDIFFUSION_GGML = stablediffusion-ggml|golang|.|--progress=plain|true
 BACKEND_WHISPER = whisper|golang|.|false|true
-BACKEND_VOXTRAL = voxtral|golang|.|false|true
 
 # Python backends with root context
 BACKEND_RERANKERS = rerankers|python|.|false|true
 BACKEND_TRANSFORMERS = transformers|python|.|false|true
-BACKEND_OUTETTS = outetts|python|.|false|true
 BACKEND_FASTER_WHISPER = faster-whisper|python|.|false|true
 BACKEND_COQUI = coqui|python|.|false|true
 BACKEND_RFDETR = rfdetr|python|.|false|true
@@ -474,10 +466,8 @@ BACKEND_MOONSHINE = moonshine|python|.|false|true
 BACKEND_POCKET_TTS = pocket-tts|python|.|false|true
 BACKEND_QWEN_TTS = qwen-tts|python|.|false|true
 BACKEND_QWEN_ASR = qwen-asr|python|.|false|true
-BACKEND_NEMO = nemo|python|.|false|true
 BACKEND_VOXCPM = voxcpm|python|.|false|true
 BACKEND_WHISPERX = whisperx|python|.|false|true
-BACKEND_ACE_STEP = ace-step|python|.|false|true
 
 # Helper function to build docker image for a backend
 # Usage: $(call docker-build-backend,BACKEND_NAME,DOCKERFILE_TYPE,BUILD_CONTEXT,PROGRESS_FLAG,NEEDS_BACKEND_ARG)
@@ -507,10 +497,8 @@ $(eval $(call generate-docker-build-target,$(BACKEND_HUGGINGFACE)))
 $(eval $(call generate-docker-build-target,$(BACKEND_SILERO_VAD)))
 $(eval $(call generate-docker-build-target,$(BACKEND_STABLEDIFFUSION_GGML)))
 $(eval $(call generate-docker-build-target,$(BACKEND_WHISPER)))
-$(eval $(call generate-docker-build-target,$(BACKEND_VOXTRAL)))
 $(eval $(call generate-docker-build-target,$(BACKEND_RERANKERS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_TRANSFORMERS)))
-$(eval $(call generate-docker-build-target,$(BACKEND_OUTETTS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_FASTER_WHISPER)))
 $(eval $(call generate-docker-build-target,$(BACKEND_COQUI)))
 $(eval $(call generate-docker-build-target,$(BACKEND_RFDETR)))
@@ -526,16 +514,14 @@ $(eval $(call generate-docker-build-target,$(BACKEND_MOONSHINE)))
 $(eval $(call generate-docker-build-target,$(BACKEND_POCKET_TTS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_QWEN_TTS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_QWEN_ASR)))
-$(eval $(call generate-docker-build-target,$(BACKEND_NEMO)))
 $(eval $(call generate-docker-build-target,$(BACKEND_VOXCPM)))
 $(eval $(call generate-docker-build-target,$(BACKEND_WHISPERX)))
-$(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
 
 # Pattern rule for docker-save targets
 docker-save-%: backend-images
 	docker save local-ai-backend:$* -o backend-images/$*.tar
 
-docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-voxtral
+docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-qwen-asr docker-build-voxcpm docker-build-whisperx
 
 ########################################################
 ### Mock Backend for E2E Tests

README.md

@@ -203,8 +203,7 @@ local-ai run oci://localai/phi-2:latest
 For more information, see [💻 Getting started](https://localai.io/basics/getting_started/index.html), if you are interested in our roadmap items and future enhancements, you can see the [Issues labeled as Roadmap here](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)
 
 ## 📰 Latest project news
-- February 2026: [Realtime API for audio-to-audio with tool calling](https://github.com/mudler/LocalAI/pull/6245), [ACE-Step 1.5 support](https://github.com/mudler/LocalAI/pull/8396)
+
-- January 2026: **LocalAI 3.10.0** - Major release with Anthropic API support, Open Responses API for stateful agents, video & image generation suite (LTX-2), unified GPU backends, tool streaming & XML parsing, system-aware backend gallery, crash fixes for AVX-only CPUs and AMD VRAM reporting, request tracing, and new backends: **Moonshine** (ultra-fast transcription), **Pocket-TTS** (lightweight TTS). Vulkan arm64 builds now available. [Release notes](https://github.com/mudler/LocalAI/releases/tag/v3.10.0).
 - December 2025: [Dynamic Memory Resource reclaimer](https://github.com/mudler/LocalAI/pull/7583), [Automatic fitting of models to multiple GPUS(llama.cpp)](https://github.com/mudler/LocalAI/pull/7584), [Added Vibevoice backend](https://github.com/mudler/LocalAI/pull/7494)
 - November 2025: Major improvements to the UX. Among these: [Import models via URL](https://github.com/mudler/LocalAI/pull/7245) and [Multiple chats and history](https://github.com/mudler/LocalAI/pull/7325)
 - October 2025: 🔌 [Model Context Protocol (MCP)](https://localai.io/docs/features/mcp/) support added for agentic capabilities with external tools
@@ -270,7 +269,6 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
 |---------|-------------|---------------------|
 | **whisper.cpp** | OpenAI Whisper in C/C++ | CUDA 12/13, ROCm, Intel SYCL, Vulkan, CPU |
 | **faster-whisper** | Fast Whisper with CTranslate2 | CUDA 12/13, ROCm, Intel, CPU |
-| **moonshine** | Ultra-fast transcription engine for low-end devices | CUDA 12/13, Metal, CPU |
 | **coqui** | Advanced TTS with 1100+ languages | CUDA 12/13, ROCm, Intel, CPU |
 | **kokoro** | Lightweight TTS model | CUDA 12/13, ROCm, Intel, CPU |
 | **chatterbox** | Production-grade TTS | CUDA 12/13, CPU |
@@ -281,7 +279,6 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
 | **vibevoice** | Real-time TTS with voice cloning | CUDA 12/13, ROCm, Intel, CPU |
 | **pocket-tts** | Lightweight CPU-based TTS | CUDA 12/13, ROCm, Intel, CPU |
 | **qwen-tts** | High-quality TTS with custom voice, voice design, and voice cloning | CUDA 12/13, ROCm, Intel, CPU |
-| **ace-step** | Music generation from text descriptions, lyrics, or audio samples | CUDA 12/13, ROCm, Intel, Metal, CPU |
 
 ### Image & Video Generation
 | Backend | Description | Acceleration Support |
@@ -303,11 +300,11 @@ LocalAI supports a comprehensive range of AI backends with multiple acceleration
 |-------------------|-------------------|------------------|
 | **NVIDIA CUDA 12** | All CUDA-compatible backends | Nvidia hardware |
 | **NVIDIA CUDA 13** | All CUDA-compatible backends | Nvidia hardware |
-| **AMD ROCm** | llama.cpp, whisper, vllm, transformers, diffusers, rerankers, coqui, kokoro, neutts, vibevoice, pocket-tts, qwen-tts, ace-step | AMD Graphics |
+| **AMD ROCm** | llama.cpp, whisper, vllm, transformers, diffusers, rerankers, coqui, kokoro, neutts, vibevoice, pocket-tts, qwen-tts | AMD Graphics |
-| **Intel oneAPI** | llama.cpp, whisper, stablediffusion, vllm, transformers, diffusers, rfdetr, rerankers, coqui, kokoro, vibevoice, pocket-tts, qwen-tts, ace-step | Intel Arc, Intel iGPUs |
+| **Intel oneAPI** | llama.cpp, whisper, stablediffusion, vllm, transformers, diffusers, rfdetr, rerankers, coqui, kokoro, vibevoice, pocket-tts, qwen-tts | Intel Arc, Intel iGPUs |
-| **Apple Metal** | llama.cpp, whisper, diffusers, MLX, MLX-VLM, moonshine, ace-step | Apple M1/M2/M3+ |
+| **Apple Metal** | llama.cpp, whisper, diffusers, MLX, MLX-VLM | Apple M1/M2/M3+ |
 | **Vulkan** | llama.cpp, whisper, stablediffusion | Cross-platform GPUs |
-| **NVIDIA Jetson (CUDA 12)** | llama.cpp, whisper, stablediffusion, diffusers, rfdetr, ace-step | ARM64 embedded AI (AGX Orin, etc.) |
+| **NVIDIA Jetson (CUDA 12)** | llama.cpp, whisper, stablediffusion, diffusers, rfdetr | ARM64 embedded AI (AGX Orin, etc.) |
 | **NVIDIA Jetson (CUDA 13)** | llama.cpp, whisper, stablediffusion, diffusers, rfdetr | ARM64 embedded AI (DGX Spark) |
 | **CPU Optimized** | All backends | AVX/AVX2/AVX512, quantization support |
 

backend/Dockerfile.golang

@@ -20,7 +20,7 @@ RUN apt-get update && \
         build-essential \
         git ccache \
         ca-certificates \
-        make cmake wget libopenblas-dev \
+        make cmake wget \
         curl unzip \
         libssl-dev && \
     apt-get clean && \

backend/backend.proto

@@ -365,14 +365,6 @@ message SoundGenerationRequest {
   optional bool sample = 6;
   optional string src = 7;
   optional int32 src_divisor = 8;
-  optional bool think = 9;
-  optional string caption = 10;
-  optional string lyrics = 11;
-  optional int32 bpm = 12;
-  optional string keyscale = 13;
-  optional string language = 14;
-  optional string timesignature = 15;
-  optional bool instrumental = 17;
 }
 
 message TokenizationResponse {

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=8872ad2125336d209a9911a82101f80095a9831d
+LLAMA_VERSION?=2634ed207a17db1a54bd8df0555bd8499a6ab691
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/go/huggingface/Makefile

@@ -7,6 +7,3 @@ package:
 	bash package.sh
 
 build: huggingface package
-
-clean:
-	rm -f huggingface

backend/go/huggingface/package.sh

@@ -8,5 +8,5 @@ set -e
 CURDIR=$(dirname "$(realpath $0)")
 
 mkdir -p $CURDIR/package
-cp -avf $CURDIR/huggingface $CURDIR/package/
+cp -avrf $CURDIR/huggingface $CURDIR/package/
 cp -rfv $CURDIR/run.sh $CURDIR/package/

backend/go/local-store/Makefile

@@ -7,6 +7,3 @@ package:
 	bash package.sh
 
 build: local-store package
-
-clean:
-	rm -f local-store

backend/go/local-store/package.sh

@@ -8,5 +8,5 @@ set -e
 CURDIR=$(dirname "$(realpath $0)")
 
 mkdir -p $CURDIR/package
-cp -avf $CURDIR/local-store $CURDIR/package/
+cp -avrf $CURDIR/local-store $CURDIR/package/
 cp -rfv $CURDIR/run.sh $CURDIR/package/

backend/go/piper/Makefile

@@ -35,6 +35,3 @@ package:
 	bash package.sh
 
 build: piper package
-
-clean:
-	rm -f piper

backend/go/piper/package.sh

@@ -10,8 +10,8 @@ CURDIR=$(dirname "$(realpath $0)")
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -avf $CURDIR/piper $CURDIR/package/
+cp -avrf $CURDIR/piper $CURDIR/package/
-cp -avf $CURDIR/espeak-ng-data $CURDIR/package/
+cp -avrf $CURDIR/espeak-ng-data $CURDIR/package/
 cp -rfv $CURDIR/run.sh $CURDIR/package/
 cp -rfLv $CURDIR/sources/go-piper/piper-phonemize/pi/lib/* $CURDIR/package/lib/
 

backend/go/silero-vad/Makefile

@@ -45,6 +45,3 @@ package:
 	bash package.sh
 
 build: silero-vad package
-
-clean:
-	rm -f silero-vad

backend/go/silero-vad/package.sh

@@ -10,8 +10,8 @@ CURDIR=$(dirname "$(realpath $0)")
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -avf $CURDIR/silero-vad $CURDIR/package/
+cp -avrf $CURDIR/silero-vad $CURDIR/package/
-cp -avf $CURDIR/run.sh $CURDIR/package/
+cp -avrf $CURDIR/run.sh $CURDIR/package/
 cp -rfLv $CURDIR/backend-assets/lib/* $CURDIR/package/lib/
 
 # Detect architecture and copy appropriate libraries

backend/go/voxtral/.gitignore

@@ -1,9 +0,0 @@
-.cache/
-sources/
-build/
-build-*/
-package/
-voxtral
-*.so
-*.dylib
-compile_commands.json

backend/go/voxtral/CMakeLists.txt

@@ -1,84 +0,0 @@
-cmake_minimum_required(VERSION 3.12)
-
-if(USE_METAL)
-    project(govoxtral LANGUAGES C OBJC)
-else()
-    project(govoxtral LANGUAGES C)
-endif()
-
-set(CMAKE_POSITION_INDEPENDENT_CODE ON)
-set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
-
-# Workaround: CMake + GCC linker depfile generation fails for MODULE libraries
-set(CMAKE_C_LINKER_DEPFILE_SUPPORTED FALSE)
-
-# Build voxtral.c as a library
-set(VOXTRAL_SOURCES
-    sources/voxtral.c/voxtral.c
-    sources/voxtral.c/voxtral_kernels.c
-    sources/voxtral.c/voxtral_audio.c
-    sources/voxtral.c/voxtral_encoder.c
-    sources/voxtral.c/voxtral_decoder.c
-    sources/voxtral.c/voxtral_tokenizer.c
-    sources/voxtral.c/voxtral_safetensors.c
-)
-
-# Metal GPU acceleration (macOS arm64 only)
-if(USE_METAL)
-    # Generate embedded shader header from .metal source via xxd
-    add_custom_command(
-        OUTPUT ${CMAKE_CURRENT_SOURCE_DIR}/sources/voxtral.c/voxtral_shaders_source.h
-        COMMAND xxd -i voxtral_shaders.metal > voxtral_shaders_source.h
-        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/sources/voxtral.c
-        DEPENDS sources/voxtral.c/voxtral_shaders.metal
-        COMMENT "Generating embedded Metal shaders header"
-    )
-    list(APPEND VOXTRAL_SOURCES sources/voxtral.c/voxtral_metal.m)
-    set_source_files_properties(sources/voxtral.c/voxtral_metal.m PROPERTIES
-        COMPILE_FLAGS "-fobjc-arc"
-    )
-endif()
-
-add_library(govoxtral MODULE csrc/govoxtral.c ${VOXTRAL_SOURCES})
-
-target_include_directories(govoxtral PRIVATE sources/voxtral.c csrc)
-
-target_compile_options(govoxtral PRIVATE -O3 -ffast-math)
-
-if(USE_METAL)
-    target_compile_definitions(govoxtral PRIVATE USE_BLAS USE_METAL ACCELERATE_NEW_LAPACK)
-    target_link_libraries(govoxtral PRIVATE
-        "-framework Accelerate"
-        "-framework Metal"
-        "-framework MetalPerformanceShaders"
-        "-framework MetalPerformanceShadersGraph"
-        "-framework Foundation"
-        "-framework AudioToolbox"
-        "-framework CoreFoundation"
-        m
-    )
-    # Ensure the generated shader header is built before compiling
-    target_sources(govoxtral PRIVATE
-        ${CMAKE_CURRENT_SOURCE_DIR}/sources/voxtral.c/voxtral_shaders_source.h
-    )
-elseif(USE_OPENBLAS)
-    # Try to find OpenBLAS; use it if available, otherwise fall back to pure C
-    find_package(BLAS)
-    if(BLAS_FOUND)
-        target_compile_definitions(govoxtral PRIVATE USE_BLAS USE_OPENBLAS)
-        target_link_libraries(govoxtral PRIVATE ${BLAS_LIBRARIES} m)
-        target_include_directories(govoxtral PRIVATE /usr/include/openblas)
-    else()
-        message(WARNING "OpenBLAS requested but not found, building without BLAS")
-        target_link_libraries(govoxtral PRIVATE m)
-    endif()
-elseif(APPLE)
-    # macOS without Metal: use Accelerate framework
-    target_compile_definitions(govoxtral PRIVATE USE_BLAS ACCELERATE_NEW_LAPACK)
-    target_link_libraries(govoxtral PRIVATE "-framework Accelerate" m)
-else()
-    target_link_libraries(govoxtral PRIVATE m)
-endif()
-
-set_property(TARGET govoxtral PROPERTY C_STANDARD 11)
-set_target_properties(govoxtral PROPERTIES LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})

backend/go/voxtral/Makefile

@@ -1,124 +0,0 @@
-.NOTPARALLEL:
-
-CMAKE_ARGS?=
-BUILD_TYPE?=
-NATIVE?=true
-
-GOCMD?=go
-GO_TAGS?=
-JOBS?=$(shell nproc --ignore=1 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)
-
-# voxtral.c version
-VOXTRAL_REPO?=https://github.com/antirez/voxtral.c
-VOXTRAL_VERSION?=8f810dd23c44be5453cb46c92216a3eaab46e85f
-
-# Detect OS
-UNAME_S := $(shell uname -s)
-
-# Shared library extension
-ifeq ($(UNAME_S),Darwin)
-	SO_EXT=dylib
-else
-	SO_EXT=so
-endif
-
-SO_TARGET?=libgovoxtral.$(SO_EXT)
-
-CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
-
-ifeq ($(NATIVE),false)
-ifneq ($(UNAME_S),Darwin)
-	CMAKE_ARGS+=-DCMAKE_C_FLAGS="-march=x86-64"
-endif
-endif
-
-ifeq ($(BUILD_TYPE),cublas)
-	CMAKE_ARGS+=-DUSE_OPENBLAS=OFF
-else ifeq ($(BUILD_TYPE),hipblas)
-	CMAKE_ARGS+=-DUSE_OPENBLAS=OFF
-else ifeq ($(BUILD_TYPE),metal)
-	CMAKE_ARGS+=-DUSE_OPENBLAS=OFF -DUSE_METAL=ON
-else ifeq ($(UNAME_S),Darwin)
-	# Default on macOS: use Accelerate (no OpenBLAS needed)
-	CMAKE_ARGS+=-DUSE_OPENBLAS=OFF
-else
-	CMAKE_ARGS+=-DUSE_OPENBLAS=ON
-endif
-
-# Only build CPU variants on Linux; on Darwin build a single dylib
-ifeq ($(UNAME_S),Linux)
-VARIANT_TARGETS = libgovoxtral-avx.so libgovoxtral-avx2.so libgovoxtral-fallback.so
-else ifeq ($(UNAME_S),Darwin)
-VARIANT_TARGETS = libgovoxtral-fallback.dylib
-else
-VARIANT_TARGETS = libgovoxtral-fallback.so
-endif
-
-sources/voxtral.c:
-	mkdir -p sources/voxtral.c
-	cd sources/voxtral.c && \
-	git init && \
-	git remote add origin $(VOXTRAL_REPO) && \
-	git fetch origin && \
-	git checkout $(VOXTRAL_VERSION) && \
-	git submodule update --init --recursive --depth 1 --single-branch
-
-voxtral: main.go govoxtral.go $(VARIANT_TARGETS)
-	CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o voxtral ./
-
-package: voxtral
-	bash package.sh
-
-build: package
-
-clean: purge
-	rm -rf libgovoxtral*.so libgovoxtral*.dylib package sources/voxtral.c voxtral
-
-purge:
-	rm -rf build*
-
-# Build all variants (Linux only)
-ifeq ($(UNAME_S),Linux)
-libgovoxtral-avx.so: sources/voxtral.c
-	$(MAKE) purge
-	$(info Building voxtral: avx)
-	SO_TARGET=libgovoxtral-avx.so CMAKE_ARGS="$(CMAKE_ARGS) -DCMAKE_C_FLAGS='-mavx -mno-avx2 -mno-avx512f -mno-fma -mno-f16c'" $(MAKE) libgovoxtral-custom
-	rm -rfv build*
-
-libgovoxtral-avx2.so: sources/voxtral.c
-	$(MAKE) purge
-	$(info Building voxtral: avx2)
-	SO_TARGET=libgovoxtral-avx2.so CMAKE_ARGS="$(CMAKE_ARGS) -DCMAKE_C_FLAGS='-mavx -mavx2 -mfma -mf16c'" $(MAKE) libgovoxtral-custom
-	rm -rfv build*
-endif
-
-# Build fallback variant
-ifeq ($(UNAME_S),Darwin)
-libgovoxtral-fallback.dylib: sources/voxtral.c
-	$(MAKE) purge
-	$(info Building voxtral: darwin fallback)
-	SO_TARGET=libgovoxtral-fallback.dylib NATIVE=true $(MAKE) libgovoxtral-custom
-	rm -rfv build*
-else
-libgovoxtral-fallback.so: sources/voxtral.c
-	$(MAKE) purge
-	$(info Building voxtral: fallback)
-	SO_TARGET=libgovoxtral-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DCMAKE_C_FLAGS='-mno-avx -mno-avx2 -mno-avx512f -mno-fma -mno-f16c'" $(MAKE) libgovoxtral-custom
-	rm -rfv build*
-endif
-
-libgovoxtral-custom: CMakeLists.txt csrc/govoxtral.c csrc/govoxtral.h
-	mkdir -p build-$(SO_TARGET) && \
-	cd build-$(SO_TARGET) && \
-	cmake .. $(CMAKE_ARGS) && \
-	cmake --build . --config Release -j$(JOBS) && \
-	cd .. && \
-	(mv build-$(SO_TARGET)/libgovoxtral.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgovoxtral.dylib ./$(SO_TARGET) 2>/dev/null)
-
-test: voxtral
-	@echo "Running voxtral tests..."
-	bash test.sh
-	@echo "voxtral tests completed."
-
-all: voxtral package

backend/go/voxtral/csrc/govoxtral.c

@@ -1,62 +0,0 @@
-#include "govoxtral.h"
-#include "voxtral.h"
-#include "voxtral_audio.h"
-#ifdef USE_METAL
-#include "voxtral_metal.h"
-#endif
-#include <stdlib.h>
-#include <string.h>
-#include <stdio.h>
-
-static vox_ctx_t *ctx = NULL;
-static char *last_result = NULL;
-static int metal_initialized = 0;
-
-int load_model(const char *model_dir) {
-    if (ctx != NULL) {
-        vox_free(ctx);
-        ctx = NULL;
-    }
-
-#ifdef USE_METAL
-    if (!metal_initialized) {
-        vox_metal_init();
-        metal_initialized = 1;
-    }
-#endif
-
-    ctx = vox_load(model_dir);
-    if (ctx == NULL) {
-        fprintf(stderr, "error: failed to load voxtral model from %s\n", model_dir);
-        return 1;
-    }
-
-    return 0;
-}
-
-const char *transcribe(const char *wav_path) {
-    if (ctx == NULL) {
-        fprintf(stderr, "error: model not loaded\n");
-        return "";
-    }
-
-    if (last_result != NULL) {
-        free(last_result);
-        last_result = NULL;
-    }
-
-    last_result = vox_transcribe(ctx, wav_path);
-    if (last_result == NULL) {
-        fprintf(stderr, "error: transcription failed for %s\n", wav_path);
-        return "";
-    }
-
-    return last_result;
-}
-
-void free_result(void) {
-    if (last_result != NULL) {
-        free(last_result);
-        last_result = NULL;
-    }
-}

backend/go/voxtral/csrc/govoxtral.h

@@ -1,8 +0,0 @@
-#ifndef GOVOXTRAL_H
-#define GOVOXTRAL_H
-
-extern int load_model(const char *model_dir);
-extern const char *transcribe(const char *wav_path);
-extern void free_result(void);
-
-#endif /* GOVOXTRAL_H */

backend/go/voxtral/govoxtral.go

@@ -1,60 +0,0 @@
-package main
-
-import (
-	"fmt"
-	"os"
-	"strings"
-
-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/utils"
-)
-
-var (
-	CppLoadModel  func(modelDir string) int
-	CppTranscribe func(wavPath string) string
-	CppFreeResult func()
-)
-
-type Voxtral struct {
-	base.SingleThread
-}
-
-func (v *Voxtral) Load(opts *pb.ModelOptions) error {
-	if ret := CppLoadModel(opts.ModelFile); ret != 0 {
-		return fmt.Errorf("failed to load Voxtral model from %s", opts.ModelFile)
-	}
-	return nil
-}
-
-func (v *Voxtral) AudioTranscription(opts *pb.TranscriptRequest) (pb.TranscriptResult, error) {
-	dir, err := os.MkdirTemp("", "voxtral")
-	if err != nil {
-		return pb.TranscriptResult{}, err
-	}
-	defer os.RemoveAll(dir)
-
-	convertedPath := dir + "/converted.wav"
-
-	if err := utils.AudioToWav(opts.Dst, convertedPath); err != nil {
-		return pb.TranscriptResult{}, err
-	}
-
-	result := strings.Clone(CppTranscribe(convertedPath))
-	CppFreeResult()
-
-	text := strings.TrimSpace(result)
-
-	segments := []*pb.TranscriptSegment{}
-	if text != "" {
-		segments = append(segments, &pb.TranscriptSegment{
-			Id:   0,
-			Text: text,
-		})
-	}
-
-	return pb.TranscriptResult{
-		Segments: segments,
-		Text:     text,
-	}, nil
-}

backend/go/voxtral/main.go

@@ -1,53 +0,0 @@
-package main
-
-// Note: this is started internally by LocalAI and a server is allocated for each model
-import (
-	"flag"
-	"os"
-	"runtime"
-
-	"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() {
-	// Get library name from environment variable, default to fallback
-	libName := os.Getenv("VOXTRAL_LIBRARY")
-	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgovoxtral-fallback.dylib"
-		} else {
-			libName = "./libgovoxtral-fallback.so"
-		}
-	}
-
-	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
-	if err != nil {
-		panic(err)
-	}
-
-	libFuncs := []LibFuncs{
-		{&CppLoadModel, "load_model"},
-		{&CppTranscribe, "transcribe"},
-		{&CppFreeResult, "free_result"},
-	}
-
-	for _, lf := range libFuncs {
-		purego.RegisterLibFunc(lf.FuncPtr, gosd, lf.Name)
-	}
-
-	flag.Parse()
-
-	if err := grpc.StartServer(*addr, &Voxtral{}); err != nil {
-		panic(err)
-	}
-}

backend/go/voxtral/package.sh

@@ -1,68 +0,0 @@
-#!/bin/bash
-
-# Script to copy the appropriate libraries based on architecture
-
-set -e
-
-CURDIR=$(dirname "$(realpath $0)")
-REPO_ROOT="${CURDIR}/../../.."
-
-# Create lib directory
-mkdir -p $CURDIR/package/lib
-
-cp -avf $CURDIR/voxtral $CURDIR/package/
-cp -fv $CURDIR/libgovoxtral-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgovoxtral-*.dylib $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/run.sh $CURDIR/package/
-
-# Detect architecture and copy appropriate libraries
-if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
-    # x86_64 architecture
-    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
-    # OpenBLAS if available
-    if [ -f /usr/lib/x86_64-linux-gnu/libopenblas.so.0 ]; then
-        cp -arfLv /usr/lib/x86_64-linux-gnu/libopenblas.so.0 $CURDIR/package/lib/
-    fi
-elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
-    # ARM64 architecture
-    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
-    # OpenBLAS if available
-    if [ -f /usr/lib/aarch64-linux-gnu/libopenblas.so.0 ]; then
-        cp -arfLv /usr/lib/aarch64-linux-gnu/libopenblas.so.0 $CURDIR/package/lib/
-    fi
-elif [ $(uname -s) = "Darwin" ]; then
-    echo "Detected Darwin — system frameworks linked dynamically, no bundled libs needed"
-else
-    echo "Error: Could not detect architecture"
-    exit 1
-fi
-
-# Package GPU libraries based on BUILD_TYPE
-GPU_LIB_SCRIPT="${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/
-ls -liah $CURDIR/package/lib/

backend/go/voxtral/run.sh

@@ -1,49 +0,0 @@
-#!/bin/bash
-set -ex
-
-# Get the absolute current dir where the script is located
-CURDIR=$(dirname "$(realpath $0)")
-
-cd /
-
-echo "CPU info:"
-if [ "$(uname)" != "Darwin" ]; then
-	grep -e "model\sname" /proc/cpuinfo | head -1
-	grep -e "flags" /proc/cpuinfo | head -1
-fi
-
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgovoxtral-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgovoxtral-fallback.so"
-
-	if grep -q -e "\savx\s" /proc/cpuinfo ; then
-		echo "CPU:    AVX    found OK"
-		if [ -e $CURDIR/libgovoxtral-avx.so ]; then
-			LIBRARY="$CURDIR/libgovoxtral-avx.so"
-		fi
-	fi
-
-	if grep -q -e "\savx2\s" /proc/cpuinfo ; then
-		echo "CPU:    AVX2   found OK"
-		if [ -e $CURDIR/libgovoxtral-avx2.so ]; then
-			LIBRARY="$CURDIR/libgovoxtral-avx2.so"
-		fi
-	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
-fi
-
-export VOXTRAL_LIBRARY=$LIBRARY
-
-# If there is a lib/ld.so, use it (Linux only)
-if [ -f $CURDIR/lib/ld.so ]; then
-	echo "Using lib/ld.so"
-	echo "Using library: $LIBRARY"
-	exec $CURDIR/lib/ld.so $CURDIR/voxtral "$@"
-fi
-
-echo "Using library: $LIBRARY"
-exec $CURDIR/voxtral "$@"

backend/go/voxtral/test.sh

@@ -1,48 +0,0 @@
-#!/bin/bash
-set -e
-
-CURDIR=$(dirname "$(realpath $0)")
-
-echo "Running voxtral backend tests..."
-
-# The test requires:
-#   - VOXTRAL_MODEL_DIR: path to directory containing consolidated.safetensors + tekken.json
-#   - VOXTRAL_BINARY: path to the voxtral binary (defaults to ./voxtral)
-#
-# Tests that require the model will be skipped if VOXTRAL_MODEL_DIR is not set.
-
-cd "$CURDIR"
-export VOXTRAL_MODEL_DIR="${VOXTRAL_MODEL_DIR:-./voxtral-model}"
-
-if [ ! -d "$VOXTRAL_MODEL_DIR" ]; then
-    echo "Creating voxtral-model directory for tests..."
-    mkdir -p "$VOXTRAL_MODEL_DIR"
-    MODEL_ID="mistralai/Voxtral-Mini-4B-Realtime-2602"
-    echo "Model: ${MODEL_ID}"
-    echo ""
-
-    # Files to download
-    FILES=(
-        "consolidated.safetensors"
-        "params.json"
-        "tekken.json"
-    )
-
-    BASE_URL="https://huggingface.co/${MODEL_ID}/resolve/main"
-
-    for file in "${FILES[@]}"; do
-        dest="${VOXTRAL_MODEL_DIR}/${file}"
-        if [ -f "${dest}" ]; then
-            echo "  [skip] ${file} (already exists)"
-        else
-            echo "  [download] ${file}..."
-            curl -L -o "${dest}" "${BASE_URL}/${file}" --progress-bar
-            echo "  [done] ${file}"
-        fi
-    done
-fi
-
-# Run Go tests
-go test -v -timeout 300s ./...
-
-echo "All voxtral tests passed."

backend/go/voxtral/voxtral_test.go

@@ -1,201 +0,0 @@
-package main
-
-import (
-	"context"
-	"fmt"
-	"io"
-	"net/http"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"strings"
-	"testing"
-	"time"
-
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"google.golang.org/grpc"
-	"google.golang.org/grpc/credentials/insecure"
-)
-
-const (
-	testAddr    = "localhost:50051"
-	sampleAudio = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-ASR-Repo/asr_en.wav"
-	startupWait = 5 * time.Second
-)
-
-func skipIfNoModel(t *testing.T) string {
-	t.Helper()
-	modelDir := os.Getenv("VOXTRAL_MODEL_DIR")
-	if modelDir == "" {
-		t.Skip("VOXTRAL_MODEL_DIR not set, skipping test (set to voxtral model directory)")
-	}
-	if _, err := os.Stat(filepath.Join(modelDir, "consolidated.safetensors")); os.IsNotExist(err) {
-		t.Skipf("Model file not found in %s, skipping", modelDir)
-	}
-	return modelDir
-}
-
-func startServer(t *testing.T) *exec.Cmd {
-	t.Helper()
-	binary := os.Getenv("VOXTRAL_BINARY")
-	if binary == "" {
-		binary = "./voxtral"
-	}
-	if _, err := os.Stat(binary); os.IsNotExist(err) {
-		t.Skipf("Backend binary not found at %s, skipping", binary)
-	}
-	cmd := exec.Command(binary, "--addr", testAddr)
-	cmd.Stdout = os.Stderr
-	cmd.Stderr = os.Stderr
-	if err := cmd.Start(); err != nil {
-		t.Fatalf("Failed to start server: %v", err)
-	}
-	time.Sleep(startupWait)
-	return cmd
-}
-
-func stopServer(cmd *exec.Cmd) {
-	if cmd != nil && cmd.Process != nil {
-		cmd.Process.Kill()
-		cmd.Wait()
-	}
-}
-
-func dialGRPC(t *testing.T) *grpc.ClientConn {
-	t.Helper()
-	conn, err := grpc.Dial(testAddr,
-		grpc.WithTransportCredentials(insecure.NewCredentials()),
-		grpc.WithDefaultCallOptions(
-			grpc.MaxCallRecvMsgSize(50*1024*1024),
-			grpc.MaxCallSendMsgSize(50*1024*1024),
-		),
-	)
-	if err != nil {
-		t.Fatalf("Failed to dial gRPC: %v", err)
-	}
-	return conn
-}
-
-func downloadFile(url, dest string) error {
-	resp, err := http.Get(url)
-	if err != nil {
-		return fmt.Errorf("HTTP GET failed: %w", err)
-	}
-	defer resp.Body.Close()
-	if resp.StatusCode != http.StatusOK {
-		return fmt.Errorf("bad status: %s", resp.Status)
-	}
-	f, err := os.Create(dest)
-	if err != nil {
-		return err
-	}
-	defer f.Close()
-	_, err = io.Copy(f, resp.Body)
-	return err
-}
-
-func TestServerHealth(t *testing.T) {
-	cmd := startServer(t)
-	defer stopServer(cmd)
-
-	conn := dialGRPC(t)
-	defer conn.Close()
-
-	client := pb.NewBackendClient(conn)
-	resp, err := client.Health(context.Background(), &pb.HealthMessage{})
-	if err != nil {
-		t.Fatalf("Health check failed: %v", err)
-	}
-	if string(resp.Message) != "OK" {
-		t.Fatalf("Expected OK, got %s", string(resp.Message))
-	}
-}
-
-func TestLoadModel(t *testing.T) {
-	modelDir := skipIfNoModel(t)
-	cmd := startServer(t)
-	defer stopServer(cmd)
-
-	conn := dialGRPC(t)
-	defer conn.Close()
-
-	client := pb.NewBackendClient(conn)
-	resp, err := client.LoadModel(context.Background(), &pb.ModelOptions{
-		ModelFile: modelDir,
-	})
-	if err != nil {
-		t.Fatalf("LoadModel failed: %v", err)
-	}
-	if !resp.Success {
-		t.Fatalf("LoadModel returned failure: %s", resp.Message)
-	}
-}
-
-func TestAudioTranscription(t *testing.T) {
-	modelDir := skipIfNoModel(t)
-
-	tmpDir, err := os.MkdirTemp("", "voxtral-test")
-	if err != nil {
-		t.Fatal(err)
-	}
-	defer os.RemoveAll(tmpDir)
-
-	// Download sample audio — JFK "ask not what your country can do for you" clip
-	audioFile := filepath.Join(tmpDir, "sample.wav")
-	t.Log("Downloading sample audio...")
-	if err := downloadFile(sampleAudio, audioFile); err != nil {
-		t.Fatalf("Failed to download sample audio: %v", err)
-	}
-
-	cmd := startServer(t)
-	defer stopServer(cmd)
-
-	conn := dialGRPC(t)
-	defer conn.Close()
-
-	client := pb.NewBackendClient(conn)
-
-	// Load model
-	loadResp, err := client.LoadModel(context.Background(), &pb.ModelOptions{
-		ModelFile: modelDir,
-	})
-	if err != nil {
-		t.Fatalf("LoadModel failed: %v", err)
-	}
-	if !loadResp.Success {
-		t.Fatalf("LoadModel returned failure: %s", loadResp.Message)
-	}
-
-	// Transcribe
-	transcriptResp, err := client.AudioTranscription(context.Background(), &pb.TranscriptRequest{
-		Dst: audioFile,
-	})
-	if err != nil {
-		t.Fatalf("AudioTranscription failed: %v", err)
-	}
-	if transcriptResp == nil {
-		t.Fatal("AudioTranscription returned nil")
-	}
-
-	t.Logf("Transcribed text: %s", transcriptResp.Text)
-	t.Logf("Number of segments: %d", len(transcriptResp.Segments))
-
-	if transcriptResp.Text == "" {
-		t.Fatal("Transcription returned empty text")
-	}
-
-	allText := strings.ToLower(transcriptResp.Text)
-	for _, seg := range transcriptResp.Segments {
-		allText += " " + strings.ToLower(seg.Text)
-	}
-	t.Logf("All text: %s", allText)
-
-	if !strings.Contains(allText, "big") {
-		t.Errorf("Expected 'big' in transcription, got: %s", allText)
-	}
-
-	// The sample audio should contain recognizable speech
-	if len(allText) < 10 {
-		t.Errorf("Transcription too short: %q", allText)
-	}
-}

backend/go/whisper/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=941bdabbe4561bc6de68981aea01bc5ab05781c5
+WHISPER_CPP_VERSION?=aa1bc0d1a6dfd70dbb9f60c11df12441e03a9075
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -78,7 +78,7 @@ package: whisper
 build: package
 
 clean: purge
-	rm -rf libgowhisper*.so package sources/whisper.cpp whisper
+	rm -rf libgowhisper*.so sources/whisper.cpp whisper
 
 purge:
 	rm -rf build*

backend/index.yaml

@@ -56,21 +56,6 @@
     nvidia-cuda-12: "cuda12-whisper"
     nvidia-l4t-cuda-12: "nvidia-l4t-arm64-whisper"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-whisper"
-- &voxtral
-  name: "voxtral"
-  alias: "voxtral"
-  license: mit
-  description: |
-    Voxtral Realtime 4B Pure C speech-to-text inference engine
-  urls:
-    - https://github.com/mudler/voxtral.c
-  tags:
-    - audio-transcription
-    - CPU
-    - Metal
-  capabilities:
-    default: "cpu-voxtral"
-    metal-darwin-arm64: "metal-voxtral"
 - &stablediffusionggml
   name: "stablediffusion-ggml"
   alias: "stablediffusion-ggml"
@@ -120,7 +105,6 @@
     intel: "intel-rfdetr"
     #amd: "rocm-rfdetr"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr"
-    metal: "metal-rfdetr"
     default: "cpu-rfdetr"
     nvidia-cuda-13: "cuda13-rfdetr"
     nvidia-cuda-12: "cuda12-rfdetr"
@@ -198,15 +182,6 @@
     - text-to-text
     - LLM
     - MLX
-  capabilities:
-    default: "cpu-mlx"
-    nvidia: "cuda12-mlx"
-    metal: "metal-mlx"
-    nvidia-cuda-12: "cuda12-mlx"
-    nvidia-cuda-13: "cuda13-mlx"
-    nvidia-l4t: "nvidia-l4t-mlx"
-    nvidia-l4t-cuda-12: "nvidia-l4t-mlx"
-    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx"
 - &mlx-vlm
   name: "mlx-vlm"
   uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-vlm"
@@ -224,15 +199,6 @@
     - vision-language
     - LLM
     - MLX
-  capabilities:
-    default: "cpu-mlx-vlm"
-    nvidia: "cuda12-mlx-vlm"
-    metal: "metal-mlx-vlm"
-    nvidia-cuda-12: "cuda12-mlx-vlm"
-    nvidia-cuda-13: "cuda13-mlx-vlm"
-    nvidia-l4t: "nvidia-l4t-mlx-vlm"
-    nvidia-l4t-cuda-12: "nvidia-l4t-mlx-vlm"
-    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-vlm"
 - &mlx-audio
   name: "mlx-audio"
   uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-audio"
@@ -250,15 +216,6 @@
     - text-to-audio
     - LLM
     - MLX
-  capabilities:
-    default: "cpu-mlx-audio"
-    nvidia: "cuda12-mlx-audio"
-    metal: "metal-mlx-audio"
-    nvidia-cuda-12: "cuda12-mlx-audio"
-    nvidia-cuda-13: "cuda13-mlx-audio"
-    nvidia-l4t: "nvidia-l4t-mlx-audio"
-    nvidia-l4t-cuda-12: "nvidia-l4t-mlx-audio"
-    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-mlx-audio"
 - &rerankers
   name: "rerankers"
   alias: "rerankers"
@@ -266,7 +223,6 @@
     nvidia: "cuda12-rerankers"
     intel: "intel-rerankers"
     amd: "rocm-rerankers"
-    metal: "metal-rerankers"
 - &transformers
   name: "transformers"
   icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4
@@ -284,7 +240,6 @@
     nvidia: "cuda12-transformers"
     intel: "intel-transformers"
     amd: "rocm-transformers"
-    metal: "metal-transformers"
     nvidia-cuda-13: "cuda13-transformers"
     nvidia-cuda-12: "cuda12-transformers"
 - &diffusers
@@ -311,34 +266,6 @@
     nvidia-cuda-12: "cuda12-diffusers"
     nvidia-l4t-cuda-12: "nvidia-l4t-arm64-diffusers"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-diffusers"
-- &ace-step
-  name: "ace-step"
-  description: |
-    ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio).
-  urls:
-    - https://github.com/ace-step/ACE-Step-1.5
-  tags:
-    - music-generation
-    - sound-generation
-  alias: "ace-step"
-  capabilities:
-    nvidia: "cuda12-ace-step"
-    intel: "intel-ace-step"
-    amd: "rocm-ace-step"
-    metal: "metal-ace-step"
-    default: "cpu-ace-step"
-    nvidia-cuda-13: "cuda13-ace-step"
-    nvidia-cuda-12: "cuda12-ace-step"
-- !!merge <<: *ace-step
-  name: "ace-step-development"
-  capabilities:
-    nvidia: "cuda12-ace-step-development"
-    intel: "intel-ace-step-development"
-    amd: "rocm-ace-step-development"
-    metal: "metal-ace-step-development"
-    default: "cpu-ace-step-development"
-    nvidia-cuda-13: "cuda13-ace-step-development"
-    nvidia-cuda-12: "cuda12-ace-step-development"
 - &faster-whisper
   icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4
   description: |
@@ -355,7 +282,6 @@
     nvidia: "cuda12-faster-whisper"
     intel: "intel-faster-whisper"
     amd: "rocm-faster-whisper"
-    metal: "metal-faster-whisper"
     nvidia-cuda-13: "cuda13-faster-whisper"
     nvidia-cuda-12: "cuda12-faster-whisper"
 - &moonshine
@@ -373,7 +299,6 @@
   alias: "moonshine"
   capabilities:
     nvidia: "cuda12-moonshine"
-    metal: "metal-moonshine"
     default: "cpu-moonshine"
     nvidia-cuda-13: "cuda13-moonshine"
     nvidia-cuda-12: "cuda12-moonshine"
@@ -393,7 +318,6 @@
   capabilities:
     nvidia: "cuda12-whisperx"
     amd: "rocm-whisperx"
-    metal: "metal-whisperx"
     default: "cpu-whisperx"
     nvidia-cuda-13: "cuda13-whisperx"
     nvidia-cuda-12: "cuda12-whisperx"
@@ -416,7 +340,6 @@
     intel: "intel-kokoro"
     amd: "rocm-kokoro"
     nvidia-l4t: "nvidia-l4t-kokoro"
-    metal: "metal-kokoro"
     nvidia-cuda-13: "cuda13-kokoro"
     nvidia-cuda-12: "cuda12-kokoro"
     nvidia-l4t-cuda-12: "nvidia-l4t-arm64-kokoro"
@@ -441,25 +364,9 @@
     nvidia: "cuda12-coqui"
     intel: "intel-coqui"
     amd: "rocm-coqui"
-    metal: "metal-coqui"
     nvidia-cuda-13: "cuda13-coqui"
     nvidia-cuda-12: "cuda12-coqui"
   icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4
-- &outetts
-  urls:
-    - https://github.com/OuteAI/outetts
-  description: |
-    OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B).
-    Supports custom speaker voices via audio path or default speakers.
-  tags:
-    - text-to-speech
-    - TTS
-  license: apache-2.0
-  name: "outetts"
-  alias: "outetts"
-  capabilities:
-    default: "cpu-outetts"
-    nvidia-cuda-12: "cuda12-outetts"
 - &chatterbox
   urls:
     - https://github.com/resemble-ai/chatterbox
@@ -498,7 +405,6 @@
     intel: "intel-vibevoice"
     amd: "rocm-vibevoice"
     nvidia-l4t: "nvidia-l4t-vibevoice"
-    metal: "metal-vibevoice"
     default: "cpu-vibevoice"
     nvidia-cuda-13: "cuda13-vibevoice"
     nvidia-cuda-12: "cuda12-vibevoice"
@@ -521,7 +427,6 @@
     intel: "intel-qwen-tts"
     amd: "rocm-qwen-tts"
     nvidia-l4t: "nvidia-l4t-qwen-tts"
-    metal: "metal-qwen-tts"
     default: "cpu-qwen-tts"
     nvidia-cuda-13: "cuda13-qwen-tts"
     nvidia-cuda-12: "cuda12-qwen-tts"
@@ -544,34 +449,12 @@
     intel: "intel-qwen-asr"
     amd: "rocm-qwen-asr"
     nvidia-l4t: "nvidia-l4t-qwen-asr"
-    metal: "metal-qwen-asr"
     default: "cpu-qwen-asr"
     nvidia-cuda-13: "cuda13-qwen-asr"
     nvidia-cuda-12: "cuda12-qwen-asr"
     nvidia-l4t-cuda-12: "nvidia-l4t-qwen-asr"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-qwen-asr"
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png
-- &nemo
-  urls:
-    - https://github.com/NVIDIA/NeMo
-  description: |
-    NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases.
-  tags:
-    - speech-recognition
-    - ASR
-    - NVIDIA
-  license: apache-2.0
-  name: "nemo"
-  alias: "nemo"
-  capabilities:
-    nvidia: "cuda12-nemo"
-    intel: "intel-nemo"
-    amd: "rocm-nemo"
-    metal: "metal-nemo"
-    default: "cpu-nemo"
-    nvidia-cuda-13: "cuda13-nemo"
-    nvidia-cuda-12: "cuda12-nemo"
-  icon: https://www.nvidia.com/favicon.ico
 - &voxcpm
   urls:
     - https://github.com/ModelBest/VoxCPM
@@ -587,7 +470,6 @@
     nvidia: "cuda12-voxcpm"
     intel: "intel-voxcpm"
     amd: "rocm-voxcpm"
-    metal: "metal-voxcpm"
     default: "cpu-voxcpm"
     nvidia-cuda-13: "cuda13-voxcpm"
     nvidia-cuda-12: "cuda12-voxcpm"
@@ -608,7 +490,6 @@
     intel: "intel-pocket-tts"
     amd: "rocm-pocket-tts"
     nvidia-l4t: "nvidia-l4t-pocket-tts"
-    metal: "metal-pocket-tts"
     default: "cpu-pocket-tts"
     nvidia-cuda-13: "cuda13-pocket-tts"
     nvidia-cuda-12: "cuda12-pocket-tts"
@@ -769,234 +650,31 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-audio"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-mlx-audio
-## mlx
-- !!merge <<: *mlx
-  name: "cpu-mlx"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-mlx"
-  mirrors:
-    - localai/localai-backends:latest-cpu-mlx
-- !!merge <<: *mlx
-  name: "cpu-mlx-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-mlx"
-  mirrors:
-    - localai/localai-backends:master-cpu-mlx
-- !!merge <<: *mlx
-  name: "cuda12-mlx"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx
-- !!merge <<: *mlx
-  name: "cuda12-mlx-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx
-- !!merge <<: *mlx
-  name: "cuda13-mlx"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx
-- !!merge <<: *mlx
-  name: "cuda13-mlx-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx
-- !!merge <<: *mlx
-  name: "nvidia-l4t-mlx"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx"
-  mirrors:
-    - localai/localai-backends:latest-nvidia-l4t-mlx
-- !!merge <<: *mlx
-  name: "nvidia-l4t-mlx-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx"
-  mirrors:
-    - localai/localai-backends:master-nvidia-l4t-mlx
-- !!merge <<: *mlx
-  name: "cuda13-nvidia-l4t-arm64-mlx"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx"
-  mirrors:
-    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx
-- !!merge <<: *mlx
-  name: "cuda13-nvidia-l4t-arm64-mlx-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx"
-  mirrors:
-    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx
-## mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "cpu-mlx-vlm"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:latest-cpu-mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "cpu-mlx-vlm-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:master-cpu-mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "cuda12-mlx-vlm"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "cuda12-mlx-vlm-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "cuda13-mlx-vlm"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "cuda13-mlx-vlm-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "nvidia-l4t-mlx-vlm"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:latest-nvidia-l4t-mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "nvidia-l4t-mlx-vlm-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:master-nvidia-l4t-mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "cuda13-nvidia-l4t-arm64-mlx-vlm"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm
-- !!merge <<: *mlx-vlm
-  name: "cuda13-nvidia-l4t-arm64-mlx-vlm-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm"
-  mirrors:
-    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm
-## mlx-audio
-- !!merge <<: *mlx-audio
-  name: "cpu-mlx-audio"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-audio"
-  mirrors:
-    - localai/localai-backends:latest-cpu-mlx-audio
-- !!merge <<: *mlx-audio
-  name: "cpu-mlx-audio-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-mlx-audio"
-  mirrors:
-    - localai/localai-backends:master-cpu-mlx-audio
-- !!merge <<: *mlx-audio
-  name: "cuda12-mlx-audio"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-audio"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-audio
-- !!merge <<: *mlx-audio
-  name: "cuda12-mlx-audio-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-audio"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-audio
-- !!merge <<: *mlx-audio
-  name: "cuda13-mlx-audio"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-audio"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-audio
-- !!merge <<: *mlx-audio
-  name: "cuda13-mlx-audio-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-audio"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-audio
-- !!merge <<: *mlx-audio
-  name: "nvidia-l4t-mlx-audio"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-audio"
-  mirrors:
-    - localai/localai-backends:latest-nvidia-l4t-mlx-audio
-- !!merge <<: *mlx-audio
-  name: "nvidia-l4t-mlx-audio-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-audio"
-  mirrors:
-    - localai/localai-backends:master-nvidia-l4t-mlx-audio
-- !!merge <<: *mlx-audio
-  name: "cuda13-nvidia-l4t-arm64-mlx-audio"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio"
-  mirrors:
-    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio
-- !!merge <<: *mlx-audio
-  name: "cuda13-nvidia-l4t-arm64-mlx-audio-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio"
-  mirrors:
-    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio
 - !!merge <<: *kitten-tts
   name: "kitten-tts-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-kitten-tts"
   mirrors:
     - localai/localai-backends:master-kitten-tts
-- !!merge <<: *kitten-tts
-  name: "metal-kitten-tts"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kitten-tts"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-kitten-tts
-- !!merge <<: *kitten-tts
-  name: "metal-kitten-tts-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kitten-tts"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-kitten-tts
 - !!merge <<: *huggingface
   name: "huggingface-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-huggingface"
   mirrors:
     - localai/localai-backends:master-huggingface
-- !!merge <<: *huggingface
-  name: "metal-huggingface"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-huggingface"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-huggingface
-- !!merge <<: *huggingface
-  name: "metal-huggingface-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-huggingface"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-huggingface
 - !!merge <<: *local-store
   name: "local-store-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-local-store"
   mirrors:
     - localai/localai-backends:master-cpu-local-store
-- !!merge <<: *local-store
-  name: "metal-local-store"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-local-store"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-local-store
-- !!merge <<: *local-store
-  name: "metal-local-store-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-local-store"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-local-store
 - !!merge <<: *silero-vad
   name: "silero-vad-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-silero-vad"
   mirrors:
     - localai/localai-backends:master-cpu-silero-vad
-- !!merge <<: *silero-vad
-  name: "metal-silero-vad"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-silero-vad"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-silero-vad
-- !!merge <<: *silero-vad
-  name: "metal-silero-vad-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-silero-vad"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-silero-vad
 - !!merge <<: *piper
   name: "piper-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-piper"
   mirrors:
     - localai/localai-backends:master-piper
-- !!merge <<: *piper
-  name: "metal-piper"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-piper"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-piper
-- !!merge <<: *piper
-  name: "metal-piper-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-piper"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-piper
 ## llama-cpp
 - !!merge <<: *llamacpp
   name: "nvidia-l4t-arm64-llama-cpp"
@@ -1370,7 +1048,6 @@
     intel: "intel-rfdetr-development"
     #amd: "rocm-rfdetr-development"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr-development"
-    metal: "metal-rfdetr-development"
     default: "cpu-rfdetr-development"
     nvidia-cuda-13: "cuda13-rfdetr-development"
 - !!merge <<: *rfdetr
@@ -1438,16 +1115,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rfdetr"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-rfdetr
-- !!merge <<: *rfdetr
-  name: "metal-rfdetr"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-rfdetr"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-rfdetr
-- !!merge <<: *rfdetr
-  name: "metal-rfdetr-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-rfdetr"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-rfdetr
 ## Rerankers
 - !!merge <<: *rerankers
   name: "rerankers-development"
@@ -1455,7 +1122,6 @@
     nvidia: "cuda12-rerankers-development"
     intel: "intel-rerankers-development"
     amd: "rocm-rerankers-development"
-    metal: "metal-rerankers-development"
     nvidia-cuda-13: "cuda13-rerankers-development"
 - !!merge <<: *rerankers
   name: "cuda12-rerankers"
@@ -1497,16 +1163,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rerankers"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-rerankers
-- !!merge <<: *rerankers
-  name: "metal-rerankers"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-rerankers"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-rerankers
-- !!merge <<: *rerankers
-  name: "metal-rerankers-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-rerankers"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-rerankers
 ## Transformers
 - !!merge <<: *transformers
   name: "transformers-development"
@@ -1514,7 +1170,6 @@
     nvidia: "cuda12-transformers-development"
     intel: "intel-transformers-development"
     amd: "rocm-transformers-development"
-    metal: "metal-transformers-development"
     nvidia-cuda-13: "cuda13-transformers-development"
 - !!merge <<: *transformers
   name: "cuda12-transformers"
@@ -1556,16 +1211,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-transformers"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-transformers
-- !!merge <<: *transformers
-  name: "metal-transformers"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-transformers"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-transformers
-- !!merge <<: *transformers
-  name: "metal-transformers-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-transformers"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-transformers
 ## Diffusers
 - !!merge <<: *diffusers
   name: "diffusers-development"
@@ -1657,67 +1302,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-diffusers"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-diffusers
-## ace-step
-- !!merge <<: *ace-step
-  name: "cpu-ace-step"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-ace-step"
-  mirrors:
-    - localai/localai-backends:latest-cpu-ace-step
-- !!merge <<: *ace-step
-  name: "cpu-ace-step-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-ace-step"
-  mirrors:
-    - localai/localai-backends:master-cpu-ace-step
-- !!merge <<: *ace-step
-  name: "cuda12-ace-step"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-ace-step"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-12-ace-step
-- !!merge <<: *ace-step
-  name: "cuda12-ace-step-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-ace-step"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-12-ace-step
-- !!merge <<: *ace-step
-  name: "cuda13-ace-step"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-ace-step"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-13-ace-step
-- !!merge <<: *ace-step
-  name: "cuda13-ace-step-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-ace-step"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-13-ace-step
-- !!merge <<: *ace-step
-  name: "rocm-ace-step"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-ace-step"
-  mirrors:
-    - localai/localai-backends:latest-gpu-rocm-hipblas-ace-step
-- !!merge <<: *ace-step
-  name: "rocm-ace-step-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-ace-step"
-  mirrors:
-    - localai/localai-backends:master-gpu-rocm-hipblas-ace-step
-- !!merge <<: *ace-step
-  name: "intel-ace-step"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-ace-step"
-  mirrors:
-    - localai/localai-backends:latest-gpu-intel-ace-step
-- !!merge <<: *ace-step
-  name: "intel-ace-step-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-ace-step"
-  mirrors:
-    - localai/localai-backends:master-gpu-intel-ace-step
-- !!merge <<: *ace-step
-  name: "metal-ace-step"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-ace-step"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-ace-step
-- !!merge <<: *ace-step
-  name: "metal-ace-step-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-ace-step"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-ace-step
 ## kokoro
 - !!merge <<: *kokoro
   name: "kokoro-development"
@@ -1726,7 +1310,6 @@
     intel: "intel-kokoro-development"
     amd: "rocm-kokoro-development"
     nvidia-l4t: "nvidia-l4t-kokoro-development"
-    metal: "metal-kokoro-development"
 - !!merge <<: *kokoro
   name: "cuda12-kokoro-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-kokoro"
@@ -1777,16 +1360,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-kokoro"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-kokoro
-- !!merge <<: *kokoro
-  name: "metal-kokoro"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kokoro"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-kokoro
-- !!merge <<: *kokoro
-  name: "metal-kokoro-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kokoro"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-kokoro
 ## faster-whisper
 - !!merge <<: *faster-whisper
   name: "faster-whisper-development"
@@ -1794,7 +1367,6 @@
     nvidia: "cuda12-faster-whisper-development"
     intel: "intel-faster-whisper-development"
     amd: "rocm-faster-whisper-development"
-    metal: "metal-faster-whisper-development"
     nvidia-cuda-13: "cuda13-faster-whisper-development"
 - !!merge <<: *faster-whisper
   name: "cuda12-faster-whisper-development"
@@ -1826,16 +1398,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-faster-whisper"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-faster-whisper
-- !!merge <<: *faster-whisper
-  name: "metal-faster-whisper"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-faster-whisper"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-faster-whisper
-- !!merge <<: *faster-whisper
-  name: "metal-faster-whisper-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-faster-whisper"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-faster-whisper
 ## moonshine
 - !!merge <<: *moonshine
   name: "moonshine-development"
@@ -1874,23 +1436,12 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-moonshine"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-moonshine
-- !!merge <<: *moonshine
-  name: "metal-moonshine"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-moonshine"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-moonshine
-- !!merge <<: *moonshine
-  name: "metal-moonshine-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-moonshine"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-moonshine
 ## whisperx
 - !!merge <<: *whisperx
   name: "whisperx-development"
   capabilities:
     nvidia: "cuda12-whisperx-development"
     amd: "rocm-whisperx-development"
-    metal: "metal-whisperx-development"
     default: "cpu-whisperx-development"
     nvidia-cuda-13: "cuda13-whisperx-development"
     nvidia-cuda-12: "cuda12-whisperx-development"
@@ -1934,16 +1485,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-whisperx"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-whisperx
-- !!merge <<: *whisperx
-  name: "metal-whisperx"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-whisperx"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-whisperx
-- !!merge <<: *whisperx
-  name: "metal-whisperx-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-whisperx"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-whisperx
 ## coqui
 
 - !!merge <<: *coqui
@@ -1952,7 +1493,6 @@
     nvidia: "cuda12-coqui-development"
     intel: "intel-coqui-development"
     amd: "rocm-coqui-development"
-    metal: "metal-coqui-development"
 - !!merge <<: *coqui
   name: "cuda12-coqui"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-coqui"
@@ -1983,42 +1523,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-coqui"
   mirrors:
     - localai/localai-backends:latest-gpu-rocm-hipblas-coqui
-- !!merge <<: *coqui
-  name: "metal-coqui"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-coqui"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-coqui
-- !!merge <<: *coqui
-  name: "metal-coqui-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-coqui"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-coqui
-## outetts
-- !!merge <<: *outetts
-  name: "outetts-development"
-  capabilities:
-    default: "cpu-outetts-development"
-    nvidia-cuda-12: "cuda12-outetts-development"
-- !!merge <<: *outetts
-  name: "cpu-outetts"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-outetts"
-  mirrors:
-    - localai/localai-backends:latest-cpu-outetts
-- !!merge <<: *outetts
-  name: "cpu-outetts-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-outetts"
-  mirrors:
-    - localai/localai-backends:master-cpu-outetts
-- !!merge <<: *outetts
-  name: "cuda12-outetts"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-outetts"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-12-outetts
-- !!merge <<: *outetts
-  name: "cuda12-outetts-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-outetts"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-12-outetts
 ## chatterbox
 - !!merge <<: *chatterbox
   name: "chatterbox-development"
@@ -2099,7 +1603,6 @@
     intel: "intel-vibevoice-development"
     amd: "rocm-vibevoice-development"
     nvidia-l4t: "nvidia-l4t-vibevoice-development"
-    metal: "metal-vibevoice-development"
     default: "cpu-vibevoice-development"
     nvidia-cuda-13: "cuda13-vibevoice-development"
     nvidia-cuda-12: "cuda12-vibevoice-development"
@@ -2175,16 +1678,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice"
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice
-- !!merge <<: *vibevoice
-  name: "metal-vibevoice"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-vibevoice"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-vibevoice
-- !!merge <<: *vibevoice
-  name: "metal-vibevoice-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-vibevoice"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-vibevoice
 ## qwen-tts
 - !!merge <<: *qwen-tts
   name: "qwen-tts-development"
@@ -2193,7 +1686,6 @@
     intel: "intel-qwen-tts-development"
     amd: "rocm-qwen-tts-development"
     nvidia-l4t: "nvidia-l4t-qwen-tts-development"
-    metal: "metal-qwen-tts-development"
     default: "cpu-qwen-tts-development"
     nvidia-cuda-13: "cuda13-qwen-tts-development"
     nvidia-cuda-12: "cuda12-qwen-tts-development"
@@ -2269,16 +1761,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-tts"
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-tts
-- !!merge <<: *qwen-tts
-  name: "metal-qwen-tts"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qwen-tts"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-qwen-tts
-- !!merge <<: *qwen-tts
-  name: "metal-qwen-tts-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-tts"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-qwen-tts
 ## qwen-asr
 - !!merge <<: *qwen-asr
   name: "qwen-asr-development"
@@ -2287,7 +1769,6 @@
     intel: "intel-qwen-asr-development"
     amd: "rocm-qwen-asr-development"
     nvidia-l4t: "nvidia-l4t-qwen-asr-development"
-    metal: "metal-qwen-asr-development"
     default: "cpu-qwen-asr-development"
     nvidia-cuda-13: "cuda13-qwen-asr-development"
     nvidia-cuda-12: "cuda12-qwen-asr-development"
@@ -2363,87 +1844,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-asr"
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-asr
-- !!merge <<: *qwen-asr
-  name: "metal-qwen-asr"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qwen-asr"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-qwen-asr
-- !!merge <<: *qwen-asr
-  name: "metal-qwen-asr-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-asr"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-qwen-asr
-## nemo
-- !!merge <<: *nemo
-  name: "nemo-development"
-  capabilities:
-    nvidia: "cuda12-nemo-development"
-    intel: "intel-nemo-development"
-    amd: "rocm-nemo-development"
-    metal: "metal-nemo-development"
-    default: "cpu-nemo-development"
-    nvidia-cuda-13: "cuda13-nemo-development"
-    nvidia-cuda-12: "cuda12-nemo-development"
-- !!merge <<: *nemo
-  name: "cpu-nemo"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-nemo"
-  mirrors:
-    - localai/localai-backends:latest-cpu-nemo
-- !!merge <<: *nemo
-  name: "cpu-nemo-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-nemo"
-  mirrors:
-    - localai/localai-backends:master-cpu-nemo
-- !!merge <<: *nemo
-  name: "cuda12-nemo"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-nemo"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-12-nemo
-- !!merge <<: *nemo
-  name: "cuda12-nemo-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-nemo"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-12-nemo
-- !!merge <<: *nemo
-  name: "cuda13-nemo"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-nemo"
-  mirrors:
-    - localai/localai-backends:latest-gpu-nvidia-cuda-13-nemo
-- !!merge <<: *nemo
-  name: "cuda13-nemo-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-nemo"
-  mirrors:
-    - localai/localai-backends:master-gpu-nvidia-cuda-13-nemo
-- !!merge <<: *nemo
-  name: "intel-nemo"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-nemo"
-  mirrors:
-    - localai/localai-backends:latest-gpu-intel-nemo
-- !!merge <<: *nemo
-  name: "intel-nemo-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-nemo"
-  mirrors:
-    - localai/localai-backends:master-gpu-intel-nemo
-- !!merge <<: *nemo
-  name: "rocm-nemo"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-nemo"
-  mirrors:
-    - localai/localai-backends:latest-gpu-rocm-hipblas-nemo
-- !!merge <<: *nemo
-  name: "rocm-nemo-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-nemo"
-  mirrors:
-    - localai/localai-backends:master-gpu-rocm-hipblas-nemo
-- !!merge <<: *nemo
-  name: "metal-nemo"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-nemo"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-nemo
-- !!merge <<: *nemo
-  name: "metal-nemo-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-nemo"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-nemo
 ## voxcpm
 - !!merge <<: *voxcpm
   name: "voxcpm-development"
@@ -2451,7 +1851,6 @@
     nvidia: "cuda12-voxcpm-development"
     intel: "intel-voxcpm-development"
     amd: "rocm-voxcpm-development"
-    metal: "metal-voxcpm-development"
     default: "cpu-voxcpm-development"
     nvidia-cuda-13: "cuda13-voxcpm-development"
     nvidia-cuda-12: "cuda12-voxcpm-development"
@@ -2505,16 +1904,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-voxcpm"
   mirrors:
     - localai/localai-backends:master-gpu-rocm-hipblas-voxcpm
-- !!merge <<: *voxcpm
-  name: "metal-voxcpm"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-voxcpm"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-voxcpm
-- !!merge <<: *voxcpm
-  name: "metal-voxcpm-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-voxcpm"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-voxcpm
 ## pocket-tts
 - !!merge <<: *pocket-tts
   name: "pocket-tts-development"
@@ -2523,7 +1912,6 @@
     intel: "intel-pocket-tts-development"
     amd: "rocm-pocket-tts-development"
     nvidia-l4t: "nvidia-l4t-pocket-tts-development"
-    metal: "metal-pocket-tts-development"
     default: "cpu-pocket-tts-development"
     nvidia-cuda-13: "cuda13-pocket-tts-development"
     nvidia-cuda-12: "cuda12-pocket-tts-development"
@@ -2599,34 +1987,3 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-pocket-tts"
   mirrors:
     - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-pocket-tts
-- !!merge <<: *pocket-tts
-  name: "metal-pocket-tts"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-pocket-tts"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-pocket-tts
-- !!merge <<: *pocket-tts
-  name: "metal-pocket-tts-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-pocket-tts"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-pocket-tts
-## voxtral
-- !!merge <<: *voxtral
-  name: "cpu-voxtral"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-voxtral"
-  mirrors:
-    - localai/localai-backends:latest-cpu-voxtral
-- !!merge <<: *voxtral
-  name: "cpu-voxtral-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-voxtral"
-  mirrors:
-    - localai/localai-backends:master-cpu-voxtral
-- !!merge <<: *voxtral
-  name: "metal-voxtral"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-voxtral"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-voxtral
-- !!merge <<: *voxtral
-  name: "metal-voxtral-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-voxtral"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-voxtral

backend/python/ace-step/Makefile

@@ -1,16 +0,0 @@
-.DEFAULT_GOAL := install
-
-.PHONY: install
-install:
-	bash install.sh
-
-.PHONY: protogen-clean
-protogen-clean:
-	$(RM) backend_pb2_grpc.py backend_pb2.py
-
-.PHONY: clean
-clean: protogen-clean
-	rm -rf venv __pycache__
-
-test: install
-	bash test.sh

backend/python/ace-step/backend.py

@@ -1,472 +0,0 @@
-#!/usr/bin/env python3
-"""
-LocalAI ACE-Step Backend
-
-gRPC backend for ACE-Step 1.5 music generation. Aligns with upstream acestep API:
-- LoadModel: initializes AceStepHandler (DiT) and LLMHandler, parses Options.
-- SoundGeneration: uses create_sample (simple mode), format_sample (optional), then
-  generate_music from acestep.inference. Writes first output to request.dst.
-- Fail hard: no fallback WAV on error; exceptions propagate to gRPC.
-"""
-from concurrent import futures
-import argparse
-import shutil
-import signal
-import sys
-import os
-import tempfile
-
-import backend_pb2
-import backend_pb2_grpc
-import grpc
-from acestep.inference import (
-    GenerationParams,
-    GenerationConfig,
-    generate_music,
-    create_sample,
-    format_sample,
-)
-from acestep.handler import AceStepHandler
-from acestep.llm_inference import LLMHandler
-from acestep.model_downloader import ensure_lm_model
-
-
-_ONE_DAY_IN_SECONDS = 60 * 60 * 24
-MAX_WORKERS = int(os.environ.get("PYTHON_GRPC_MAX_WORKERS", "1"))
-
-# Model name -> HuggingFace/ModelScope repo (from upstream api_server.py)
-MODEL_REPO_MAPPING = {
-    "acestep-v15-turbo": "ACE-Step/Ace-Step1.5",
-    "acestep-5Hz-lm-0.6B": "ACE-Step/Ace-Step1.5",
-    "acestep-5Hz-lm-1.7B": "ACE-Step/Ace-Step1.5",
-    "vae": "ACE-Step/Ace-Step1.5",
-    "Qwen3-Embedding-0.6B": "ACE-Step/Ace-Step1.5",
-    "acestep-v15-base": "ACE-Step/acestep-v15-base",
-    "acestep-v15-sft": "ACE-Step/acestep-v15-sft",
-    "acestep-v15-turbo-shift3": "ACE-Step/acestep-v15-turbo-shift3",
-    "acestep-5Hz-lm-4B": "ACE-Step/acestep-5Hz-lm-4B",
-}
-DEFAULT_REPO_ID = "ACE-Step/Ace-Step1.5"
-
-def _is_float(s):
-    try:
-        float(s)
-        return True
-    except (ValueError, TypeError):
-        return False
-
-
-def _is_int(s):
-    try:
-        int(s)
-        return True
-    except (ValueError, TypeError):
-        return False
-
-
-def _parse_timesteps(s):
-    if s is None or (isinstance(s, str) and not s.strip()):
-        return None
-    if isinstance(s, (list, tuple)):
-        return [float(x) for x in s]
-    try:
-        return [float(x.strip()) for x in str(s).split(",") if x.strip()]
-    except (ValueError, TypeError):
-        return None
-
-
-def _parse_options(opts_list):
-    """Parse repeated 'key:value' options into a dict. Coerce numeric and bool."""
-    out = {}
-    for opt in opts_list or []:
-        if ":" not in opt:
-            continue
-        key, value = opt.split(":", 1)
-        key = key.strip()
-        value = value.strip()
-        if _is_int(value):
-            out[key] = int(value)
-        elif _is_float(value):
-            out[key] = float(value)
-        elif value.lower() in ("true", "false"):
-            out[key] = value.lower() == "true"
-        else:
-            out[key] = value
-    return out
-
-
-def _generate_audio_sync(servicer, payload, dst_path):
-    """
-    Run full ACE-Step pipeline using acestep.inference:
-    - If sample_mode/sample_query: create_sample() for caption/lyrics/metadata.
-    - If use_format and caption/lyrics: format_sample().
-    - Build GenerationParams and GenerationConfig, then generate_music().
-    Writes the first generated audio to dst_path. Raises on failure.
-    """
-
-    opts = servicer.options
-    dit_handler = servicer.dit_handler
-    llm_handler = servicer.llm_handler
-
-    for key, value in opts.items():
-        if key not in payload:
-            payload[key] = value
-
-    def _opt(name, default):
-        return opts.get(name, default)
-
-    lm_temperature = _opt("temperature", 0.85)
-    lm_cfg_scale = _opt("lm_cfg_scale", _opt("cfg_scale", 2.0))
-    lm_top_k = opts.get("top_k")
-    lm_top_p = _opt("top_p", 0.9)
-    if lm_top_p is not None and lm_top_p >= 1.0:
-        lm_top_p = None
-    inference_steps = _opt("inference_steps", 8)
-    guidance_scale = _opt("guidance_scale", 7.0)
-    batch_size = max(1, int(_opt("batch_size", 1)))
-
-    use_simple = bool(payload.get("sample_query") or payload.get("text"))
-    sample_mode = use_simple and (payload.get("thinking") or payload.get("sample_mode"))
-    sample_query = (payload.get("sample_query") or payload.get("text") or "").strip()
-    use_format = bool(payload.get("use_format"))
-    caption = (payload.get("prompt") or payload.get("caption") or "").strip()
-    lyrics = (payload.get("lyrics") or "").strip()
-    vocal_language = (payload.get("vocal_language") or "en").strip()
-    instrumental = bool(payload.get("instrumental"))
-    bpm = payload.get("bpm")
-    key_scale = (payload.get("key_scale") or "").strip()
-    time_signature = (payload.get("time_signature") or "").strip()
-    audio_duration = payload.get("audio_duration")
-    if audio_duration is not None:
-        try:
-            audio_duration = float(audio_duration)
-        except (TypeError, ValueError):
-            audio_duration = None
-
-    if sample_mode and llm_handler and getattr(llm_handler, "llm_initialized", False):
-        parsed_language = None
-        if sample_query:
-            for hint in ("english", "en", "chinese", "zh", "japanese", "ja"):
-                if hint in sample_query.lower():
-                    parsed_language = "en" if hint == "english" or hint == "en" else hint
-                    break
-        vocal_lang = vocal_language if vocal_language and vocal_language != "unknown" else parsed_language
-        sample_result = create_sample(
-            llm_handler=llm_handler,
-            query=sample_query or "NO USER INPUT",
-            instrumental=instrumental,
-            vocal_language=vocal_lang,
-            temperature=lm_temperature,
-            top_k=lm_top_k,
-            top_p=lm_top_p,
-            use_constrained_decoding=True,
-        )
-        if not sample_result.success:
-            raise RuntimeError(f"create_sample failed: {sample_result.error or sample_result.status_message}")
-        caption = sample_result.caption or caption
-        lyrics = sample_result.lyrics or lyrics
-        bpm = sample_result.bpm
-        key_scale = sample_result.keyscale or key_scale
-        time_signature = sample_result.timesignature or time_signature
-        if sample_result.duration is not None:
-            audio_duration = sample_result.duration
-        if getattr(sample_result, "language", None):
-            vocal_language = sample_result.language
-
-    if use_format and (caption or lyrics) and llm_handler and getattr(llm_handler, "llm_initialized", False):
-        user_metadata = {}
-        if bpm is not None:
-            user_metadata["bpm"] = bpm
-        if audio_duration is not None and float(audio_duration) > 0:
-            user_metadata["duration"] = int(audio_duration)
-        if key_scale:
-            user_metadata["keyscale"] = key_scale
-        if time_signature:
-            user_metadata["timesignature"] = time_signature
-        if vocal_language and vocal_language != "unknown":
-            user_metadata["language"] = vocal_language
-        format_result = format_sample(
-            llm_handler=llm_handler,
-            caption=caption,
-            lyrics=lyrics,
-            user_metadata=user_metadata if user_metadata else None,
-            temperature=lm_temperature,
-            top_k=lm_top_k,
-            top_p=lm_top_p,
-            use_constrained_decoding=True,
-        )
-        if format_result.success:
-            caption = format_result.caption or caption
-            lyrics = format_result.lyrics or lyrics
-            if format_result.duration is not None:
-                audio_duration = format_result.duration
-            if format_result.bpm is not None:
-                bpm = format_result.bpm
-            if format_result.keyscale:
-                key_scale = format_result.keyscale
-            if format_result.timesignature:
-                time_signature = format_result.timesignature
-            if getattr(format_result, "language", None):
-                vocal_language = format_result.language
-
-    thinking = bool(payload.get("thinking"))
-    use_cot_metas = not sample_mode
-    params = GenerationParams(
-        task_type=payload.get("task_type", "text2music"),
-        instruction=payload.get("instruction", "Fill the audio semantic mask based on the given conditions:"),
-        reference_audio=payload.get("reference_audio_path"),
-        src_audio=payload.get("src_audio_path"),
-        audio_codes=payload.get("audio_code_string", ""),
-        caption=caption,
-        lyrics=lyrics,
-        instrumental=instrumental or (not lyrics or str(lyrics).strip().lower() in ("[inst]", "[instrumental]")),
-        vocal_language=vocal_language or "unknown",
-        bpm=bpm,
-        keyscale=key_scale,
-        timesignature=time_signature,
-        duration=float(audio_duration) if audio_duration and float(audio_duration) > 0 else -1.0,
-        inference_steps=inference_steps,
-        seed=int(payload.get("seed", -1)),
-        guidance_scale=guidance_scale,
-        use_adg=bool(payload.get("use_adg")),
-        cfg_interval_start=float(payload.get("cfg_interval_start", 0.0)),
-        cfg_interval_end=float(payload.get("cfg_interval_end", 1.0)),
-        shift=float(payload.get("shift", 1.0)),
-        infer_method=(payload.get("infer_method") or "ode").strip(),
-        timesteps=_parse_timesteps(payload.get("timesteps")),
-        repainting_start=float(payload.get("repainting_start", 0.0)),
-        repainting_end=float(payload.get("repainting_end", -1)) if payload.get("repainting_end") is not None else -1,
-        audio_cover_strength=float(payload.get("audio_cover_strength", 1.0)),
-        thinking=thinking,
-        lm_temperature=lm_temperature,
-        lm_cfg_scale=lm_cfg_scale,
-        lm_top_k=lm_top_k or 0,
-        lm_top_p=lm_top_p if lm_top_p is not None and lm_top_p < 1.0 else 0.9,
-        lm_negative_prompt=payload.get("lm_negative_prompt", "NO USER INPUT"),
-        use_cot_metas=use_cot_metas,
-        use_cot_caption=bool(payload.get("use_cot_caption", True)),
-        use_cot_language=bool(payload.get("use_cot_language", True)),
-        use_constrained_decoding=True,
-    )
-
-    config = GenerationConfig(
-        batch_size=batch_size,
-        allow_lm_batch=bool(payload.get("allow_lm_batch", False)),
-        use_random_seed=bool(payload.get("use_random_seed", True)),
-        seeds=payload.get("seeds"),
-        lm_batch_chunk_size=max(1, int(payload.get("lm_batch_chunk_size", 8))),
-        constrained_decoding_debug=bool(payload.get("constrained_decoding_debug")),
-        audio_format=(payload.get("audio_format") or "flac").strip() or "flac",
-    )
-
-    save_dir = tempfile.mkdtemp(prefix="ace_step_")
-    try:
-        result = generate_music(
-            dit_handler=dit_handler,
-            llm_handler=llm_handler if (llm_handler and getattr(llm_handler, "llm_initialized", False)) else None,
-            params=params,
-            config=config,
-            save_dir=save_dir,
-            progress=None,
-        )
-        if not result.success:
-            raise RuntimeError(result.error or result.status_message or "generate_music failed")
-
-        audios = result.audios or []
-        if not audios:
-            raise RuntimeError("generate_music returned no audio")
-
-        first_path = audios[0].get("path") or ""
-        if not first_path or not os.path.isfile(first_path):
-            raise RuntimeError("first generated audio path missing or not a file")
-
-        shutil.copy2(first_path, dst_path)
-    finally:
-        try:
-            shutil.rmtree(save_dir, ignore_errors=True)
-        except Exception:
-            pass
-
-
-class BackendServicer(backend_pb2_grpc.BackendServicer):
-    def __init__(self):
-        self.model_path = None
-        self.model_dir = None
-        self.checkpoint_dir = None
-        self.project_root = None
-        self.options = {}
-        self.dit_handler = None
-        self.llm_handler = None
-
-    def Health(self, request, context):
-        return backend_pb2.Reply(message=b"OK")
-
-    def LoadModel(self, request, context):
-        try:
-            self.options = _parse_options(list(getattr(request, "Options", []) or []))
-            model_path = getattr(request, "ModelPath", None) or ""
-            model_name = (request.Model or "").strip()
-            model_file = (getattr(request, "ModelFile", None) or "").strip()
-
-            # Model dir: where we store checkpoints (always under LocalAI models path, never backend dir)
-            if model_path and model_name:
-                model_dir = os.path.join(model_path, model_name)
-            elif model_file:
-                model_dir = model_file
-            else:
-                model_dir = os.path.abspath(model_name or ".")
-            self.model_dir = model_dir
-            self.checkpoint_dir = os.path.join(model_dir, "checkpoints")
-            self.project_root = model_dir
-            self.model_path = os.path.join(self.checkpoint_dir, model_name or os.path.basename(model_dir.rstrip("/\\")))
-
-            config_path = model_name or os.path.basename(model_dir.rstrip("/\\"))
-            os.makedirs(self.checkpoint_dir, exist_ok=True)
-
-            self.dit_handler = AceStepHandler()
-            # Patch handler so it uses our model dir instead of site-packages/checkpoints
-            self.dit_handler._get_project_root = lambda: self.project_root
-            device = self.options.get("device", "auto")
-            use_flash = self.options.get("use_flash_attention", True)
-            if isinstance(use_flash, str):
-                use_flash = str(use_flash).lower() in ("1", "true", "yes")
-            offload = self.options.get("offload_to_cpu", False)
-            if isinstance(offload, str):
-                offload = str(offload).lower() in ("1", "true", "yes")
-            status_msg, ok = self.dit_handler.initialize_service(
-                project_root=self.project_root,
-                config_path=config_path,
-                device=device,
-                use_flash_attention=use_flash,
-                compile_model=False,
-                offload_to_cpu=offload,
-                offload_dit_to_cpu=bool(self.options.get("offload_dit_to_cpu", False)),
-            )
-            if not ok:
-                return backend_pb2.Result(success=False, message=f"DiT init failed: {status_msg}")
-
-            self.llm_handler = None
-            if self.options.get("init_lm", True):
-                lm_model = self.options.get("lm_model_path", "acestep-5Hz-lm-0.6B")
-                
-                # Ensure LM model is downloaded before initializing
-                try:
-                    from pathlib import Path
-                    lm_success, lm_msg = ensure_lm_model(
-                        model_name=lm_model,
-                        checkpoints_dir=Path(self.checkpoint_dir),
-                        prefer_source=None,  # Auto-detect HuggingFace vs ModelScope
-                    )
-                    if not lm_success:
-                        print(f"[ace-step] Warning: LM model download failed: {lm_msg}", file=sys.stderr)
-                        # Continue anyway - LLM initialization will fail gracefully
-                    else:
-                        print(f"[ace-step] LM model ready: {lm_msg}", file=sys.stderr)
-                except Exception as e:
-                    print(f"[ace-step] Warning: LM model download check failed: {e}", file=sys.stderr)
-                    # Continue anyway - LLM initialization will fail gracefully
-                
-                self.llm_handler = LLMHandler()
-                lm_backend = (self.options.get("lm_backend") or "vllm").strip().lower()
-                if lm_backend not in ("vllm", "pt"):
-                    lm_backend = "vllm"
-                lm_status, lm_ok = self.llm_handler.initialize(
-                    checkpoint_dir=self.checkpoint_dir,
-                    lm_model_path=lm_model,
-                    backend=lm_backend,
-                    device=device,
-                    offload_to_cpu=offload,
-                    dtype=getattr(self.dit_handler, "dtype", None),
-                )
-                if not lm_ok:
-                    self.llm_handler = None
-                    print(f"[ace-step] LM init failed (optional): {lm_status}", file=sys.stderr)
-
-            print(f"[ace-step] LoadModel: model={self.model_path}, options={list(self.options.keys())}", file=sys.stderr)
-            return backend_pb2.Result(success=True, message="Model loaded successfully")
-        except Exception as err:
-            return backend_pb2.Result(success=False, message=f"LoadModel error: {err}")
-
-    def SoundGeneration(self, request, context):
-        if not request.dst:
-            return backend_pb2.Result(success=False, message="request.dst is required")
-
-        use_simple = bool(request.text)
-        if use_simple:
-            payload = {
-                "sample_query": request.text or "",
-                "sample_mode": True,
-                "thinking": True,
-                "vocal_language": request.language or request.GetLanguage() or "en",
-                "instrumental": request.instrumental if request.HasField("instrumental") else False,
-            }
-        else:
-            caption = request.caption or request.GetCaption() or request.text
-            payload = {
-                "prompt": caption,
-                "lyrics": request.lyrics or request.lyrics or "",
-                "thinking": request.think if request.HasField("think") else False,
-                "vocal_language": request.language or request.GetLanguage() or "en",
-            }
-            if request.HasField("bpm"):
-                payload["bpm"] = request.bpm
-            if request.HasField("keyscale") and request.keyscale:
-                payload["key_scale"] = request.keyscale
-            if request.HasField("timesignature") and request.timesignature:
-                payload["time_signature"] = request.timesignature
-            if request.HasField("duration") and request.duration:
-                payload["audio_duration"] = int(request.duration) if request.duration else None
-            if request.src:
-                payload["src_audio_path"] = request.src
-
-        _generate_audio_sync(self, payload, request.dst)
-        return backend_pb2.Result(success=True, message="Sound generated successfully")
-
-    def TTS(self, request, context):
-        if not request.dst:
-            return backend_pb2.Result(success=False, message="request.dst is required")
-        payload = {
-            "sample_query": request.text,
-            "sample_mode": True,
-            "thinking": False,
-            "vocal_language": (request.language if request.language else "") or "en",
-            "instrumental": False,
-        }
-        _generate_audio_sync(self, payload, request.dst)
-        return backend_pb2.Result(success=True, message="TTS (music fallback) generated successfully")
-
-
-def serve(address):
-    server = grpc.server(
-        futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
-        options=[
-            ("grpc.max_message_length", 50 * 1024 * 1024),
-            ("grpc.max_send_message_length", 50 * 1024 * 1024),
-            ("grpc.max_receive_message_length", 50 * 1024 * 1024),
-        ],
-    )
-    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
-    server.add_insecure_port(address)
-    server.start()
-    print(f"[ace-step] Server listening on {address}", file=sys.stderr)
-
-    def shutdown(sig, frame):
-        server.stop(0)
-        sys.exit(0)
-
-    signal.signal(signal.SIGINT, shutdown)
-    signal.signal(signal.SIGTERM, shutdown)
-
-    try:
-        while True:
-            import time
-            time.sleep(_ONE_DAY_IN_SECONDS)
-    except KeyboardInterrupt:
-        server.stop(0)
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--addr", default="localhost:50051", help="Listen address")
-    args = parser.parse_args()
-    serve(args.addr)

backend/python/ace-step/install.sh

@@ -1,26 +0,0 @@
-#!/bin/bash
-set -e
-
-backend_dir=$(dirname $0)
-if [ -d $backend_dir/common ]; then
-    source $backend_dir/common/libbackend.sh
-else
-    source $backend_dir/../common/libbackend.sh
-fi
-
-PYTHON_VERSION="3.11"
-PYTHON_PATCH="14"
-PY_STANDALONE_TAG="20260203"
-
-installRequirements
-
-if [ ! -d ACE-Step-1.5 ]; then
-    git clone https://github.com/ace-step/ACE-Step-1.5
-    cd ACE-Step-1.5/
-    if [ "x${USE_PIP}" == "xtrue" ]; then
-        pip install ${EXTRA_PIP_INSTALL_FLAGS:-} --no-deps .
-    else
-        uv pip install ${EXTRA_PIP_INSTALL_FLAGS:-} --no-deps .
-    fi
-fi
-

backend/python/ace-step/requirements-cpu.txt

@@ -1,22 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cpu
-torch
-torchaudio
-torchvision
-
-# Core dependencies
-transformers>=4.51.0,<4.58.0
-diffusers
-gradio
-matplotlib>=3.7.5
-scipy>=1.10.1
-soundfile>=0.13.1
-loguru>=0.7.3
-einops>=0.8.1
-accelerate>=1.12.0
-fastapi>=0.110.0
-uvicorn[standard]>=0.27.0
-numba>=0.63.1
-vector-quantize-pytorch>=1.27.15
-torchcodec>=0.9.1
-torchao
-modelscope

backend/python/ace-step/requirements-cublas12.txt

@@ -1,22 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cu128
-torch
-torchaudio
-torchvision
-
-# Core dependencies
-transformers>=4.51.0,<4.58.0
-diffusers
-gradio>=6.5.1
-matplotlib>=3.7.5
-scipy>=1.10.1
-soundfile>=0.13.1
-loguru>=0.7.3
-einops>=0.8.1
-accelerate>=1.12.0
-fastapi>=0.110.0
-uvicorn[standard]>=0.27.0
-numba>=0.63.1
-vector-quantize-pytorch>=1.27.15
-torchcodec>=0.9.1
-torchao
-modelscope

backend/python/ace-step/requirements-cublas13.txt

@@ -1,22 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cu130
-torch
-torchaudio
-torchvision
-
-# Core dependencies
-transformers>=4.51.0,<4.58.0
-diffusers
-gradio>=6.5.1
-matplotlib>=3.7.5
-scipy>=1.10.1
-soundfile>=0.13.1
-loguru>=0.7.3
-einops>=0.8.1
-accelerate>=1.12.0
-fastapi>=0.110.0
-uvicorn[standard]>=0.27.0
-numba>=0.63.1
-vector-quantize-pytorch>=1.27.15
-torchcodec>=0.9.1
-torchao
-modelscope

backend/python/ace-step/requirements-hipblas.txt

@@ -1,22 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/rocm6.4
-torch==2.8.0+rocm6.4
-torchaudio
-torchvision
-
-# Core dependencies
-transformers>=4.51.0,<4.58.0
-diffusers
-gradio>=6.5.1
-matplotlib>=3.7.5
-scipy>=1.10.1
-soundfile>=0.13.1
-loguru>=0.7.3
-einops>=0.8.1
-accelerate>=1.12.0
-fastapi>=0.110.0
-uvicorn[standard]>=0.27.0
-numba>=0.63.1
-vector-quantize-pytorch>=1.27.15
-torchcodec>=0.9.1
-torchao
-modelscope

backend/python/ace-step/requirements-intel.txt

@@ -1,26 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/xpu
-torch
-torchaudio
-torchvision
-
-# Core dependencies
-transformers>=4.51.0,<4.58.0
-diffusers
-gradio
-matplotlib>=3.7.5
-scipy>=1.10.1
-soundfile>=0.13.1
-loguru>=0.7.3
-einops>=0.8.1
-accelerate>=1.12.0
-fastapi>=0.110.0
-uvicorn[standard]>=0.27.0
-numba>=0.63.1
-vector-quantize-pytorch>=1.27.15
-torchcodec>=0.9.1
-torchao
-modelscope
-
-# LoRA Training dependencies (optional)
-peft>=0.7.0
-lightning>=2.0.0

backend/python/ace-step/requirements-l4t13.txt

@@ -1,21 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cu130
-torch
-torchaudio
-torchvision
-# Core dependencies
-transformers>=4.51.0,<4.58.0
-diffusers
-gradio>=6.5.1
-matplotlib>=3.7.5
-scipy>=1.10.1
-soundfile>=0.13.1
-loguru>=0.7.3
-einops>=0.8.1
-accelerate>=1.12.0
-fastapi>=0.110.0
-uvicorn[standard]>=0.27.0
-numba>=0.63.1
-vector-quantize-pytorch>=1.27.15
-torchcodec>=0.9.1
-torchao
-modelscope

backend/python/ace-step/requirements-mps.txt

@@ -1,25 +0,0 @@
-torch
-torchaudio
-torchvision
-
-# Core dependencies
-transformers>=4.51.0,<4.58.0
-diffusers
-gradio
-matplotlib>=3.7.5
-scipy>=1.10.1
-soundfile>=0.13.1
-loguru>=0.7.3
-einops>=0.8.1
-accelerate>=1.12.0
-fastapi>=0.110.0
-uvicorn[standard]>=0.27.0
-numba>=0.63.1
-vector-quantize-pytorch>=1.27.15
-torchcodec>=0.9.1
-torchao
-modelscope
-
-# LoRA Training dependencies (optional)
-peft>=0.7.0
-lightning>=2.0.0

backend/python/ace-step/requirements.txt

@@ -1,4 +0,0 @@
-setuptools
-grpcio==1.76.0
-protobuf
-certifi

backend/python/ace-step/run.sh

@@ -1,9 +0,0 @@
-#!/bin/bash
-backend_dir=$(dirname $0)
-if [ -d $backend_dir/common ]; then
-    source $backend_dir/common/libbackend.sh
-else
-    source $backend_dir/../common/libbackend.sh
-fi
-
-startBackend $@

backend/python/ace-step/test.py

@@ -1,53 +0,0 @@
-"""
-Tests for the ACE-Step gRPC backend.
-"""
-import os
-import tempfile
-import unittest
-
-import backend_pb2
-import backend_pb2_grpc
-import grpc
-
-
-class TestACEStepBackend(unittest.TestCase):
-    """Test Health, LoadModel, and SoundGeneration (minimal; no real model required)."""
-
-    @classmethod
-    def setUpClass(cls):
-        port = os.environ.get("BACKEND_PORT", "50051")
-        cls.channel = grpc.insecure_channel(f"localhost:{port}")
-        cls.stub = backend_pb2_grpc.BackendStub(cls.channel)
-
-    @classmethod
-    def tearDownClass(cls):
-        cls.channel.close()
-
-    def test_health(self):
-        response = self.stub.Health(backend_pb2.HealthMessage())
-        self.assertEqual(response.message, b"OK")
-
-    def test_load_model(self):
-        response = self.stub.LoadModel(backend_pb2.ModelOptions(Model="ace-step-test"))
-        self.assertTrue(response.success, response.message)
-
-    def test_sound_generation_minimal(self):
-        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as f:
-            dst = f.name
-        try:
-            req = backend_pb2.SoundGenerationRequest(
-                text="upbeat pop song",
-                model="ace-step-test",
-                dst=dst,
-            )
-            response = self.stub.SoundGeneration(req)
-            self.assertTrue(response.success, response.message)
-            self.assertTrue(os.path.exists(dst), f"Output file not created: {dst}")
-            self.assertGreater(os.path.getsize(dst), 0)
-        finally:
-            if os.path.exists(dst):
-                os.unlink(dst)
-
-
-if __name__ == "__main__":
-    unittest.main()

backend/python/ace-step/test.sh

@@ -1,19 +0,0 @@
-#!/bin/bash
-set -e
-
-backend_dir=$(dirname $0)
-if [ -d $backend_dir/common ]; then
-    source $backend_dir/common/libbackend.sh
-else
-    source $backend_dir/../common/libbackend.sh
-fi
-
-# Start backend in background (use env to avoid port conflict in parallel tests)
-export PYTHONUNBUFFERED=1
-BACKEND_PORT=${BACKEND_PORT:-50051}
-python backend.py --addr "localhost:${BACKEND_PORT}" &
-BACKEND_PID=$!
-trap "kill $BACKEND_PID 2>/dev/null || true" EXIT
-sleep 3
-export BACKEND_PORT
-runUnittests

backend/python/chatterbox/requirements-mps.txt

@@ -1,7 +0,0 @@
-torch
-torchaudio
-accelerate
-numpy>=1.24.0,<1.26.0
-transformers
-# https://github.com/mudler/LocalAI/pull/6240#issuecomment-3329518289
-chatterbox-tts@git+https://git@github.com/mudler/chatterbox.git@faster

backend/python/coqui/requirements-mps.txt

@@ -1,4 +0,0 @@
-torch==2.7.1
-transformers==4.48.3
-accelerate
-coqui-tts

backend/python/faster-whisper/requirements-mps.txt

@@ -1,8 +0,0 @@
-torch==2.7.1
-faster-whisper
-opencv-python
-accelerate
-compel
-peft
-sentencepiece
-optimum-quanto

backend/python/kitten-tts/requirements-mps.txt

@@ -1,5 +0,0 @@
-grpcio==1.71.0
-protobuf
-certifi
-packaging==24.1
-https://github.com/KittenML/KittenTTS/releases/download/0.1/kittentts-0.1.0-py3-none-any.whl

backend/python/kokoro/requirements-mps.txt

@@ -1,5 +0,0 @@
-torch==2.7.1
-transformers
-accelerate
-kokoro
-soundfile

backend/python/mlx-audio/requirements-cpu.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-audio
-mlx[cpu]

backend/python/mlx-audio/requirements-cublas12.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-audio
-mlx[cuda12]

backend/python/mlx-audio/requirements-cublas13.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-audio
-mlx[cuda13]

backend/python/mlx-audio/requirements-l4t12.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-audio
-mlx[cuda12]

backend/python/mlx-audio/requirements-l4t13.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-audio
-mlx[cuda13]

backend/python/mlx-vlm/requirements-cpu.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-vlm
-mlx[cpu]

backend/python/mlx-vlm/requirements-cublas12.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-vlm
-mlx[cuda12]

backend/python/mlx-vlm/requirements-cublas13.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-vlm
-mlx[cuda13]

backend/python/mlx-vlm/requirements-l4t12.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-vlm
-mlx[cuda12]

backend/python/mlx-vlm/requirements-l4t13.txt

@@ -1,2 +0,0 @@
-git+https://github.com/Blaizzy/mlx-vlm
-mlx[cuda13]

backend/python/mlx/requirements-cpu.txt

@@ -1,2 +0,0 @@
-mlx-lm
-mlx[cpu]

backend/python/mlx/requirements-cublas12.txt

@@ -1,2 +0,0 @@
-mlx-lm
-mlx[cuda12]

backend/python/mlx/requirements-cublas13.txt

@@ -1,2 +0,0 @@
-mlx-lm
-mlx[cuda13]

backend/python/mlx/requirements-l4t12.txt

@@ -1,2 +0,0 @@
-mlx-lm
-mlx[cuda12]

backend/python/mlx/requirements-l4t13.txt

@@ -1,2 +0,0 @@
-mlx-lm
-mlx[cuda13]

backend/python/moonshine/requirements-mps.txt

@@ -1,4 +0,0 @@
-grpcio==1.71.0
-protobuf
-grpcio-tools
-useful-moonshine-onnx@git+https://git@github.com/moonshine-ai/moonshine.git#subdirectory=moonshine-onnx

backend/python/nemo/Makefile

@@ -1,23 +0,0 @@
-.PHONY: nemo-asr
-nemo-asr:
-	bash install.sh
-
-.PHONY: run
-run: nemo-asr
-	@echo "Running nemo-asr..."
-	bash run.sh
-	@echo "nemo-asr run."
-
-.PHONY: test
-test: nemo-asr
-	@echo "Testing nemo-asr..."
-	bash test.sh
-	@echo "nemo-asr tested."
-
-.PHONY: protogen-clean
-protogen-clean:
-	$(RM) backend_pb2_grpc.py backend_pb2.py
-
-.PHONY: clean
-clean: protogen-clean
-	rm -rf venv __pycache__

backend/python/nemo/backend.py

@@ -1,147 +0,0 @@
-#!/usr/bin/env python3
-"""
-gRPC server of LocalAI for NVIDIA NEMO Toolkit ASR.
-"""
-from concurrent import futures
-import time
-import argparse
-import signal
-import sys
-import os
-import backend_pb2
-import backend_pb2_grpc
-import torch
-import nemo.collections.asr as nemo_asr
-
-import grpc
-
-
-def is_float(s):
-    try:
-        float(s)
-        return True
-    except ValueError:
-        return False
-
-
-def is_int(s):
-    try:
-        int(s)
-        return True
-    except ValueError:
-        return False
-
-
-_ONE_DAY_IN_SECONDS = 60 * 60 * 24
-MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
-
-
-class BackendServicer(backend_pb2_grpc.BackendServicer):
-    def Health(self, request, context):
-        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
-
-    def LoadModel(self, request, context):
-        if torch.cuda.is_available():
-            device = "cuda"
-        else:
-            device = "cpu"
-        mps_available = hasattr(torch.backends, "mps") and torch.backends.mps.is_available()
-        if mps_available:
-            device = "mps"
-        if not torch.cuda.is_available() and request.CUDA:
-            return backend_pb2.Result(success=False, message="CUDA is not available")
-
-        self.device = device
-        self.options = {}
-
-        for opt in request.Options:
-            if ":" not in opt:
-                continue
-            key, value = opt.split(":", 1)
-            if is_float(value):
-                value = float(value)
-            elif is_int(value):
-                value = int(value)
-            elif value.lower() in ["true", "false"]:
-                value = value.lower() == "true"
-            self.options[key] = value
-
-        model_name = request.Model or "nvidia/parakeet-tdt-0.6b-v3"
-
-        try:
-            print(f"Loading NEMO ASR model from {model_name}", file=sys.stderr)
-            self.model = nemo_asr.models.ASRModel.from_pretrained(model_name=model_name)
-            print("NEMO ASR model loaded successfully", file=sys.stderr)
-        except Exception as err:
-            print(f"[ERROR] LoadModel failed: {err}", file=sys.stderr)
-            import traceback
-            traceback.print_exc(file=sys.stderr)
-            return backend_pb2.Result(success=False, message=str(err))
-
-        return backend_pb2.Result(message="Model loaded successfully", success=True)
-
-    def AudioTranscription(self, request, context):
-        result_segments = []
-        text = ""
-        try:
-            audio_path = request.dst
-            if not audio_path or not os.path.exists(audio_path):
-                print(f"Error: Audio file not found: {audio_path}", file=sys.stderr)
-                return backend_pb2.TranscriptResult(segments=[], text="")
-
-            # NEMO's transcribe method accepts a list of audio paths and returns a list of transcripts
-            results = self.model.transcribe([audio_path])
-
-            if not results or len(results) == 0:
-                return backend_pb2.TranscriptResult(segments=[], text="")
-
-            # Get the transcript text from the first result
-            text = results[0]
-            if text:
-                # Create a single segment with the full transcription
-                result_segments.append(backend_pb2.TranscriptSegment(
-                    id=0, start=0, end=0, text=text
-                ))
-
-        except Exception as err:
-            print(f"Error in AudioTranscription: {err}", file=sys.stderr)
-            import traceback
-            traceback.print_exc(file=sys.stderr)
-            return backend_pb2.TranscriptResult(segments=[], text="")
-
-        return backend_pb2.TranscriptResult(segments=result_segments, text=text)
-
-
-def serve(address):
-    server = grpc.server(
-        futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
-        options=[
-            ('grpc.max_message_length', 50 * 1024 * 1024),
-            ('grpc.max_send_message_length', 50 * 1024 * 1024),
-            ('grpc.max_receive_message_length', 50 * 1024 * 1024),
-        ])
-    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
-    server.add_insecure_port(address)
-    server.start()
-    print("Server started. Listening on: " + address, file=sys.stderr)
-
-    def signal_handler(sig, frame):
-        print("Received termination signal. Shutting down...")
-        server.stop(0)
-        sys.exit(0)
-
-    signal.signal(signal.SIGINT, signal_handler)
-    signal.signal(signal.SIGTERM, signal_handler)
-
-    try:
-        while True:
-            time.sleep(_ONE_DAY_IN_SECONDS)
-    except KeyboardInterrupt:
-        server.stop(0)
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Run the gRPC server.")
-    parser.add_argument("--addr", default="localhost:50051", help="The address to bind the server to.")
-    args = parser.parse_args()
-    serve(args.addr)

backend/python/nemo/install.sh

@@ -1,17 +0,0 @@
-#!/bin/bash
-set -e
-
-EXTRA_PIP_INSTALL_FLAGS="--no-build-isolation"
-
-backend_dir=$(dirname $0)
-if [ -d $backend_dir/common ]; then
-    source $backend_dir/common/libbackend.sh
-else
-    source $backend_dir/../common/libbackend.sh
-fi
-
-if [ "x${BUILD_PROFILE}" == "xintel" ]; then
-    EXTRA_PIP_INSTALL_FLAGS+=" --upgrade --index-strategy=unsafe-first-match"
-fi
-
-installRequirements

backend/python/nemo/protogen.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-set -e
-
-backend_dir=$(dirname $0)
-if [ -d $backend_dir/common ]; then
-    source $backend_dir/common/libbackend.sh
-else
-    source $backend_dir/../common/libbackend.sh
-fi
-
-python3 -m grpc_tools.protoc -I../.. -I./ --python_out=. --grpc_python_out=. backend.proto

backend/python/nemo/requirements-cpu.txt

@@ -1,3 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cpu
-torch
-nemo_toolkit[asr]

backend/python/nemo/requirements-cublas12.txt

@@ -1,3 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cu128
-torch
-nemo_toolkit[asr]

backend/python/nemo/requirements-cublas13.txt

@@ -1,3 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cu130
-torch
-nemo_toolkit[asr]

backend/python/nemo/requirements-hipblas.txt

@@ -1,3 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/rocm6.3
-torch
-nemo_toolkit[asr]

backend/python/nemo/requirements-intel.txt

@@ -1,3 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/xpu
-torch
-nemo_toolkit[asr]

backend/python/nemo/requirements-l4t12.txt

@@ -1,3 +0,0 @@
---extra-index-url https://pypi.jetson-ai-lab.io/jp6/cu129/
-torch
-nemo_toolkit[asr]

backend/python/nemo/requirements-l4t13.txt

@@ -1,3 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cu130
-torch
-nemo_toolkit[asr]

backend/python/nemo/requirements-mps.txt

@@ -1,2 +0,0 @@
-torch
-nemo_toolkit[asr]

backend/python/nemo/requirements.txt

@@ -1,6 +0,0 @@
-grpcio==1.71.0
-protobuf
-certifi
-packaging==24.1
-setuptools
-pyarrow==20.0.0

backend/python/nemo/run.sh

@@ -1,9 +0,0 @@
-#!/bin/bash
-backend_dir=$(dirname $0)
-if [ -d $backend_dir/common ]; then
-    source $backend_dir/common/libbackend.sh
-else
-    source $backend_dir/../common/libbackend.sh
-fi
-
-startBackend $@

backend/python/nemo/test.py

@@ -1,99 +0,0 @@
-"""
-Tests for the NEMO Toolkit ASR gRPC backend.
-"""
-import unittest
-import subprocess
-import time
-import os
-import tempfile
-import shutil
-import backend_pb2
-import backend_pb2_grpc
-
-import grpc
-
-# Skip heavy transcription test in CI (model download + inference)
-SKIP_ASR_TESTS = os.environ.get("SKIP_ASR_TESTS", "false").lower() == "true"
-
-
-class TestBackendServicer(unittest.TestCase):
-    def setUp(self):
-        self.service = subprocess.Popen(["python3", "backend.py", "--addr", "localhost:50051"])
-        time.sleep(15)
-
-    def tearDown(self):
-        self.service.terminate()
-        self.service.wait()
-
-    def test_server_startup(self):
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.Health(backend_pb2.HealthMessage())
-                self.assertEqual(response.message, b'OK')
-        except Exception as err:
-            print(err)
-            self.fail("Server failed to start")
-        finally:
-            self.tearDown()
-
-    def test_load_model(self):
-        try:
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                response = stub.LoadModel(backend_pb2.ModelOptions(Model="nvidia/parakeet-tdt-0.6b-v3"))
-                self.assertTrue(response.success, response.message)
-                self.assertEqual(response.message, "Model loaded successfully")
-        except Exception as err:
-            print(err)
-            self.fail("LoadModel service failed")
-        finally:
-            self.tearDown()
-
-    @unittest.skipIf(SKIP_ASR_TESTS, "ASR transcription test skipped (SKIP_ASR_TESTS=true)")
-    def test_audio_transcription(self):
-        temp_dir = tempfile.mkdtemp()
-        audio_file = os.path.join(temp_dir, 'audio.wav')
-        try:
-            # Download a sample audio file for testing
-            url = "https://audio-samples.github.io/samples/mp3/crowd-cheering-and-applause-sound-effect.mp3"
-            result = subprocess.run(
-                ["wget", "-q", url, "-O", audio_file],
-                capture_output=True,
-                text=True,
-                timeout=30,
-            )
-            if result.returncode != 0:
-                self.skipTest(f"Could not download sample audio: {result.stderr}")
-            if not os.path.exists(audio_file):
-                self.skipTest("Sample audio file not found after download")
-
-            self.setUp()
-            with grpc.insecure_channel("localhost:50051") as channel:
-                stub = backend_pb2_grpc.BackendStub(channel)
-                load_response = stub.LoadModel(backend_pb2.ModelOptions(Model="nvidia/parakeet-tdt-0.6b-v3"))
-                self.assertTrue(load_response.success, load_response.message)
-
-                transcript_response = stub.AudioTranscription(
-                    backend_pb2.TranscriptRequest(dst=audio_file)
-                )
-                self.assertIsNotNone(transcript_response)
-                self.assertIsNotNone(transcript_response.text)
-                self.assertGreaterEqual(len(transcript_response.segments), 0)
-                all_text = ""
-                for segment in transcript_response.segments:
-                    all_text += segment.text
-                print(f"Transcription result: {all_text}")
-                self.assertIn("big", all_text)
-                if transcript_response.segments:
-                    self.assertIsNotNone(transcript_response.segments[0].text)
-        finally:
-            self.tearDown()
-            if os.path.exists(temp_dir):
-                shutil.rmtree(temp_dir)
-
-
-if __name__ == '__main__':
-    unittest.main()

backend/python/nemo/test.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-set -e
-
-backend_dir=$(dirname $0)
-if [ -d $backend_dir/common ]; then
-    source $backend_dir/common/libbackend.sh
-else
-    source $backend_dir/../common/libbackend.sh
-fi
-
-runUnittests

backend/python/outetts/Makefile

@@ -1,23 +0,0 @@
-.PHONY: outetts
-outetts:
-	bash install.sh
-
-.PHONY: run
-run: outetts
-	@echo "Running outetts..."
-	bash run.sh
-	@echo "outetts run."
-
-.PHONY: test
-test: outetts
-	@echo "Testing outetts..."
-	bash test.sh
-	@echo "outetts tested."
-
-.PHONY: protogen-clean
-protogen-clean:
-	$(RM) backend_pb2_grpc.py backend_pb2.py
-
-.PHONY: clean
-clean: protogen-clean
-	rm -rf venv __pycache__

backend/python/outetts/backend.py

@@ -1,138 +0,0 @@
-#!/usr/bin/env python3
-"""
-gRPC server for OuteTTS (OuteAI TTS) models.
-"""
-from concurrent import futures
-
-import argparse
-import signal
-import sys
-import os
-import asyncio
-
-import backend_pb2
-import backend_pb2_grpc
-
-import grpc
-import outetts
-
-_ONE_DAY_IN_SECONDS = 60 * 60 * 24
-
-MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
-
-
-class BackendServicer(backend_pb2_grpc.BackendServicer):
-    def Health(self, request, context):
-        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
-
-    def LoadModel(self, request, context):
-        model_name = request.Model
-        if os.path.exists(request.ModelFile):
-            model_name = request.ModelFile
-
-        self.options = {}
-        for opt in request.Options:
-            if ":" not in opt:
-                continue
-            key, value = opt.split(":", 1)
-            try:
-                if "." in value:
-                    value = float(value)
-                else:
-                    value = int(value)
-            except ValueError:
-                pass
-            self.options[key] = value
-
-        MODELNAME = "OuteAI/OuteTTS-0.3-1B"
-        TOKENIZER = "OuteAI/OuteTTS-0.3-1B"
-        VERSION = "0.3"
-        SPEAKER = "en_male_1"
-        for opt in request.Options:
-            if opt.startswith("tokenizer:"):
-                TOKENIZER = opt.split(":")[1]
-                break
-            if opt.startswith("version:"):
-                VERSION = opt.split(":")[1]
-                break
-            if opt.startswith("speaker:"):
-                SPEAKER = opt.split(":")[1]
-                break
-
-        if model_name != "":
-            MODELNAME = model_name
-
-        try:
-            model_config = outetts.HFModelConfig_v2(
-                model_path=MODELNAME,
-                tokenizer_path=TOKENIZER
-            )
-            self.interface = outetts.InterfaceHF(model_version=VERSION, cfg=model_config)
-
-            self.interface.print_default_speakers()
-            if request.AudioPath:
-                if os.path.isabs(request.AudioPath):
-                    self.AudioPath = request.AudioPath
-                else:
-                    self.AudioPath = os.path.join(request.ModelPath, request.AudioPath)
-                self.speaker = self.interface.create_speaker(audio_path=self.AudioPath)
-            else:
-                self.speaker = self.interface.load_default_speaker(name=SPEAKER)
-
-            if request.ContextSize > 0:
-                self.max_tokens = request.ContextSize
-            else:
-                self.max_tokens = self.options.get("max_new_tokens", 512)
-
-        except Exception as err:
-            print("Error:", err, file=sys.stderr)
-            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
-        return backend_pb2.Result(message="Model loaded successfully", success=True)
-
-    def TTS(self, request, context):
-        try:
-            text = request.text if request.text else "Speech synthesis is the artificial production of human speech."
-            print("[OuteTTS] generating TTS", file=sys.stderr)
-            gen_cfg = outetts.GenerationConfig(
-                text=text,
-                temperature=self.options.get("temperature", 0.1),
-                repetition_penalty=self.options.get("repetition_penalty", 1.1),
-                max_length=self.max_tokens,
-                speaker=self.speaker,
-            )
-            output = self.interface.generate(config=gen_cfg)
-            print("[OuteTTS] Generated TTS", file=sys.stderr)
-            output.save(request.dst)
-            print("[OuteTTS] TTS done", file=sys.stderr)
-        except Exception as err:
-            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
-        return backend_pb2.Result(success=True)
-
-
-async def serve(address):
-    server = grpc.aio.server(
-        migration_thread_pool=futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
-        options=[
-            ('grpc.max_message_length', 50 * 1024 * 1024),
-            ('grpc.max_send_message_length', 50 * 1024 * 1024),
-            ('grpc.max_receive_message_length', 50 * 1024 * 1024),
-        ])
-    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
-    server.add_insecure_port(address)
-
-    loop = asyncio.get_event_loop()
-    for sig in (signal.SIGINT, signal.SIGTERM):
-        loop.add_signal_handler(
-            sig, lambda: asyncio.ensure_future(server.stop(5))
-        )
-
-    await server.start()
-    print("Server started. Listening on: " + address, file=sys.stderr)
-    await server.wait_for_termination()
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Run the OuteTTS gRPC server.")
-    parser.add_argument("--addr", default="localhost:50051", help="The address to bind the server to.")
-    args = parser.parse_args()
-    asyncio.run(serve(args.addr))

backend/python/outetts/install.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-set -e
-
-backend_dir=$(dirname $0)
-if [ -d $backend_dir/common ]; then
-    source $backend_dir/common/libbackend.sh
-else
-    source $backend_dir/../common/libbackend.sh
-fi
-
-installRequirements

backend/python/outetts/requirements-cpu.txt

@@ -1,7 +0,0 @@
-torch==2.7.1
-llvmlite==0.43.0
-numba==0.60.0
-accelerate
-bitsandbytes
-outetts
-protobuf==6.33.5

backend/python/outetts/requirements-cublas12.txt

@@ -1,7 +0,0 @@
-torch==2.7.1
-accelerate
-llvmlite==0.43.0
-numba==0.60.0
-bitsandbytes
-protobuf==6.33.5
-outetts

backend/python/outetts/requirements-cublas13.txt

@@ -1,7 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cu130
-torch==2.9.0
-llvmlite==0.43.0
-numba==0.60.0
-bitsandbytes
-outetts
-protobuf==6.33.5

backend/python/outetts/requirements-hipblas.txt

@@ -1,8 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/rocm6.4
-torch==2.8.0+rocm6.4
-accelerate
-llvmlite==0.43.0
-numba==0.60.0
-bitsandbytes
-outetts
-protobuf==6.33.5