chore(model gallery): 🤖 add 1 new models via gallery agent (#10505)

chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

.github/backend-matrix.yml

@@ -4974,6 +4974,12 @@ includeDarwin:
   - backend: "kitten-tts"
     tag-suffix: "-metal-darwin-arm64-kitten-tts"
     build-type: "mps"
+  - backend: "trl"
+    tag-suffix: "-metal-darwin-arm64-trl"
+    build-type: "mps"
+  - backend: "liquid-audio"
+    tag-suffix: "-metal-darwin-arm64-liquid-audio"
+    build-type: "mps"
   - backend: "piper"
     tag-suffix: "-metal-darwin-arm64-piper"
     build-type: "metal"
@@ -4990,6 +4996,10 @@ includeDarwin:
     tag-suffix: "-metal-darwin-arm64-sherpa-onnx"
     build-type: "metal"
     lang: "go"
+  - backend: "supertonic"
+    tag-suffix: "-metal-darwin-arm64-supertonic"
+    build-type: "metal"
+    lang: "go"
   - backend: "local-store"
     tag-suffix: "-metal-darwin-arm64-local-store"
     build-type: "metal"

.github/workflows/backend.yml

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

.github/workflows/backend_build.yml

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

.github/workflows/backend_build_darwin.yml

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

.github/workflows/backend_merge.yml

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

.github/workflows/backend_pr.yml

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

.github/workflows/base-images.yml

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

.github/workflows/build-test.yaml

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

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

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

.github/workflows/bump_deps.yaml

@@ -92,7 +92,7 @@ jobs:
             file: "backend/go/vibevoice-cpp/Makefile"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
       - name: Bump dependencies 🔧
         id: bump
         run: |
@@ -128,7 +128,7 @@ jobs:
     if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
       - name: Bump vLLM cu130 wheel pin 🔧
         id: bump
         run: |

.github/workflows/bump_docs.yaml

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

.github/workflows/checksum_checker.yaml

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

.github/workflows/deploy-explorer.yaml

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

.github/workflows/gallery-agent.yaml

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

.github/workflows/generate_intel_image.yaml

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

.github/workflows/gh-pages.yml

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

.github/workflows/image_build.yml

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

.github/workflows/image_merge.yml

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

.github/workflows/lint.yml

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

.github/workflows/release.yaml

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

.github/workflows/secscan.yaml

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

.github/workflows/test-extra.yml

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

.github/workflows/test.yml

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

.github/workflows/tests-aio.yml

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

.github/workflows/tests-e2e.yml

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

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

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

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

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

.github/workflows/update_swagger.yaml

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

.gitignore

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

Makefile

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

backend/cpp/ik-llama-cpp/Makefile

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

backend/cpp/llama-cpp/Makefile

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

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

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

backend/go/acestep-cpp/Makefile

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

backend/go/acestep-cpp/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,8 +23,12 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("ACESTEP_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libgoacestepcpp-fallback.dylib"
+		} else {
 			libName = "./libgoacestepcpp-fallback.so"
 		}
+	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/acestep-cpp/package.sh

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

backend/go/acestep-cpp/run.sh

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

backend/go/ced/Makefile

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

backend/go/ced/main.go

@@ -12,6 +12,7 @@ import (
 	"flag"
 	"fmt"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -27,8 +28,12 @@ type libFunc struct {
 func main() {
 	libName := os.Getenv("CED_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "libced.dylib"
+		} else {
 			libName = "libced.so"
 		}
+	}
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {
 		panic(fmt.Errorf("ced: dlopen %q: %w", libName, err))

backend/go/ced/package.sh

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

backend/go/ced/run.sh

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

backend/go/crispasr/Makefile

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

backend/go/crispasr/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,8 +22,12 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("CRISPASR_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libgocrispasr-fallback.dylib"
+		} else {
 			libName = "./libgocrispasr-fallback.so"
 		}
+	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/crispasr/package.sh

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

backend/go/crispasr/run.sh

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

backend/go/depth-anything-cpp/Makefile

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

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

@@ -9,6 +9,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -27,8 +28,12 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("DEPTHANYTHING_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libdepthanythingcpp-fallback.dylib"
+		} else {
 			libName = "./libdepthanythingcpp-fallback.so"
 		}
+	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

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

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

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

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

backend/go/localvqe/Makefile

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

backend/go/localvqe/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,8 +22,12 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("LOCALVQE_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./liblocalvqe.dylib"
+		} else {
 			libName = "./liblocalvqe.so"
 		}
+	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/localvqe/package.sh

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

backend/go/localvqe/run.sh

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

backend/go/locate-anything-cpp/Makefile

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

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

@@ -9,6 +9,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -27,8 +28,12 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("LOCATEANYTHING_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./liblocateanythingcpp-fallback.dylib"
+		} else {
 			libName = "./liblocateanythingcpp-fallback.so"
 		}
+	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

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

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

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

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

backend/go/omnivoice-cpp/Makefile

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

backend/go/omnivoice-cpp/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,8 +22,12 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("OMNIVOICE_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libgomnivoicecpp-fallback.dylib"
+		} else {
 			libName = "./libgomnivoicecpp-fallback.so"
 		}
+	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/omnivoice-cpp/package.sh

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

backend/go/omnivoice-cpp/run.sh

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

backend/go/parakeet-cpp/Makefile

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

backend/go/parakeet-cpp/main.go

@@ -2,15 +2,17 @@ package main
 
 // Started internally by LocalAI - one gRPC server per loaded model.
 //
-// Loads libparakeet.so via purego and registers the flat C-API entry
+// Loads the parakeet shared library via purego and registers the flat
-// points declared in parakeet_capi.h. The library name can be overridden
+// C-API entry points declared in parakeet_capi.h. The library name can be
-// with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY / VIBEVOICECPP_LIBRARY
+// overridden with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY /
-// convention in the sibling backends); the default looks for the .so next
+// VIBEVOICECPP_LIBRARY convention in the sibling backends); the default
-// to this binary.
+// looks next to this binary for libparakeet.so on Linux and
+// libparakeet.dylib on macOS.
 import (
 	"flag"
 	"fmt"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,8 +30,12 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("PARAKEET_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "libparakeet.dylib"
+		} else {
 			libName = "libparakeet.so"
 		}
+	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/parakeet-cpp/package.sh

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

backend/go/parakeet-cpp/run.sh

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

backend/go/qwen3-tts-cpp/Makefile

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

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

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,8 +22,12 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("QWEN3TTS_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libgoqwen3ttscpp-fallback.dylib"
+		} else {
 			libName = "./libgoqwen3ttscpp-fallback.so"
 		}
+	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

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

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

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

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

backend/go/rfdetr-cpp/Makefile

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

backend/go/rfdetr-cpp/main.go

@@ -9,6 +9,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -27,8 +28,12 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("RFDETR_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./librfdetrcpp-fallback.dylib"
+		} else {
 			libName = "./librfdetrcpp-fallback.so"
 		}
+	}
 
 	rfdetrLib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/rfdetr-cpp/package.sh

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

backend/go/rfdetr-cpp/run.sh

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

backend/go/sam3-cpp/Makefile

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

backend/go/sam3-cpp/main.go

@@ -3,6 +3,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,8 +22,12 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("SAM3_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libgosam3-fallback.dylib"
+		} else {
 			libName = "./libgosam3-fallback.so"
 		}
+	}
 
 	gosamLib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/sam3-cpp/package.sh

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

backend/go/sam3-cpp/run.sh

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

backend/go/sherpa-onnx/backend.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"runtime"
 	"strconv"
 	"strings"
 	"sync"
@@ -238,12 +239,20 @@ func loadSherpaLibs() error {
 func loadSherpaLibsOnce() error {
 	shimLib := os.Getenv("SHERPA_SHIM_LIBRARY")
 	if shimLib == "" {
+		if runtime.GOOS == "darwin" {
+			shimLib = "libsherpa-shim.dylib"
+		} else {
 			shimLib = "libsherpa-shim.so"
 		}
+	}
 	capiLib := os.Getenv("SHERPA_ONNX_LIBRARY")
 	if capiLib == "" {
+		if runtime.GOOS == "darwin" {
+			capiLib = "libsherpa-onnx-c-api.dylib"
+		} else {
 			capiLib = "libsherpa-onnx-c-api.so"
 		}
+	}
 
 	shim, err := purego.Dlopen(shimLib, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/sherpa-onnx/run.sh

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

backend/go/stablediffusion-ggml/Makefile

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

backend/go/stablediffusion-ggml/main.go

@@ -3,6 +3,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,8 +22,12 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("SD_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libgosd-fallback.dylib"
+		} else {
 			libName = "./libgosd-fallback.so"
 		}
+	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/stablediffusion-ggml/package.sh

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

backend/go/stablediffusion-ggml/run.sh

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

backend/go/supertonic/helper.go

@@ -16,6 +16,7 @@ import (
 	"os"
 	"path/filepath"
 	"regexp"
+	"runtime"
 	"strings"
 	"time"
 	"unicode"
@@ -943,9 +944,15 @@ func InitializeONNXRuntime() error {
 			}
 		}
 		if libPath == "" {
+			// LocalAI: default to the platform-native shared library
+			// extension when nothing else is found (dyld vs ld.so).
+			if runtime.GOOS == "darwin" {
+				libPath = "/usr/local/lib/libonnxruntime.dylib"
+			} else {
 				libPath = "/usr/local/lib/libonnxruntime.so"
 			}
 		}
+	}
 	ort.SetSharedLibraryPath(libPath)
 
 	if err := ort.InitializeEnvironment(); err != nil {

backend/go/supertonic/package.sh

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

backend/go/supertonic/run.sh

@@ -3,6 +3,12 @@ set -ex
 
 CURDIR=$(dirname "$(realpath $0)")
 
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS uses dyld: there is no ld.so loader, and the search path env
+	# var is DYLD_LIBRARY_PATH. ONNX Runtime ships as a .dylib here.
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+	export ONNXRUNTIME_LIB_PATH=$CURDIR/lib/libonnxruntime.dylib
+else
 	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 	export ONNXRUNTIME_LIB_PATH=$CURDIR/lib/libonnxruntime.so
 
@@ -10,5 +16,6 @@ if [ -f $CURDIR/lib/ld.so ]; then
 		echo "Using lib/ld.so"
 		exec $CURDIR/lib/ld.so $CURDIR/supertonic "$@"
 	fi
+fi
 
 exec $CURDIR/supertonic "$@"

backend/go/vibevoice-cpp/Makefile

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

backend/go/vibevoice-cpp/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,8 +22,12 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("VIBEVOICECPP_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libgovibevoicecpp-fallback.dylib"
+		} else {
 			libName = "./libgovibevoicecpp-fallback.so"
 		}
+	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/vibevoice-cpp/package.sh

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

backend/go/vibevoice-cpp/run.sh

@@ -11,9 +11,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/libgovibevoicecpp-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
 	LIBRARY="$CURDIR/libgovibevoicecpp-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgovibevoicecpp-avx.so ]; then
@@ -34,9 +38,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libgovibevoicecpp-avx512.so"
 		fi
 	fi
-fi
 
 	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+fi
+
 export VIBEVOICECPP_LIBRARY=$LIBRARY
 
 if [ -f $CURDIR/lib/ld.so ]; then

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?=5ed76e9a079962f1c85cfce44edd325c27ef1f97
+WHISPER_CPP_VERSION?=43d78af5be58f41d6ffbc227d608f104577741ea
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -117,6 +117,7 @@ libgowhisper-custom: CMakeLists.txt cpp/gowhisper.cpp cpp/gowhisper.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgowhisper.so ./$(SO_TARGET)
+	mv build-$(SO_TARGET)/libgowhisper.so ./$(SO_TARGET) 2>/dev/null || \
+		mv build-$(SO_TARGET)/libgowhisper.dylib ./$(SO_TARGET:.so=.dylib)
 
 all: whisper package

backend/go/whisper/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,8 +23,12 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("WHISPER_LIBRARY")
 	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libgowhisper-fallback.dylib"
+		} else {
 			libName = "./libgowhisper-fallback.so"
 		}
+	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/whisper/package.sh

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

backend/go/whisper/run.sh

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

backend/index.yaml

@@ -1284,6 +1284,7 @@
     nvidia-cuda-13: "cuda13-liquid-audio"
     nvidia-cuda-12: "cuda12-liquid-audio"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-liquid-audio"
+    metal: "metal-liquid-audio"
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/61b8e2ba285851687028d395/7_6D7rWrLxp2hb6OHSV1p.png
 - &qwen-tts
   urls:
@@ -1569,6 +1570,7 @@
     - TTS
   capabilities:
     default: "cpu-supertonic"
+    metal: "metal-supertonic"
 - !!merge <<: *neutts
   name: "neutts-development"
   capabilities:
@@ -4612,6 +4614,7 @@
     nvidia-cuda-13: "cuda13-liquid-audio-development"
     nvidia-cuda-12: "cuda12-liquid-audio-development"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-liquid-audio-development"
+    metal: "metal-liquid-audio-development"
 - !!merge <<: *liquid-audio
   name: "cpu-liquid-audio"
   uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-liquid-audio"
@@ -4622,6 +4625,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-liquid-audio"
   mirrors:
     - localai/localai-backends:master-cpu-liquid-audio
+- !!merge <<: *liquid-audio
+  name: "metal-liquid-audio"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-liquid-audio"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-liquid-audio
+- !!merge <<: *liquid-audio
+  name: "metal-liquid-audio-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-liquid-audio"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-liquid-audio
 - !!merge <<: *liquid-audio
   name: "cuda12-liquid-audio"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-liquid-audio"
@@ -5282,6 +5295,7 @@
     nvidia: "cuda12-trl"
     nvidia-cuda-12: "cuda12-trl"
     nvidia-cuda-13: "cuda13-trl"
+    metal: "metal-trl"
 ## TRL backend images
 - !!merge <<: *trl
   name: "cpu-trl"
@@ -5313,6 +5327,16 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-trl"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-trl
+- !!merge <<: *trl
+  name: "metal-trl"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-trl"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-trl
+- !!merge <<: *trl
+  name: "metal-trl-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-trl"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-trl
 ## llama.cpp quantization backend
 - &llama-cpp-quantization
   name: "llama-cpp-quantization"
@@ -5484,6 +5508,7 @@
   name: "supertonic-development"
   capabilities:
     default: "cpu-supertonic-development"
+    metal: "metal-supertonic-development"
 - !!merge <<: *supertonic
   name: "cpu-supertonic"
   uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-supertonic"
@@ -5494,3 +5519,13 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-supertonic"
   mirrors:
     - localai/localai-backends:master-cpu-supertonic
+- !!merge <<: *supertonic
+  name: "metal-supertonic"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-supertonic"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-supertonic
+- !!merge <<: *supertonic
+  name: "metal-supertonic-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-supertonic"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-supertonic

backend/python/diffusers/requirements-cpu.txt

@@ -1,7 +1,7 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 torchvision==0.22.1
 accelerate
 git+https://github.com/xhinker/sd_embed
@@ -10,9 +10,15 @@ sentencepiece
 torch==2.7.1
 optimum-quanto
 ftfy
-# TODO: re-add compel once it supports transformers >= 5.
+# diffusers and transformers are pinned together on purpose. transformers v5
-# Tracking: https://github.com/damian0815/compel/pull/129
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
-#           https://github.com/damian0815/compel/issues/128
+# breaks single-file Stable Diffusion loading on every released diffusers
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
+# main via git froze whichever broken pair existed at image-build time. Pin the
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-cublas12.txt

@@ -1,7 +1,7 @@
 --extra-index-url https://download.pytorch.org/whl/cu121
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 torchvision
 accelerate
 git+https://github.com/xhinker/sd_embed
@@ -10,9 +10,15 @@ sentencepiece
 torch
 ftfy
 optimum-quanto
-# TODO: re-add compel once it supports transformers >= 5.
+# diffusers and transformers are pinned together on purpose. transformers v5
-# Tracking: https://github.com/damian0815/compel/pull/129
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
-#           https://github.com/damian0815/compel/issues/128
+# breaks single-file Stable Diffusion loading on every released diffusers
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
+# main via git froze whichever broken pair existed at image-build time. Pin the
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-cublas13.txt

@@ -1,7 +1,7 @@
 --extra-index-url https://download.pytorch.org/whl/cu130
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 torchvision
 accelerate
 git+https://github.com/xhinker/sd_embed
@@ -10,9 +10,15 @@ sentencepiece
 torch
 ftfy
 optimum-quanto
-# TODO: re-add compel once it supports transformers >= 5.
+# diffusers and transformers are pinned together on purpose. transformers v5
-# Tracking: https://github.com/damian0815/compel/pull/129
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
-#           https://github.com/damian0815/compel/issues/128
+# breaks single-file Stable Diffusion loading on every released diffusers
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
+# main via git froze whichever broken pair existed at image-build time. Pin the
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-hipblas.txt

@@ -1,17 +1,23 @@
 --extra-index-url https://download.pytorch.org/whl/rocm7.0
 torch==2.10.0+rocm7.0
 torchvision==0.25.0+rocm7.0
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 accelerate
 peft
 sentencepiece
 optimum-quanto
 ftfy
-# TODO: re-add compel once it supports transformers >= 5.
+# diffusers and transformers are pinned together on purpose. transformers v5
-# Tracking: https://github.com/damian0815/compel/pull/129
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
-#           https://github.com/damian0815/compel/issues/128
+# breaks single-file Stable Diffusion loading on every released diffusers
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
+# main via git froze whichever broken pair existed at image-build time. Pin the
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-intel.txt

@@ -3,18 +3,24 @@ torch
 torchvision
 optimum[openvino]
 setuptools
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 accelerate
 git+https://github.com/xhinker/sd_embed
 peft
 sentencepiece
 optimum-quanto
 ftfy
-# TODO: re-add compel once it supports transformers >= 5.
+# diffusers and transformers are pinned together on purpose. transformers v5
-# Tracking: https://github.com/damian0815/compel/pull/129
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
-#           https://github.com/damian0815/compel/issues/128
+# breaks single-file Stable Diffusion loading on every released diffusers
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
+# main via git froze whichever broken pair existed at image-build time. Pin the
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.