docs: ⬆️ update docs version mudler/LocalAI (#10709 )

⬆️ Update docs version mudler/LocalAI Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
chore: ⬆️ Update ggml-org/llama.cpp to f36e5c348bc8795c34f9a038e58876e7a8423d4d (#10710 )
2026-07-07 06:49:49 -04:00 · 2026-07-07 08:55:01 +02:00 · 2026-07-07 08:54:33 +02:00 · 2026-07-07 08:41:46 +02:00 · 2026-07-07 08:41:34 +02:00 · 2026-07-07 08:41:21 +02:00
14 changed files with 619 additions and 49 deletions
--- a/.github/workflows/backend.yml
+++ b/.github/workflows/backend.yml
@@ -32,16 +32,30 @@ jobs:
    if: github.repository == 'mudler/LocalAI'
    runs-on: ubuntu-latest
    outputs:
-      matrix-singlearch: ${{ steps.set-matrix.outputs['matrix-singlearch'] }}
      matrix-multiarch: ${{ steps.set-matrix.outputs['matrix-multiarch'] }}
      matrix-darwin: ${{ steps.set-matrix.outputs['matrix-darwin'] }}
      merge-matrix-multiarch: ${{ steps.set-matrix.outputs['merge-matrix-multiarch'] }}
-      merge-matrix-singlearch: ${{ steps.set-matrix.outputs['merge-matrix-singlearch'] }}
-      has-backends-singlearch: ${{ steps.set-matrix.outputs['has-backends-singlearch'] }}
      has-backends-multiarch: ${{ steps.set-matrix.outputs['has-backends-multiarch'] }}
      has-backends-darwin: ${{ steps.set-matrix.outputs['has-backends-darwin'] }}
      has-merges-multiarch: ${{ steps.set-matrix.outputs['has-merges-multiarch'] }}
-      has-merges-singlearch: ${{ steps.set-matrix.outputs['has-merges-singlearch'] }}
+      # Single-arch backends are sharded across SINGLEARCH_SHARDS matrix jobs to
+      # stay under GitHub's 256-jobs-per-matrix limit (see changed-backends.js).
+      matrix-singlearch-1: ${{ steps.set-matrix.outputs['matrix-singlearch-1'] }}
+      merge-matrix-singlearch-1: ${{ steps.set-matrix.outputs['merge-matrix-singlearch-1'] }}
+      has-backends-singlearch-1: ${{ steps.set-matrix.outputs['has-backends-singlearch-1'] }}
+      has-merges-singlearch-1: ${{ steps.set-matrix.outputs['has-merges-singlearch-1'] }}
+      matrix-singlearch-2: ${{ steps.set-matrix.outputs['matrix-singlearch-2'] }}
+      merge-matrix-singlearch-2: ${{ steps.set-matrix.outputs['merge-matrix-singlearch-2'] }}
+      has-backends-singlearch-2: ${{ steps.set-matrix.outputs['has-backends-singlearch-2'] }}
+      has-merges-singlearch-2: ${{ steps.set-matrix.outputs['has-merges-singlearch-2'] }}
+      matrix-singlearch-3: ${{ steps.set-matrix.outputs['matrix-singlearch-3'] }}
+      merge-matrix-singlearch-3: ${{ steps.set-matrix.outputs['merge-matrix-singlearch-3'] }}
+      has-backends-singlearch-3: ${{ steps.set-matrix.outputs['has-backends-singlearch-3'] }}
+      has-merges-singlearch-3: ${{ steps.set-matrix.outputs['has-merges-singlearch-3'] }}
+      matrix-singlearch-4: ${{ steps.set-matrix.outputs['matrix-singlearch-4'] }}
+      merge-matrix-singlearch-4: ${{ steps.set-matrix.outputs['merge-matrix-singlearch-4'] }}
+      has-backends-singlearch-4: ${{ steps.set-matrix.outputs['has-backends-singlearch-4'] }}
+      has-merges-singlearch-4: ${{ steps.set-matrix.outputs['has-merges-singlearch-4'] }}
    steps:
      - name: Checkout repository
        uses: actions/checkout@v7
@@ -109,9 +123,9 @@ jobs:
  # take their full ~6h cold without blocking manifest assembly for the
  # multi-arch backends whose per-arch digests would otherwise sit untagged
  # on quay long enough to be GC'd.
-  backend-jobs-singlearch:
+  backend-jobs-singlearch-1:
    needs: generate-matrix
-    if: needs.generate-matrix.outputs['has-backends-singlearch'] == 'true'
+    if: needs.generate-matrix.outputs['has-backends-singlearch-1'] == 'true'
    uses: ./.github/workflows/backend_build.yml
    with:
      tag-latest: ${{ matrix.tag-latest }}
@@ -138,7 +152,100 @@ jobs:
    strategy:
      fail-fast: false
      max-parallel: 8
-      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch']) }}
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch-1']) }}
+
+  backend-jobs-singlearch-2:
+    needs: generate-matrix
+    if: needs.generate-matrix.outputs['has-backends-singlearch-2'] == 'true'
+    uses: ./.github/workflows/backend_build.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+      build-type: ${{ matrix.build-type }}
+      cuda-major-version: ${{ matrix.cuda-major-version }}
+      cuda-minor-version: ${{ matrix.cuda-minor-version }}
+      platforms: ${{ matrix.platforms }}
+      platform-tag: ${{ matrix.platform-tag || '' }}
+      runs-on: ${{ matrix.runs-on }}
+      builder-base-image: ${{ matrix.builder-base-image || '' }}
+      base-image: ${{ matrix.base-image }}
+      backend: ${{ matrix.backend }}
+      dockerfile: ${{ matrix.dockerfile }}
+      skip-drivers: ${{ matrix.skip-drivers }}
+      context: ${{ matrix.context }}
+      ubuntu-version: ${{ matrix.ubuntu-version }}
+      amdgpu-targets: ${{ matrix.amdgpu-targets || 'gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201' }}
+    secrets:
+      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
+      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: false
+      max-parallel: 8
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch-2']) }}
+
+  backend-jobs-singlearch-3:
+    needs: generate-matrix
+    if: needs.generate-matrix.outputs['has-backends-singlearch-3'] == 'true'
+    uses: ./.github/workflows/backend_build.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+      build-type: ${{ matrix.build-type }}
+      cuda-major-version: ${{ matrix.cuda-major-version }}
+      cuda-minor-version: ${{ matrix.cuda-minor-version }}
+      platforms: ${{ matrix.platforms }}
+      platform-tag: ${{ matrix.platform-tag || '' }}
+      runs-on: ${{ matrix.runs-on }}
+      builder-base-image: ${{ matrix.builder-base-image || '' }}
+      base-image: ${{ matrix.base-image }}
+      backend: ${{ matrix.backend }}
+      dockerfile: ${{ matrix.dockerfile }}
+      skip-drivers: ${{ matrix.skip-drivers }}
+      context: ${{ matrix.context }}
+      ubuntu-version: ${{ matrix.ubuntu-version }}
+      amdgpu-targets: ${{ matrix.amdgpu-targets || 'gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201' }}
+    secrets:
+      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
+      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: false
+      max-parallel: 8
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch-3']) }}
+
+  backend-jobs-singlearch-4:
+    needs: generate-matrix
+    if: needs.generate-matrix.outputs['has-backends-singlearch-4'] == 'true'
+    uses: ./.github/workflows/backend_build.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+      build-type: ${{ matrix.build-type }}
+      cuda-major-version: ${{ matrix.cuda-major-version }}
+      cuda-minor-version: ${{ matrix.cuda-minor-version }}
+      platforms: ${{ matrix.platforms }}
+      platform-tag: ${{ matrix.platform-tag || '' }}
+      runs-on: ${{ matrix.runs-on }}
+      builder-base-image: ${{ matrix.builder-base-image || '' }}
+      base-image: ${{ matrix.base-image }}
+      backend: ${{ matrix.backend }}
+      dockerfile: ${{ matrix.dockerfile }}
+      skip-drivers: ${{ matrix.skip-drivers }}
+      context: ${{ matrix.context }}
+      ubuntu-version: ${{ matrix.ubuntu-version }}
+      amdgpu-targets: ${{ matrix.amdgpu-targets || 'gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201' }}
+    secrets:
+      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
+      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: false
+      max-parallel: 8
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch-4']) }}

  # Apply tags to per-arch digests via `imagetools create`. Split into two
  # jobs that mirror the build split so each merge waits ONLY on its
@@ -174,10 +281,12 @@ jobs:
      fail-fast: false
      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-multiarch']) }}

-  backend-merge-jobs-singlearch:
-    needs: [generate-matrix, backend-jobs-singlearch]
-    # See note on backend-merge-jobs-multiarch above for !cancelled().
-    if: ${{ !cancelled() && needs.generate-matrix.outputs['has-merges-singlearch'] == 'true' }}
+  # One merge shard per build shard: backend-merge-jobs-singlearch-<n> needs only
+  # backend-jobs-singlearch-<n>, preserving the "merge waits only on its own
+  # build" property while staying under the 256-jobs-per-matrix limit.
+  backend-merge-jobs-singlearch-1:
+    needs: [generate-matrix, backend-jobs-singlearch-1]
+    if: ${{ !cancelled() && needs.generate-matrix.outputs['has-merges-singlearch-1'] == 'true' }}
    uses: ./.github/workflows/backend_merge.yml
    with:
      tag-latest: ${{ matrix.tag-latest }}
@@ -189,7 +298,55 @@ jobs:
      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
    strategy:
      fail-fast: false
-      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch']) }}
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch-1']) }}
+
+  backend-merge-jobs-singlearch-2:
+    needs: [generate-matrix, backend-jobs-singlearch-2]
+    if: ${{ !cancelled() && needs.generate-matrix.outputs['has-merges-singlearch-2'] == 'true' }}
+    uses: ./.github/workflows/backend_merge.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+    secrets:
+      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
+      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch-2']) }}
+
+  backend-merge-jobs-singlearch-3:
+    needs: [generate-matrix, backend-jobs-singlearch-3]
+    if: ${{ !cancelled() && needs.generate-matrix.outputs['has-merges-singlearch-3'] == 'true' }}
+    uses: ./.github/workflows/backend_merge.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+    secrets:
+      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
+      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch-3']) }}
+
+  backend-merge-jobs-singlearch-4:
+    needs: [generate-matrix, backend-jobs-singlearch-4]
+    if: ${{ !cancelled() && needs.generate-matrix.outputs['has-merges-singlearch-4'] == 'true' }}
+    uses: ./.github/workflows/backend_merge.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+    secrets:
+      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
+      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch-4']) }}

  backend-jobs-darwin:
    needs: generate-matrix
--- a/.github/workflows/backend_pr.yml
+++ b/.github/workflows/backend_pr.yml
@@ -11,16 +11,30 @@ jobs:
  generate-matrix:
    runs-on: ubuntu-latest
    outputs:
-      matrix-singlearch: ${{ steps.set-matrix.outputs['matrix-singlearch'] }}
      matrix-multiarch: ${{ steps.set-matrix.outputs['matrix-multiarch'] }}
      matrix-darwin: ${{ steps.set-matrix.outputs['matrix-darwin'] }}
      merge-matrix-multiarch: ${{ steps.set-matrix.outputs['merge-matrix-multiarch'] }}
-      merge-matrix-singlearch: ${{ steps.set-matrix.outputs['merge-matrix-singlearch'] }}
-      has-backends-singlearch: ${{ steps.set-matrix.outputs['has-backends-singlearch'] }}
      has-backends-multiarch: ${{ steps.set-matrix.outputs['has-backends-multiarch'] }}
      has-backends-darwin: ${{ steps.set-matrix.outputs['has-backends-darwin'] }}
      has-merges-multiarch: ${{ steps.set-matrix.outputs['has-merges-multiarch'] }}
-      has-merges-singlearch: ${{ steps.set-matrix.outputs['has-merges-singlearch'] }}
+      # Single-arch backends are sharded across SINGLEARCH_SHARDS matrix jobs to
+      # stay under GitHub's 256-jobs-per-matrix limit (see changed-backends.js).
+      matrix-singlearch-1: ${{ steps.set-matrix.outputs['matrix-singlearch-1'] }}
+      merge-matrix-singlearch-1: ${{ steps.set-matrix.outputs['merge-matrix-singlearch-1'] }}
+      has-backends-singlearch-1: ${{ steps.set-matrix.outputs['has-backends-singlearch-1'] }}
+      has-merges-singlearch-1: ${{ steps.set-matrix.outputs['has-merges-singlearch-1'] }}
+      matrix-singlearch-2: ${{ steps.set-matrix.outputs['matrix-singlearch-2'] }}
+      merge-matrix-singlearch-2: ${{ steps.set-matrix.outputs['merge-matrix-singlearch-2'] }}
+      has-backends-singlearch-2: ${{ steps.set-matrix.outputs['has-backends-singlearch-2'] }}
+      has-merges-singlearch-2: ${{ steps.set-matrix.outputs['has-merges-singlearch-2'] }}
+      matrix-singlearch-3: ${{ steps.set-matrix.outputs['matrix-singlearch-3'] }}
+      merge-matrix-singlearch-3: ${{ steps.set-matrix.outputs['merge-matrix-singlearch-3'] }}
+      has-backends-singlearch-3: ${{ steps.set-matrix.outputs['has-backends-singlearch-3'] }}
+      has-merges-singlearch-3: ${{ steps.set-matrix.outputs['has-merges-singlearch-3'] }}
+      matrix-singlearch-4: ${{ steps.set-matrix.outputs['matrix-singlearch-4'] }}
+      merge-matrix-singlearch-4: ${{ steps.set-matrix.outputs['merge-matrix-singlearch-4'] }}
+      has-backends-singlearch-4: ${{ steps.set-matrix.outputs['has-backends-singlearch-4'] }}
+      has-merges-singlearch-4: ${{ steps.set-matrix.outputs['has-merges-singlearch-4'] }}
    steps:
      - name: Checkout repository
        uses: actions/checkout@v7
@@ -71,10 +85,10 @@ jobs:
      fail-fast: true
      max-parallel: 8
      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-multiarch']) }}
-  backend-jobs-singlearch:
+  backend-jobs-singlearch-1:
    needs: generate-matrix
+    if: needs.generate-matrix.outputs['has-backends-singlearch-1'] == 'true'
    uses: ./.github/workflows/backend_build.yml
-    if: needs.generate-matrix.outputs['has-backends-singlearch'] == 'true'
    with:
      tag-latest: ${{ matrix.tag-latest }}
      tag-suffix: ${{ matrix.tag-suffix }}
@@ -98,7 +112,94 @@ jobs:
    strategy:
      fail-fast: true
      max-parallel: 8
-      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch']) }}
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch-1']) }}
+
+  backend-jobs-singlearch-2:
+    needs: generate-matrix
+    if: needs.generate-matrix.outputs['has-backends-singlearch-2'] == 'true'
+    uses: ./.github/workflows/backend_build.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+      build-type: ${{ matrix.build-type }}
+      cuda-major-version: ${{ matrix.cuda-major-version }}
+      cuda-minor-version: ${{ matrix.cuda-minor-version }}
+      platforms: ${{ matrix.platforms }}
+      platform-tag: ${{ matrix.platform-tag || '' }}
+      runs-on: ${{ matrix.runs-on }}
+      builder-base-image: ${{ matrix.builder-base-image || '' }}
+      base-image: ${{ matrix.base-image }}
+      backend: ${{ matrix.backend }}
+      dockerfile: ${{ matrix.dockerfile }}
+      skip-drivers: ${{ matrix.skip-drivers }}
+      context: ${{ matrix.context }}
+      ubuntu-version: ${{ matrix.ubuntu-version }}
+      amdgpu-targets: ${{ matrix.amdgpu-targets || 'gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201' }}
+    secrets:
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: true
+      max-parallel: 8
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch-2']) }}
+
+  backend-jobs-singlearch-3:
+    needs: generate-matrix
+    if: needs.generate-matrix.outputs['has-backends-singlearch-3'] == 'true'
+    uses: ./.github/workflows/backend_build.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+      build-type: ${{ matrix.build-type }}
+      cuda-major-version: ${{ matrix.cuda-major-version }}
+      cuda-minor-version: ${{ matrix.cuda-minor-version }}
+      platforms: ${{ matrix.platforms }}
+      platform-tag: ${{ matrix.platform-tag || '' }}
+      runs-on: ${{ matrix.runs-on }}
+      builder-base-image: ${{ matrix.builder-base-image || '' }}
+      base-image: ${{ matrix.base-image }}
+      backend: ${{ matrix.backend }}
+      dockerfile: ${{ matrix.dockerfile }}
+      skip-drivers: ${{ matrix.skip-drivers }}
+      context: ${{ matrix.context }}
+      ubuntu-version: ${{ matrix.ubuntu-version }}
+      amdgpu-targets: ${{ matrix.amdgpu-targets || 'gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201' }}
+    secrets:
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: true
+      max-parallel: 8
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch-3']) }}
+
+  backend-jobs-singlearch-4:
+    needs: generate-matrix
+    if: needs.generate-matrix.outputs['has-backends-singlearch-4'] == 'true'
+    uses: ./.github/workflows/backend_build.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+      build-type: ${{ matrix.build-type }}
+      cuda-major-version: ${{ matrix.cuda-major-version }}
+      cuda-minor-version: ${{ matrix.cuda-minor-version }}
+      platforms: ${{ matrix.platforms }}
+      platform-tag: ${{ matrix.platform-tag || '' }}
+      runs-on: ${{ matrix.runs-on }}
+      builder-base-image: ${{ matrix.builder-base-image || '' }}
+      base-image: ${{ matrix.base-image }}
+      backend: ${{ matrix.backend }}
+      dockerfile: ${{ matrix.dockerfile }}
+      skip-drivers: ${{ matrix.skip-drivers }}
+      context: ${{ matrix.context }}
+      ubuntu-version: ${{ matrix.ubuntu-version }}
+      amdgpu-targets: ${{ matrix.amdgpu-targets || 'gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201' }}
+    secrets:
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: true
+      max-parallel: 8
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['matrix-singlearch-4']) }}
  backend-merge-jobs-multiarch:
    needs: [generate-matrix, backend-jobs-multiarch]
    # backend_merge.yml's push-side steps are all gated on
@@ -118,9 +219,9 @@ jobs:
      fail-fast: false
      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-multiarch']) }}

-  backend-merge-jobs-singlearch:
-    needs: [generate-matrix, backend-jobs-singlearch]
-    if: ${{ !cancelled() && github.event_name != 'pull_request' && needs.generate-matrix.outputs['has-merges-singlearch'] == 'true' }}
+  backend-merge-jobs-singlearch-1:
+    needs: [generate-matrix, backend-jobs-singlearch-1]
+    if: ${{ !cancelled() && github.event_name != 'pull_request' && needs.generate-matrix.outputs['has-merges-singlearch-1'] == 'true' }}
    uses: ./.github/workflows/backend_merge.yml
    with:
      tag-latest: ${{ matrix.tag-latest }}
@@ -130,7 +231,49 @@ jobs:
      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
    strategy:
      fail-fast: false
-      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch']) }}
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch-1']) }}
+
+  backend-merge-jobs-singlearch-2:
+    needs: [generate-matrix, backend-jobs-singlearch-2]
+    if: ${{ !cancelled() && github.event_name != 'pull_request' && needs.generate-matrix.outputs['has-merges-singlearch-2'] == 'true' }}
+    uses: ./.github/workflows/backend_merge.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+    secrets:
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch-2']) }}
+
+  backend-merge-jobs-singlearch-3:
+    needs: [generate-matrix, backend-jobs-singlearch-3]
+    if: ${{ !cancelled() && github.event_name != 'pull_request' && needs.generate-matrix.outputs['has-merges-singlearch-3'] == 'true' }}
+    uses: ./.github/workflows/backend_merge.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+    secrets:
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch-3']) }}
+
+  backend-merge-jobs-singlearch-4:
+    needs: [generate-matrix, backend-jobs-singlearch-4]
+    if: ${{ !cancelled() && github.event_name != 'pull_request' && needs.generate-matrix.outputs['has-merges-singlearch-4'] == 'true' }}
+    uses: ./.github/workflows/backend_merge.yml
+    with:
+      tag-latest: ${{ matrix.tag-latest }}
+      tag-suffix: ${{ matrix.tag-suffix }}
+    secrets:
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJson(needs.generate-matrix.outputs['merge-matrix-singlearch-4']) }}
  backend-jobs-darwin:
    needs: generate-matrix
    uses: ./.github/workflows/backend_build_darwin.yml
--- a/.github/workflows/realtime-conformance.yml
+++ b/.github/workflows/realtime-conformance.yml
@@ -54,7 +54,7 @@ jobs:
          go-version: ${{ matrix.go-version }}
          cache: false
      - name: Cache FizzBee
-        uses: actions/cache@v4
+        uses: actions/cache@v6
        with:
          path: .tools/fizzbee
          key: fizzbee-v0.5.2-${{ runner.os }}-${{ hashFiles('formal-verification/fizzbee.sha256') }}
--- a/backend/cpp/ik-llama-cpp/Makefile
+++ b/backend/cpp/ik-llama-cpp/Makefile
@@ -1,5 +1,5 @@

-IK_LLAMA_VERSION?=bbc7de475178dd0535c16ad85f204a2529806c9d
+IK_LLAMA_VERSION?=a8cf53fd69bada5450bd653eb0e32d1113fbd7fe
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp

 CMAKE_ARGS?=
--- a/backend/cpp/llama-cpp/Makefile
+++ b/backend/cpp/llama-cpp/Makefile
@@ -1,5 +1,5 @@

-LLAMA_VERSION?=2da668617612d2df773f966e3b0ee22dc2beef7b
+LLAMA_VERSION?=f36e5c348bc8795c34f9a038e58876e7a8423d4d
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp

 CMAKE_ARGS?=
--- a/backend/go/crispasr/Makefile
+++ b/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?=09df654e304947f7521e1f52992ceacccf03c300
+CRISPASR_VERSION?=0a7643f1006c6bf2d1f37f5c63e9726f5eb4f364
 SO_TARGET?=libgocrispasr.so

 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
--- a/backend/go/qwen3-tts-cpp/Makefile
+++ b/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?=73fe0c67bbf0898ba2999535e0680a02a7f8537d
+QWEN3TTS_CPP_VERSION?=0725d2e53b7d2749a99ff33d3a460b954ffa7805
 SO_TARGET?=libgoqwen3ttscpp.so

 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
--- a/backend/go/stablediffusion-ggml/Makefile
+++ b/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?=2574f5936571645f784b77623e1f09bad97d948a
+STABLEDIFFUSION_GGML_VERSION?=bb84971129d2a094ab8051c6feed5406d3b4409d

 CMAKE_ARGS+=-DGGML_MAX_NAME=128

--- a/backend/go/stablediffusion-ggml/cpp/gosd.cpp
+++ b/backend/go/stablediffusion-ggml/cpp/gosd.cpp
@@ -660,9 +660,16 @@ int load_model(const char *model, char *model_path, char* options[], int threads
    ctx_params.diffusion_conv_direct = diffusion_conv_direct;
    ctx_params.vae_conv_direct = vae_conv_direct;
    ctx_params.force_sdxl_vae_conv_scale = force_sdxl_vae_conv_scale;
-    ctx_params.chroma_use_dit_mask = chroma_use_dit_mask;
-    ctx_params.chroma_use_t5_mask = chroma_use_t5_mask;
-    ctx_params.chroma_t5_mask_pad = chroma_t5_mask_pad;
+    // Chroma knobs: upstream dropped the dedicated chroma_use_dit_mask /
+    // chroma_use_t5_mask / chroma_t5_mask_pad struct fields and now reads them
+    // from the generic model_args key=value spec (parse_key_value_args). Emit
+    // them there so the existing chroma options keep working. This string must
+    // outlive new_sd_ctx() below.
+    std::string model_args_spec =
+        "chroma_use_dit_mask=" + std::string(chroma_use_dit_mask ? "true" : "false") +
+        ",chroma_use_t5_mask=" + std::string(chroma_use_t5_mask ? "true" : "false") +
+        ",chroma_t5_mask_pad=" + std::to_string(chroma_t5_mask_pad);
+    ctx_params.model_args = model_args_spec.c_str();
    sd_ctx_t* sd_ctx = new_sd_ctx(&ctx_params);

    if (sd_ctx == NULL) {
--- a/backend/python/vllm/install.sh
+++ b/backend/python/vllm/install.sh
@@ -119,7 +119,7 @@ if [ "$(uname -s)" = "Darwin" ]; then
    # can rewrite it. Darwin therefore follows vllm-metal and can lag the Linux
    # vllm pin (requirements-cublas13-after.txt, bumped independently against
    # vllm/vllm) until vllm-metal supports a newer vLLM.
-    VLLM_METAL_VERSION="v0.3.0.dev20260704102955"
+    VLLM_METAL_VERSION="v0.3.0.dev20260706123649"

    # The coupled vLLM source version is whatever this vllm-metal release builds
    # against -- it declares it in its own installer as `vllm_v=`. Derive it from
--- a/backend/python/vllm/requirements.txt
+++ b/backend/python/vllm/requirements.txt
@@ -3,5 +3,5 @@ protobuf
 certifi
 setuptools
 pillow
-charset-normalizer>=3.4.8
+charset-normalizer>=3.4.7
 chardet
--- a/docs/data/version.json
+++ b/docs/data/version.json
@@ -1,3 +1,3 @@
 {
-  "version": "v4.6.0"
+  "version": "v4.6.2"
 }
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -13475,6 +13475,223 @@
    - filename: minicpm-v-4_5-mmproj-f16.gguf
      sha256: 7a7225a32e8d453aaa3d22d8c579b5bf833c253f784cdb05c99c9a76fd616df8
      uri: huggingface://openbmb/MiniCPM-V-4_5-gguf/mmproj-model-f16.gguf
+- name: minicpm-v-4_6
+  url: github:mudler/LocalAI/gallery/qwen3.yaml@master
+  urls:
+    - https://huggingface.co/openbmb/MiniCPM-V-4.6-gguf
+    - https://huggingface.co/openbmb/MiniCPM-V-4.6
+  description: |
+    MiniCPM-V 4.6 is the most edge-deployment-friendly model in the MiniCPM-V series, with a total of 1.3B parameters. Built on Qwen3.5-0.8B and SigLIP2-400M, it features ultra-efficient architecture with mixed 4x/16x visual token compression for on-device deployment on iOS, Android, and HarmonyOS.
+  license: apache-2.0
+  icon: https://avatars.githubusercontent.com/u/89920203
+  tags:
+    - llm
+    - multimodal
+    - gguf
+    - gpu
+    - qwen3
+    - cpu
+  overrides:
+    mmproj: minicpm-v-4_6-mmproj-f16.gguf
+    parameters:
+      model: minicpm-v-4_6-Q4_K_M.gguf
+  files:
+    - filename: minicpm-v-4_6-Q4_K_M.gguf
+      sha256: 6b0c74962c44bc6bf4b655b9b02c13eda9d5a0491543ae976d1ac18e4b7892e2
+      uri: huggingface://openbmb/MiniCPM-V-4.6-gguf/MiniCPM-V-4_6-Q4_K_M.gguf
+    - filename: minicpm-v-4_6-mmproj-f16.gguf
+      sha256: ca931d861d0801d9003e50697cd764721a334107c0e0415a51168ee1938462de
+      uri: huggingface://openbmb/MiniCPM-V-4.6-gguf/mmproj-model-f16.gguf
+- name: minicpm5-1b
+  url: github:mudler/LocalAI/gallery/chatml.yaml@master
+  urls:
+    - https://huggingface.co/openbmb/MiniCPM5-1B-GGUF
+    - https://huggingface.co/openbmb/MiniCPM5-1B
+  description: |
+    MiniCPM5-1B is a compact 1B-parameter language model based on the LLaMA architecture. Despite its small size, it achieves competitive performance among sub-2B models, making it ideal for edge deployment and resource-constrained environments.
+  license: apache-2.0
+  icon: https://avatars.githubusercontent.com/u/89920203
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - cpu
+  overrides:
+    parameters:
+      model: MiniCPM5-1B-Q4_K_M.gguf
+  files:
+    - filename: MiniCPM5-1B-Q4_K_M.gguf
+      sha256: 81b64d05a23b17b34c475f42b3e72fbde62d4b92cc34541f7a8031d0752deafa
+      uri: huggingface://openbmb/MiniCPM5-1B-GGUF/MiniCPM5-1B-Q4_K_M.gguf
+- name: minicpm-o-4_5
+  url: github:mudler/LocalAI/gallery/qwen3.yaml@master
+  urls:
+    - https://huggingface.co/openbmb/MiniCPM-o-4_5-gguf
+    - https://huggingface.co/openbmb/MiniCPM-o-4_5
+  description: |
+    MiniCPM-o 4.5 is the latest omni-modal model in the MiniCPM series. Built on Qwen3-8B and SigLIP2-400M, it supports vision, speech, and text in a unified 8B-parameter architecture with full-duplex real-time streaming.
+  license: apache-2.0
+  icon: https://avatars.githubusercontent.com/u/89920203
+  tags:
+    - llm
+    - multimodal
+    - gguf
+    - gpu
+    - qwen3
+    - cpu
+  overrides:
+    mmproj: minicpm-o-4_5-mmproj-f16.gguf
+    parameters:
+      model: minicpm-o-4_5-Q4_K_M.gguf
+  files:
+    - filename: minicpm-o-4_5-Q4_K_M.gguf
+      sha256: 1237a97ee081b8abebc47aa7dad565701e8f5f904cdc92f6723ac4281bbc0932
+      uri: huggingface://openbmb/MiniCPM-o-4_5-gguf/MiniCPM-o-4_5-Q4_K_M.gguf
+    - filename: minicpm-o-4_5-mmproj-f16.gguf
+      sha256: 1453678cc4e4fe18de241952962e234f265cb8dda780773526103ab8ba82f421
+      uri: huggingface://openbmb/MiniCPM-o-4_5-gguf/vision/MiniCPM-o-4_5-vision-F16.gguf
+- name: minicpm-v-4_6-thinking
+  url: github:mudler/LocalAI/gallery/qwen3.yaml@master
+  urls:
+    - https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking-gguf
+    - https://huggingface.co/openbmb/MiniCPM-V-4.6-Thinking
+  description: |
+    MiniCPM-V 4.6 Thinking is the reasoning-enhanced version of MiniCPM-V 4.6, with a total of 1.3B parameters. Built on Qwen3.5-0.8B and SigLIP2-400M, it features extended thinking capabilities for complex visual reasoning tasks while maintaining an ultra-compact architecture for edge deployment.
+  license: apache-2.0
+  icon: https://avatars.githubusercontent.com/u/89920203
+  tags:
+    - llm
+    - multimodal
+    - gguf
+    - gpu
+    - qwen3
+    - cpu
+  overrides:
+    mmproj: minicpm-v-4_6-thinking-mmproj-f16.gguf
+    parameters:
+      model: MiniCPM-V-4_6-Thinking-Q4_K_M.gguf
+  files:
+    - filename: MiniCPM-V-4_6-Thinking-Q4_K_M.gguf
+      sha256: 2d15cea059289533a4e51cff895888a2afaf8ed0c88bcc11ba590d2a45c6f174
+      uri: huggingface://openbmb/MiniCPM-V-4.6-Thinking-gguf/MiniCPM-V-4_6-Thinking-Q4_K_M.gguf
+    - filename: minicpm-v-4_6-thinking-mmproj-f16.gguf
+      sha256: b9d09d261de167b291a69958b520c6411877cbff50e96a83d06e9835627c70f6
+      uri: huggingface://openbmb/MiniCPM-V-4.6-Thinking-gguf/mmproj-model-f16.gguf
+- name: minicpm-v-4
+  url: github:mudler/LocalAI/gallery/chatml.yaml@master
+  urls:
+    - https://huggingface.co/openbmb/MiniCPM-V-4-gguf
+    - https://huggingface.co/openbmb/MiniCPM-V-4
+  description: |
+    MiniCPM-V 4 is a multimodal large language model in the MiniCPM-V series, supporting image and video understanding with strong OCR and multi-image capabilities.
+  license: apache-2.0
+  icon: https://avatars.githubusercontent.com/u/89920203
+  tags:
+    - llm
+    - multimodal
+    - gguf
+    - gpu
+    - cpu
+  overrides:
+    mmproj: minicpm-v-4-mmproj-f16.gguf
+    parameters:
+      model: minicpm-v-4-Q4_K_M.gguf
+  files:
+    - filename: minicpm-v-4-Q4_K_M.gguf
+      sha256: b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
+      uri: huggingface://openbmb/MiniCPM-V-4-gguf/ggml-model-Q4_K_M.gguf
+    - filename: minicpm-v-4-mmproj-f16.gguf
+      sha256: f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761
+      uri: huggingface://openbmb/MiniCPM-V-4-gguf/mmproj-model-f16.gguf
+- name: minicpm3-4b
+  url: github:mudler/LocalAI/gallery/chatml.yaml@master
+  urls:
+    - https://huggingface.co/openbmb/MiniCPM3-4B-GGUF
+    - https://huggingface.co/openbmb/MiniCPM3-4B
+  description: |
+    MiniCPM3-4B is a 4B-parameter language model that surpasses many larger models. It features enhanced long-context capability up to 32K tokens, strong function calling, and improved instruction following.
+  license: apache-2.0
+  icon: https://avatars.githubusercontent.com/u/89920203
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - cpu
+  overrides:
+    parameters:
+      model: minicpm3-4b-q4_k_m.gguf
+  files:
+    - filename: minicpm3-4b-q4_k_m.gguf
+      sha256: 64913247e927414ecf47fd3e9ea8e3f0c9acae293f583dfa7e24b8872e20fa4c
+      uri: huggingface://openbmb/MiniCPM3-4B-GGUF/minicpm3-4b-q4_k_m.gguf
+- name: minicpm-o-2_6
+  url: github:mudler/LocalAI/gallery/chatml.yaml@master
+  urls:
+    - https://huggingface.co/openbmb/MiniCPM-o-2_6-gguf
+    - https://huggingface.co/openbmb/MiniCPM-o-2_6
+  description: |
+    MiniCPM-o 2.6 is an omni-modal model supporting vision, speech, and text. Based on a 7.6B-parameter architecture with SigLIP-400M and Whisper-medium, it offers real-time speech conversation and multimodal live streaming capabilities.
+  license: apache-2.0
+  icon: https://avatars.githubusercontent.com/u/89920203
+  tags:
+    - llm
+    - multimodal
+    - gguf
+    - gpu
+    - cpu
+  overrides:
+    mmproj: minicpm-o-2_6-mmproj-f16.gguf
+    parameters:
+      model: minicpm-o-2_6-Q4_K_M.gguf
+  files:
+    - filename: minicpm-o-2_6-Q4_K_M.gguf
+      sha256: 4f635fc0c0bb88d50ccd9cf1f1e5892b5cb085ff88fe0d8e1148fd9a8a836bc2
+      uri: huggingface://openbmb/MiniCPM-o-2_6-gguf/Model-7.6B-Q4_K_M.gguf
+    - filename: minicpm-o-2_6-mmproj-f16.gguf
+      sha256: efa4f7d96aa0f838f2023fc8d28e519179b16f1106777fa9280b32628191aa3e
+      uri: huggingface://openbmb/MiniCPM-o-2_6-gguf/mmproj-model-f16.gguf
+- name: minicpm4_1-8b
+  url: github:mudler/LocalAI/gallery/chatml.yaml@master
+  urls:
+    - https://huggingface.co/openbmb/MiniCPM4.1-8B-GGUF
+    - https://huggingface.co/openbmb/MiniCPM4.1-8B
+  description: |
+    MiniCPM4.1-8B is an 8B-parameter language model with enhanced capabilities in coding, mathematics, and instruction following, building upon the MiniCPM4 architecture.
+  license: apache-2.0
+  icon: https://avatars.githubusercontent.com/u/89920203
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - cpu
+  overrides:
+    parameters:
+      model: MiniCPM4.1-8B-Q4_K_M.gguf
+  files:
+    - filename: MiniCPM4.1-8B-Q4_K_M.gguf
+      sha256: 9d2ffb9145bf7a88ddb94b2542b42d925293666c42962aa158eeb62fc9708654
+      uri: huggingface://openbmb/MiniCPM4.1-8B-GGUF/MiniCPM4.1-8B-Q4_K_M.gguf
+- name: minicpm4-8b
+  url: github:mudler/LocalAI/gallery/chatml.yaml@master
+  urls:
+    - https://huggingface.co/openbmb/MiniCPM4-8B-GGUF
+    - https://huggingface.co/openbmb/MiniCPM4-8B
+  description: |
+    MiniCPM4-8B is an 8B-parameter language model achieving competitive performance among models of similar size, with strong capabilities in reasoning, coding, and multilingual tasks.
+  license: apache-2.0
+  icon: https://avatars.githubusercontent.com/u/89920203
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - cpu
+  overrides:
+    parameters:
+      model: MiniCPM4-8B-Q4_K_M.gguf
+  files:
+    - filename: MiniCPM4-8B-Q4_K_M.gguf
+      sha256: 80b99ec4ceac302e7d474c8659e96b9f6c3bbeb73c41b2ef841c7fcb6d8250f3
+      uri: huggingface://openbmb/MiniCPM4-8B-GGUF/MiniCPM4-8B-Q4_K_M.gguf
 - name: aquif-ai_aquif-3.5-8b-think
  url: github:mudler/LocalAI/gallery/qwen3.yaml@master
  urls:
--- a/scripts/changed-backends.js
+++ b/scripts/changed-backends.js
@@ -209,23 +209,75 @@ function splitByArch(entries) {
  return { multiarch, singlearch };
 }

+// GitHub Actions refuses to instantiate a matrix with more than 256 jobs. When
+// it happens the job doesn't error visibly — it hangs forever at "Waiting for
+// pending jobs" and the whole run is marked `failure` while every *other* job
+// stays green (seen on the v4.6.1 tag build, run 28786533892: 268 single-arch
+// entries, zero single-arch jobs ever created). The single-arch list is the
+// one that grows unbounded as backends are added, so we shard it across a
+// fixed number of matrix jobs instead of feeding one oversized matrix.
+//
+// SINGLEARCH_SHARDS MUST equal the number of backend-jobs-singlearch-<n>
+// (and backend-merge-jobs-singlearch-<n>) blocks defined in backend.yml and
+// backend_pr.yml. Bump all three together.
+const SINGLEARCH_SHARDS = 4;
+const GHA_MATRIX_LIMIT = 256;
+
+// Split `arr` into exactly `shards` balanced, contiguous chunks. Earlier chunks
+// absorb the remainder when the length doesn't divide evenly; trailing chunks
+// may be empty when there are fewer entries than shards (those emit a
+// has-backends-singlearch-<n>=false flag so their job is skipped).
+function chunkEqually(arr, shards) {
+  const out = [];
+  const base = Math.floor(arr.length / shards);
+  const rem = arr.length % shards;
+  let idx = 0;
+  for (let i = 0; i < shards; i++) {
+    const size = base + (i < rem ? 1 : 0);
+    out.push(arr.slice(idx, idx + size));
+    idx += size;
+  }
+  return out;
+}
+
+// Emit the sharded single-arch build + merge matrices and their has-* gates.
+// Called with the full or filtered single-arch entry list.
+function emitSinglearchShards(singlearch) {
+  const shards = chunkEqually(singlearch, SINGLEARCH_SHARDS);
+  for (let i = 0; i < SINGLEARCH_SHARDS; i++) {
+    const shard = shards[i];
+    // Fail loudly rather than let GitHub silently drop the overflow: a shard at
+    // or above the limit means SINGLEARCH_SHARDS (and the matching job blocks in
+    // both workflows) need to grow.
+    if (shard.length >= GHA_MATRIX_LIMIT) {
+      throw new Error(
+        `single-arch shard ${i + 1} has ${shard.length} entries (>= ${GHA_MATRIX_LIMIT}, ` +
+        `GitHub's per-matrix job limit). Increase SINGLEARCH_SHARDS in ` +
+        `scripts/changed-backends.js and add matching backend-jobs-singlearch-<n> / ` +
+        `backend-merge-jobs-singlearch-<n> blocks to backend.yml and backend_pr.yml.`
+      );
+    }
+    const merge = computeMergeMatrix(shard);
+    const n = i + 1;
+    fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-singlearch-${n}=${shard.length > 0 ? 'true' : 'false'}\n`);
+    fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-singlearch-${n}=${merge.include.length > 0 ? 'true' : 'false'}\n`);
+    fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-singlearch-${n}=${JSON.stringify({ include: shard })}\n`);
+    fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-singlearch-${n}=${JSON.stringify(merge)}\n`);
+  }
+}
+
 function emitFullMatrix() {
  const { multiarch, singlearch } = splitByArch(includes);
  const mergeMatrixMultiarch = computeMergeMatrix(multiarch);
-  const mergeMatrixSinglearch = computeMergeMatrix(singlearch);
  const hasMergesMultiarch = mergeMatrixMultiarch.include.length > 0 ? 'true' : 'false';
-  const hasMergesSinglearch = mergeMatrixSinglearch.include.length > 0 ? 'true' : 'false';
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `run-all=true\n`);
-  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-singlearch=${singlearch.length > 0 ? 'true' : 'false'}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-multiarch=${multiarch.length > 0 ? 'true' : 'false'}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-darwin=true\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-multiarch=${hasMergesMultiarch}\n`);
-  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-singlearch=${hasMergesSinglearch}\n`);
-  fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-singlearch=${JSON.stringify({ include: singlearch })}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-multiarch=${JSON.stringify({ include: multiarch })}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-darwin=${JSON.stringify({ include: includesDarwin })}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-multiarch=${JSON.stringify(mergeMatrixMultiarch)}\n`);
-  fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-singlearch=${JSON.stringify(mergeMatrixSinglearch)}\n`);
+  emitSinglearchShards(singlearch);
  for (const backend of allBackendPaths.keys()) {
    fs.appendFileSync(process.env.GITHUB_OUTPUT, `${backend}=true\n`);
  }
@@ -249,29 +301,23 @@ function emitFilteredMatrix(changedFiles) {
  console.log("Filtered files Darwin:", filteredDarwin);

  const { multiarch, singlearch } = splitByArch(filtered);
-  const hasBackendsSinglearch = singlearch.length > 0 ? 'true' : 'false';
  const hasBackendsMultiarch = multiarch.length > 0 ? 'true' : 'false';
  const hasBackendsDarwin = filteredDarwin.length > 0 ? 'true' : 'false';
-  console.log("Has single-arch backends?:", hasBackendsSinglearch);
+  console.log("Has single-arch backends?:", singlearch.length > 0 ? 'true' : 'false');
  console.log("Has multi-arch backends?:", hasBackendsMultiarch);
  console.log("Has Darwin backends?:", hasBackendsDarwin);

  const mergeMatrixMultiarch = computeMergeMatrix(multiarch);
-  const mergeMatrixSinglearch = computeMergeMatrix(singlearch);
  const hasMergesMultiarch = mergeMatrixMultiarch.include.length > 0 ? 'true' : 'false';
-  const hasMergesSinglearch = mergeMatrixSinglearch.include.length > 0 ? 'true' : 'false';

  fs.appendFileSync(process.env.GITHUB_OUTPUT, `run-all=false\n`);
-  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-singlearch=${hasBackendsSinglearch}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-multiarch=${hasBackendsMultiarch}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-backends-darwin=${hasBackendsDarwin}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-multiarch=${hasMergesMultiarch}\n`);
-  fs.appendFileSync(process.env.GITHUB_OUTPUT, `has-merges-singlearch=${hasMergesSinglearch}\n`);
-  fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-singlearch=${JSON.stringify({ include: singlearch })}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-multiarch=${JSON.stringify({ include: multiarch })}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `matrix-darwin=${JSON.stringify({ include: filteredDarwin })}\n`);
  fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-multiarch=${JSON.stringify(mergeMatrixMultiarch)}\n`);
-  fs.appendFileSync(process.env.GITHUB_OUTPUT, `merge-matrix-singlearch=${JSON.stringify(mergeMatrixSinglearch)}\n`);
+  emitSinglearchShards(singlearch);

  // Per-backend boolean outputs
  for (const [backend, pathPrefix] of allBackendPaths) {
Author	SHA1	Message	Date
LocalAI [bot]	22225217e0	docs: ⬆️ update docs version mudler/LocalAI (#10709 ) ⬆️ Update docs version mudler/LocalAI Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>	2026-07-07 08:55:01 +02:00
LocalAI [bot]	c1fd12a506	chore: ⬆️ Update ggml-org/llama.cpp to `f36e5c348bc8795c34f9a038e58876e7a8423d4d` (#10710 ) ⬆️ Update ggml-org/llama.cpp Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>	2026-07-07 08:54:33 +02:00
LocalAI [bot]	d01b2c4f46	chore: ⬆️ Update ServeurpersoCom/qwentts.cpp to `0725d2e53b7d2749a99ff33d3a460b954ffa7805` (#10711 ) ⬆️ Update ServeurpersoCom/qwentts.cpp Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>	2026-07-07 08:41:46 +02:00
LocalAI [bot]	fb9ff061f1	chore: ⬆️ Update vllm-metal (darwin) to `v0.3.0.dev20260706123649` (#10712 ) ⬆️ Update vllm-project/vllm-metal (darwin) Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>	2026-07-07 08:41:34 +02:00
LocalAI [bot]	40f847745e	chore: ⬆️ Update ikawrakow/ik_llama.cpp to `a8cf53fd69bada5450bd653eb0e32d1113fbd7fe` (#10713 ) ⬆️ Update ikawrakow/ik_llama.cpp Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>	2026-07-07 08:41:21 +02:00
LocalAI [bot]	ba9327b9f8	chore: ⬆️ Update CrispStrobe/CrispASR to `0a7643f1006c6bf2d1f37f5c63e9726f5eb4f364` (#10716 ) ⬆️ Update CrispStrobe/CrispASR Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>	2026-07-07 08:41:00 +02:00
LocalAI [bot]	fd467c5b3b	chore: ⬆️ Update leejet/stable-diffusion.cpp to `bb84971129d2a094ab8051c6feed5406d3b4409d` (#10684 ) * ⬆️ Update leejet/stable-diffusion.cpp Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * fix(stablediffusion-ggml): pass chroma knobs via model_args after upstream API change Upstream stable-diffusion.cpp bb849711 removed the dedicated chroma_use_dit_mask / chroma_use_t5_mask / chroma_t5_mask_pad fields from sd_ctx_params_t and now reads them from the generic model_args key=value spec (parse_key_value_args). Assigning the old struct members broke the gosd.cpp build. Emit the three options into model_args instead so the existing chroma controls keep working. Verified by building libgosd-fallback.so against the pinned upstream commit. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code] --------- Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: mudler <2420543+mudler@users.noreply.github.com> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>	2026-07-06 23:57:50 +00:00
dependabot[bot]	fa0622604a	chore(deps): bump actions/cache from 4 to 6 (#10704 ) Bumps [actions/cache](https://github.com/actions/cache) from 4 to 6. - [Release notes](https://github.com/actions/cache/releases) - [Changelog](https://github.com/actions/cache/blob/main/RELEASES.md) - [Commits](https://github.com/actions/cache/compare/v4...v6) --- updated-dependencies: - dependency-name: actions/cache dependency-version: '6' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2026-07-06 21:39:37 +02:00
Dennis Huang	ff5758113b	chore(model gallery): add MiniCPM series models (#10699 ) Add 9 MiniCPM models to the gallery: - MiniCPM-V 4.6 (1.3B multimodal, edge-optimized) - MiniCPM-V 4.6 Thinking (1.3B multimodal with reasoning) - MiniCPM-V 4 (multimodal) - MiniCPM-o 4.5 (8B omni-modal, vision+speech) - MiniCPM-o 2.6 (7.6B omni-modal) - MiniCPM5-1B (text) - MiniCPM4.1-8B (text) - MiniCPM4-8B (text) - MiniCPM3-4B (text) All sha256 checksums sourced from HuggingFace LFS metadata. Signed-off-by: Dennis Huang <huangsiyuan20060408@hotmail.com>	2026-07-06 21:39:12 +02:00
LocalAI [bot]	29db4ab414	fix(ci): shard single-arch backend matrix under GitHub's 256-job limit (#10703 ) GitHub Actions refuses to instantiate a matrix that would generate more than 256 jobs. It does so silently: the job hangs forever at "Waiting for pending jobs" and the whole run is marked `failure` while every other job stays green. This is exactly what happened on the v4.6.1 tag build (run 28786533892): the single-arch build matrix had grown to 268 entries, so `backend-jobs-singlearch` (and its downstream merge) never produced a single job, and the release build "failed" with no failing job to point at. The single-arch list is the one that grows unbounded as backends are added, so shard it across a fixed number of matrix jobs (SINGLEARCH_SHARDS=4, ~67 entries each today, headroom to ~1020 backends). Each merge shard `needs:` only its matching build shard, preserving the "merge waits only on its own build" property that keeps slow CUDA/ROCm builds from gating multi-arch manifest assembly. changed-backends.js now emits per-shard matrix/has-* outputs and throws loudly if a shard ever reaches the 256 limit (telling the maintainer to bump SINGLEARCH_SHARDS and add matching job blocks) instead of letting GitHub drop the overflow silently. backend.yml and backend_pr.yml define the four build + four merge shard jobs; multi-arch and darwin groups are untouched. Assisted-by: Claude:claude-opus-4-8 [Claude Code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>	2026-07-06 21:38:12 +02:00