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>

.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

.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

.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') }}

core/cli/chat/session.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"slices"
 	"strings"
 )
 
@@ -58,7 +59,7 @@ func (s *chatSession) Clear() {
 }
 
 func (s *chatSession) SwitchModel(model string) error {
-	if !modelExists(s.models, model) {
+	if !slices.Contains(s.models, model) {
 		return fmt.Errorf("model %q is not available. Use /models to see installed models", model)
 	}
 	s.model = model
@@ -103,18 +104,9 @@ Then start a chat session:
 		b.WriteString("multiple models are available; choose one with --model:\n")
 		b.WriteString(formatChatModelList(models, ""))
 		return "", errors.New(b.String())
-	case !modelExists(models, requested):
+	case !slices.Contains(models, requested):
 		return "", fmt.Errorf("model %q is not available. Use `local-ai models list` and `local-ai models install <model>`, or pass an installed model with --model", requested)
 	default:
 		return requested, nil
 	}
 }
-
-func modelExists(models []string, name string) bool {
-	for _, model := range models {
-		if model == name {
-			return true
-		}
-	}
-	return false
-}

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:

pkg/xsysinfo/clinfo.go

@@ -6,6 +6,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"os/exec"
+	"slices"
 	"strings"
 	"sync"
 	"time"
@@ -49,12 +50,7 @@ type clinfoTypeProp struct {
 }
 
 func (t clinfoTypeProp) isGPU() bool {
-	for _, s := range t.Type {
-		if s == clDeviceTypeGPU {
-			return true
-		}
-	}
-	return false
+	return slices.Contains(t.Type, clDeviceTypeGPU)
 }
 
 // clinfoOnce caches the result for the process lifetime. GPU hardware

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) {