ci: run only cublas on selfhosted (#1224)

* ci: run only cublas on selfhosted

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* debug

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* update git

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* change testing embeddings model link

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

.github/workflows/image.yml

@@ -24,45 +24,52 @@ jobs:
             tag-latest: 'auto'
             tag-suffix: ''
             ffmpeg: ''
-          - build-type: 'cublas'
-            cuda-major-version: 11
-            cuda-minor-version: 7
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda11'
-            ffmpeg: ''
-          - build-type: 'cublas'
-            cuda-major-version: 12
-            cuda-minor-version: 1
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda12'
-            ffmpeg: ''
           - build-type: ''
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-ffmpeg'
             ffmpeg: 'true'
-          - build-type: 'cublas'
-            cuda-major-version: 11
-            cuda-minor-version: 7
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda11-ffmpeg'
-            ffmpeg: 'true'
-          - build-type: 'cublas'
-            cuda-major-version: 12
-            cuda-minor-version: 1
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda12-ffmpeg'
-            ffmpeg: 'true'
 
-    runs-on: docker-build
+    runs-on: ubuntu-latest
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-
+      - name: Release space from worker
+        run: |
+          echo "Listing top largest packages"
+          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
+          head -n 30 <<< "${pkgs}"
+          echo
+          df -h
+          echo
+          sudo apt-get remove -y '^llvm-.*|^libllvm.*' || true
+          sudo apt-get remove --auto-remove android-sdk-platform-tools || true
+          sudo apt-get purge --auto-remove android-sdk-platform-tools || true
+          sudo rm -rf /usr/local/lib/android
+          sudo apt-get remove -y '^dotnet-.*|^aspnetcore-.*' || true
+          sudo rm -rf /usr/share/dotnet
+          sudo apt-get remove -y '^mono-.*' || true
+          sudo apt-get remove -y '^ghc-.*' || true
+          sudo apt-get remove -y '.*jdk.*|.*jre.*' || true
+          sudo apt-get remove -y 'php.*' || true
+          sudo apt-get remove -y hhvm powershell firefox monodoc-manual msbuild || true
+          sudo apt-get remove -y '^google-.*' || true
+          sudo apt-get remove -y azure-cli || true
+          sudo apt-get remove -y '^mongo.*-.*|^postgresql-.*|^mysql-.*|^mssql-.*' || true
+          sudo apt-get remove -y '^gfortran-.*' || true
+          sudo apt-get remove -y microsoft-edge-stable || true
+          sudo apt-get remove -y firefox || true
+          sudo apt-get remove -y powershell || true
+          sudo apt-get remove -y r-base-core || true
+          sudo apt-get autoremove -y
+          sudo apt-get clean
+          echo
+          echo "Listing top largest packages"
+          pkgs=$(dpkg-query -Wf '${Installed-Size}\t${Package}\t${Status}\n' | awk '$NF == "installed"{print $1 "\t" $2}' | sort -nr)
+          head -n 30 <<< "${pkgs}"
+          echo
+          sudo rm -rfv build || true
+          df -h
       - name: Docker meta
         id: meta
         uses: docker/metadata-action@v5
@@ -108,6 +115,98 @@ jobs:
           push: ${{ github.event_name != 'pull_request' }}
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
+
+
+  docker-gpu:
+    strategy:
+      matrix:
+        include:
+          - build-type: 'cublas'
+            cuda-major-version: 11
+            cuda-minor-version: 7
+            platforms: 'linux/amd64'
+            tag-latest: 'false'
+            tag-suffix: '-cublas-cuda11'
+            ffmpeg: ''
+          - build-type: 'cublas'
+            cuda-major-version: 12
+            cuda-minor-version: 1
+            platforms: 'linux/amd64'
+            tag-latest: 'false'
+            tag-suffix: '-cublas-cuda12'
+            ffmpeg: ''
+          - build-type: 'cublas'
+            cuda-major-version: 11
+            cuda-minor-version: 7
+            platforms: 'linux/amd64'
+            tag-latest: 'false'
+            tag-suffix: '-cublas-cuda11-ffmpeg'
+            ffmpeg: 'true'
+          - build-type: 'cublas'
+            cuda-major-version: 12
+            cuda-minor-version: 1
+            platforms: 'linux/amd64'
+            tag-latest: 'false'
+            tag-suffix: '-cublas-cuda12-ffmpeg'
+            ffmpeg: 'true'
+
+    runs-on: arc-runner-set 
+    steps:
+      - name: Force Install GIT latest
+        run: |
+          sudo apt-get update \
+          && sudo apt-get install -y software-properties-common \
+          && sudo apt-get update \
+          && sudo add-apt-repository -y ppa:git-core/ppa \
+          && sudo apt-get update \
+          && sudo apt-get install -y git
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: quay.io/go-skynet/local-ai
+          tags: |
+            type=ref,event=branch
+            type=semver,pattern={{raw}}
+            type=sha
+          flavor: |
+            latest=${{ matrix.tag-latest }}
+            suffix=${{ matrix.tag-suffix }}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@master
+        with:
+          platforms: all
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@master
+
+      - name: Login to DockerHub
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          registry: quay.io
+          username: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+          password: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+      - name: Build and push
+        uses: docker/build-push-action@v5
+        with:
+          builder: ${{ steps.buildx.outputs.name }}
+          build-args: |
+            BUILD_TYPE=${{ matrix.build-type }}
+            CUDA_MAJOR_VERSION=${{ matrix.cuda-major-version }}
+            CUDA_MINOR_VERSION=${{ matrix.cuda-minor-version }}
+            FFMPEG=${{ matrix.ffmpeg }}
+          context: .
+          file: ./Dockerfile
+          platforms: ${{ matrix.platforms }}
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
       - name: Release space from worker ♻
         if: always()
         run: |

Makefile

@@ -292,7 +292,7 @@ test-models/testmodel:
 	mkdir test-dir
 	wget https://huggingface.co/nnakasato/ggml-model-test/resolve/main/ggml-model-q4.bin -O test-models/testmodel
 	wget https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin -O test-models/whisper-en
-	wget https://huggingface.co/skeskinen/ggml/resolve/main/all-MiniLM-L6-v2/ggml-model-q4_0.bin -O test-models/bert
+	wget https://huggingface.co/mudler/all-MiniLM-L6-v2/resolve/main/ggml-model-q4_0.bin -O test-models/bert
 	wget https://cdn.openai.com/whisper/draft-20220913a/micro-machines.wav -O test-dir/audio.wav
 	wget https://huggingface.co/mudler/rwkv-4-raven-1.5B-ggml/resolve/main/RWKV-4-Raven-1B5-v11-Eng99%2525-Other1%2525-20230425-ctx4096_Q4_0.bin -O test-models/rwkv
 	wget https://raw.githubusercontent.com/saharNooby/rwkv.cpp/5eb8f09c146ea8124633ab041d9ea0b1f1db4459/rwkv/20B_tokenizer.json -O test-models/rwkv.tokenizer.json

api/api_test.go

@@ -687,7 +687,7 @@ var _ = Describe("API test", func() {
 					Input: []string{"sun", "cat"},
 				},
 			)
-			Expect(err).ToNot(HaveOccurred())
+			Expect(err).ToNot(HaveOccurred(), err)
 			Expect(len(resp.Data[0].Embedding)).To(BeNumerically("==", 384))
 			Expect(len(resp.Data[1].Embedding)).To(BeNumerically("==", 384))