debug

.github/ci/modelslist.go

@@ -75,7 +75,7 @@ var modelPageTemplate string = `
     <div class="container mx-auto px-4 py-4">
         <div class="flex items-center justify-between">
             <div class="flex items-center">
-                <a href="/" class="text-white text-xl font-bold"><img src="https://github.com/mudler/LocalAI/assets/2420543/0966aa2a-166e-4f99-a3e5-6c915fc997dd" alt="LocalAI Logo" class="h-10 mr-3 border-2 border-gray-300 shadow rounded"></a>
+                <a href="/" class="text-white text-xl font-bold"><img src="https://github.com/go-skynet/LocalAI/assets/2420543/0966aa2a-166e-4f99-a3e5-6c915fc997dd" alt="LocalAI Logo" class="h-10 mr-3 border-2 border-gray-300 shadow rounded"></a>
                 <a href="/" class="text-white text-xl font-bold">LocalAI</a>
             </div>
             <!-- Menu button for small screens -->
@@ -92,9 +92,9 @@ var modelPageTemplate string = `
         <!-- Collapsible menu for small screens -->
         <div class="hidden lg:hidden" id="mobile-menu">
             <div class="pt-4 pb-3 border-t border-gray-700">
-
+                
                 <a href="https://localai.io" class="block text-gray-400 hover:text-white px-3 py-2 rounded mt-1" target="_blank" ><i class="fas fa-book-reader pr-2"></i> Documentation</a>
-
+               
             </div>
         </div>
     </div>
@@ -114,17 +114,17 @@ var modelPageTemplate string = `
 
 	<h2 class="text-center text-3xl font-semibold text-gray-100">
 
-	 🖼️ Available {{.AvailableModels}} models</i> <a href="https://localai.io/models/" target="_blank" >
+	 🖼️ Available {{.AvailableModels}} models</i> repositories     <a href="https://localai.io/models/" target="_blank" >
 			<i class="fas fa-circle-info pr-2"></i>
-		</a></h2>
+		</a></h2> 
 
-	<h3>
+	<h3>	  
-	Refer to the Model gallery <a href="https://localai.io/models/" target="_blank" ><i class="fas fa-circle-info pr-2"></i></a> for more information on how to use the models with LocalAI.<br>
+	Refer to <a href="https://localai.io/models" target=_blank> Model gallery</a> for more information on how to use the models with LocalAI.
 
 	You can install models with the CLI command <code>local-ai models install <model-name></code>. or by using the WebUI.
 	</h3>
-
+  
-	<input class="form-control appearance-none block w-full mt-5 px-3 py-2 text-base font-normal text-gray-300 pb-2 mb-5 bg-gray-800 bg-clip-padding border border-solid border-gray-600 rounded transition ease-in-out m-0 focus:text-gray-300 focus:bg-gray-900 focus:border-blue-500 focus:outline-none" type="search"
+	<input class="form-control appearance-none block w-full mt-5 px-3 py-2 text-base font-normal text-gray-300 pb-2 mb-5 bg-gray-800 bg-clip-padding border border-solid border-gray-600 rounded transition ease-in-out m-0 focus:text-gray-300 focus:bg-gray-900 focus:border-blue-500 focus:outline-none" type="search" 
 	id="searchbox" placeholder="Live search keyword..">
 	  <div class="dark grid grid-cols-1 grid-rows-1 md:grid-cols-3 block rounded-lg shadow-secondary-1 dark:bg-surface-dark">
 		{{ range $_, $model := .Models }}
@@ -139,10 +139,10 @@ var modelPageTemplate string = `
 			</div>
 	  		<div class="p-6 text-surface dark:text-white">
 				<h5 class="mb-2 text-xl font-medium leading-tight">{{$model.Name}}</h5>
-
+				
-
+				   
 				<p class="mb-4 text-base truncate">{{ $model.Description }}</p>
-
+		
 			</div>
 			<div class="px-6 pt-4 pb-2">
 
@@ -178,7 +178,7 @@ var modelPageTemplate string = `
                     {{ $model.Description }}
 
                     </p>
-
+                    
                     <p class="text-base leading-relaxed text-gray-500 dark:text-gray-400">
                     To install the model with the CLI, run: <br>
                     <code> local-ai models install {{$model.Name}} </code> <br>
@@ -193,7 +193,7 @@ var modelPageTemplate string = `
                     <ul>
                     {{ range $_, $u := $model.URLs }}
                     <li><a href="{{ $u }}" target=_blank><i class="fa-solid fa-link"></i> {{ $u }}</a></li>
-                    {{ end }}
+                    {{ end }}  
                     </ul>
                     </p>
                 </div>
@@ -209,7 +209,7 @@ var modelPageTemplate string = `
 			</div>
 		</div>
 		</div>
-		{{ end }}
+		{{ end }}      
 
 		</div>
   </div>
@@ -221,10 +221,10 @@ var lazyLoadInstance = new LazyLoad({
 });
 
 let cards = document.querySelectorAll('.box')
-
+    
 function liveSearch() {
     let search_query = document.getElementById("searchbox").value;
-
+    
     //Use innerText if all contents are visible
     //Use textContent for including hidden elements
     for (var i = 0; i < cards.length; i++) {
@@ -238,8 +238,8 @@ function liveSearch() {
 }
 
 //A little delay
-let typingTimer;
+let typingTimer;               
-let typeInterval = 500;
+let typeInterval = 500;  
 let searchInput = document.getElementById('searchbox');
 
 searchInput.addEventListener('keyup', () => {

.github/workflows/image-pr.yml

@@ -32,7 +32,7 @@ jobs:
     strategy:
       # Pushing with all jobs in parallel
       # eats the bandwidth of all the nodes
-      max-parallel: ${{ github.event_name != 'pull_request' && 4 || 8 }}
+      max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
       matrix:
         include:
           - build-type: ''
@@ -46,7 +46,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12-ffmpeg'
@@ -119,7 +119,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12-ffmpeg-core'
@@ -127,13 +127,4 @@ jobs:
             image-type: 'core'
             runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
-            makeflags: "--jobs=4 --output-sync=target"
+            makeflags: "--jobs=4 --output-sync=target"
-          - build-type: 'vulkan'
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-vulkan-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=4 --output-sync=target"

.github/workflows/image.yml

@@ -39,7 +39,7 @@ jobs:
     strategy:
       # Pushing with all jobs in parallel
       # eats the bandwidth of all the nodes
-      max-parallel: ${{ github.event_name != 'pull_request' && 6 || 10 }}
+      max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
       matrix:
         include:
           # Extra images
@@ -64,7 +64,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
-            cuda-minor-version: "8"
+            cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda11'
@@ -75,7 +75,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12'
@@ -86,7 +86,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
-            cuda-minor-version: "8"
+            cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-cublas-cuda11-ffmpeg'
@@ -100,7 +100,7 @@ jobs:
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-cublas-cuda12-ffmpeg'
@@ -232,7 +232,7 @@ jobs:
             grpc-base-image: "ubuntu:22.04"
             runs-on: 'arc-runner-set'
             makeflags: "--jobs=3 --output-sync=target"
-
+  
   core-image-build:
     uses: ./.github/workflows/image_build.yml
     with:
@@ -257,7 +257,6 @@ jobs:
       quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
       quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
     strategy:
-      max-parallel: ${{ github.event_name != 'pull_request' && 2 || 4 }}
       matrix:
         include:
           - build-type: ''
@@ -267,62 +266,52 @@ jobs:
             ffmpeg: 'true'
             image-type: 'core'
             base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
             aio: "-aio-cpu"
             latest-image: 'latest-cpu'
             latest-image-aio: 'latest-aio-cpu'
             makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
-            cuda-minor-version: "8"
+            cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda11-core'
             ffmpeg: ''
             image-type: 'core'
             base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
             makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12-core'
             ffmpeg: ''
             image-type: 'core'
             base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
             makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
-            cuda-minor-version: "8"
+            cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda11-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
             base-image: "ubuntu:22.04"
             makeflags: "--jobs=4 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "5"
+            cuda-minor-version: "1"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-cublas-cuda12-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
-            runs-on: 'arc-runner-set'
+            runs-on: 'ubuntu-latest'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=4 --output-sync=target"
-          - build-type: 'vulkan'
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-vulkan-ffmpeg-core'
-            latest-image: 'latest-vulkan-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'arc-runner-set'
             base-image: "ubuntu:22.04"
             makeflags: "--jobs=4 --output-sync=target"

.github/workflows/image_build.yml

@@ -19,11 +19,11 @@ on:
         type: string
       cuda-major-version:
         description: 'CUDA major version'
-        default: "12"
+        default: "11"
         type: string
       cuda-minor-version:
         description: 'CUDA minor version'
-        default: "5"
+        default: "7"
         type: string
       platforms:
         description: 'Platforms'
@@ -324,7 +324,7 @@ jobs:
           docker pull quay.io/go-skynet/local-ai:${{ steps.meta_aio.outputs.version }}
           docker tag quay.io/go-skynet/local-ai:${{ steps.meta_aio.outputs.version }} quay.io/go-skynet/local-ai:${{ inputs.latest-image-aio }}
           docker push quay.io/go-skynet/local-ai:${{ inputs.latest-image-aio }}
-
+  
       - name: job summary
         run: |
           echo "Built image: ${{ steps.meta.outputs.labels }}" >> $GITHUB_STEP_SUMMARY

.github/workflows/release.yaml

@@ -40,7 +40,7 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y cuda-cross-aarch64 cuda-nvcc-cross-aarch64-${CUDA_VERSION} libcublas-cross-aarch64-${CUDA_VERSION}
         env:
-          CUDA_VERSION: 12-5
+          CUDA_VERSION: 12-4
       - name: Cache grpc
         id: cache-grpc
         uses: actions/cache@v4
@@ -100,14 +100,7 @@ jobs:
           go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.0
           export PATH=$PATH:$GOPATH/bin
           export PATH=/usr/local/cuda/bin:$PATH
-          sudo rm -rf /usr/aarch64-linux-gnu/lib/libstdc++.so.6
+          GO_TAGS=p2p GOOS=linux GOARCH=arm64 CMAKE_ARGS="-DProtobuf_INCLUDE_DIRS=$CROSS_STAGING_PREFIX/include -DProtobuf_DIR=$CROSS_STAGING_PREFIX/lib/cmake/protobuf -DgRPC_DIR=$CROSS_STAGING_PREFIX/lib/cmake/grpc -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++" make dist-cross-linux-arm64
-          sudo cp -rf /usr/aarch64-linux-gnu/lib/libstdc++.so* /usr/aarch64-linux-gnu/lib/libstdc++.so.6
-          sudo cp /usr/aarch64-linux-gnu/lib/ld-linux-aarch64.so.1 ld.so
-          GO_TAGS=p2p \
-          BACKEND_LIBS="./grpc/cmake/cross_build/third_party/re2/libre2.a ./grpc/cmake/cross_build/libgrpc.a ./grpc/cmake/cross_build/libgrpc++.a ./grpc/cmake/cross_build/third_party/protobuf/libprotobuf.a /usr/aarch64-linux-gnu/lib/libc.so.6 /usr/aarch64-linux-gnu/lib/libstdc++.so.6 /usr/aarch64-linux-gnu/lib/libgomp.so.1 /usr/aarch64-linux-gnu/lib/libm.so.6 /usr/aarch64-linux-gnu/lib/libgcc_s.so.1 /usr/aarch64-linux-gnu/lib/libdl.so.2 /usr/aarch64-linux-gnu/lib/libpthread.so.0 ./ld.so" \
-          GOOS=linux \
-          GOARCH=arm64 \
-          CMAKE_ARGS="-DProtobuf_INCLUDE_DIRS=$CROSS_STAGING_PREFIX/include -DProtobuf_DIR=$CROSS_STAGING_PREFIX/lib/cmake/protobuf -DgRPC_DIR=$CROSS_STAGING_PREFIX/lib/cmake/grpc -DCMAKE_TOOLCHAIN_FILE=$CMAKE_CROSS_TOOLCHAIN -DCMAKE_C_COMPILER=aarch64-linux-gnu-gcc -DCMAKE_CXX_COMPILER=aarch64-linux-gnu-g++" make dist-cross-linux-arm64
       - uses: actions/upload-artifact@v4
         with:
           name: LocalAI-linux-arm64
@@ -118,13 +111,7 @@ jobs:
         with:
           files: |
             release/*
-      - name: Setup tmate session if tests fail
+
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
   build-linux:
     runs-on: arc-runner-set
     steps:
@@ -167,15 +154,15 @@ jobs:
           ROCM_VERSION: "6.1"
           AMDGPU_VERSION: "6.1"
         run: |
-            set -ex
+            set -ex 
 
             sudo apt-get update
-            sudo DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends ca-certificates curl libnuma-dev gnupg
+            sudo DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends ca-certificates curl libnuma-dev gnupg 
-
+            
-            curl -sL https://repo.radeon.com/rocm/rocm.gpg.key | sudo apt-key add -
+            curl -sL https://repo.radeon.com/rocm/rocm.gpg.key | sudo apt-key add - 
-
+              
             printf "deb [arch=amd64] https://repo.radeon.com/rocm/apt/$ROCM_VERSION/ jammy main" | sudo tee /etc/apt/sources.list.d/rocm.list
-
+            
             printf "deb [arch=amd64] https://repo.radeon.com/amdgpu/$AMDGPU_VERSION/ubuntu jammy main" | sudo tee /etc/apt/sources.list.d/amdgpu.list
             printf 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
             sudo apt-get update
@@ -183,10 +170,10 @@ jobs:
             sudo DEBIAN_FRONTEND=noninteractive apt-get install -y \
                 hipblas-dev rocm-dev \
                 rocblas-dev
-
+          
             sudo apt-get clean
             sudo rm -rf /var/lib/apt/lists/*
-            sudo ldconfig
+            sudo ldconfig 
       - name: Cache grpc
         id: cache-grpc
         uses: actions/cache@v4
@@ -203,7 +190,6 @@ jobs:
       - name: Install gRPC
         run: |
           cd grpc && cd cmake/build && sudo make --jobs 5 --output-sync=target install
-      # BACKEND_LIBS needed for gpu-workload: /opt/intel/oneapi/*/lib/libiomp5.so /opt/intel/oneapi/*/lib/libmkl_core.so /opt/intel/oneapi/*/lib/libmkl_core.so.2 /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so /opt/intel/oneapi/*/lib/libmkl_intel_ilp64.so.2 /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so /opt/intel/oneapi/*/lib/libmkl_sycl_blas.so.4 /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so /opt/intel/oneapi/*/lib/libmkl_tbb_thread.so.2 /opt/intel/oneapi/*/lib/libsycl.so /opt/intel/oneapi/*/lib/libsycl.so.7 /opt/intel/oneapi/*/lib/libsycl.so.7.1.0 /opt/rocm-*/lib/libamdhip64.so /opt/rocm-*/lib/libamdhip64.so.5 /opt/rocm-*/lib/libamdhip64.so.6 /opt/rocm-*/lib/libamdhip64.so.6.1.60100 /opt/rocm-*/lib/libhipblas.so /opt/rocm-*/lib/libhipblas.so.2 /opt/rocm-*/lib/libhipblas.so.2.1.60100 /opt/rocm-*/lib/librocblas.so /opt/rocm-*/lib/librocblas.so.4 /opt/rocm-*/lib/librocblas.so.4.1.60100 /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1 /usr/lib/x86_64-linux-gnu/libOpenCL.so.1.0.0 /usr/lib/x86_64-linux-gnu/libm.so.6 /usr/lib/x86_64-linux-gnu/libgcc_s.so.1 /usr/lib/x86_64-linux-gnu/libc.so.6 /usr/lib/x86_64-linux-gnu/librt.so.1 /usr/local/cuda-*/targets/x86_64-linux/lib/libcublas.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcublasLt.so /usr/local/cuda-*/targets/x86_64-linux/lib/libcudart.so /usr/local/cuda-*/targets/x86_64-linux/lib/stubs/libcuda.so
       - name: Build
         id: build
         run: |
@@ -213,10 +199,7 @@ jobs:
           export PATH=/usr/local/cuda/bin:$PATH
           export PATH=/opt/rocm/bin:$PATH
           source /opt/intel/oneapi/setvars.sh
-          sudo cp /lib64/ld-linux-x86-64.so.2 ld.so
+          GO_TAGS=p2p make -j4 dist
-          GO_TAGS=p2p \
-          BACKEND_LIBS="./ld.so /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /usr/lib/x86_64-linux-gnu/libm.so.6 /usr/lib/x86_64-linux-gnu/libgcc_s.so.1 /usr/lib/x86_64-linux-gnu/libc.so.6 /usr/lib/x86_64-linux-gnu/libgomp.so.1" \
-          make -j4 dist
       - uses: actions/upload-artifact@v4
         with:
           name: LocalAI-linux
@@ -227,13 +210,7 @@ jobs:
         with:
           files: |
             release/*
-      - name: Setup tmate session if tests fail
+
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
   build-stablediffusion:
     runs-on: ubuntu-latest
     steps:
@@ -272,6 +249,11 @@ jobs:
   build-macOS-arm64:
     runs-on: macos-14
     steps:
+      - name: Setup tmate session if tests fail
+        uses: mxschmitt/action-tmate@v3.18
+        with:
+          connect-timeout-seconds: 180
+          limit-access-to-actor: true
       - name: Clone
         uses: actions/checkout@v4
         with:
@@ -291,8 +273,7 @@ jobs:
           export C_INCLUDE_PATH=/usr/local/include
           export CPLUS_INCLUDE_PATH=/usr/local/include
           export PATH=$PATH:$GOPATH/bin
-
+          GO_TAGS=p2p make dist
-          BACKEND_LIBS="$(ls /opt/homebrew/opt/grpc/lib/*.dylib /opt/homebrew/opt/re2/lib/*.dylib /opt/homebrew/opt/openssl@3/lib/*.dylib /opt/homebrew/opt/protobuf/lib/*.dylib /opt/homebrew/opt/abseil/lib/*.dylib | xargs)" GO_TAGS=p2p make dist
       - uses: actions/upload-artifact@v4
         with:
           name: LocalAI-MacOS-arm64
@@ -303,10 +284,3 @@ jobs:
         with:
           files: |
             release/*
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.18
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true

.github/workflows/test.yml

@@ -220,7 +220,7 @@ jobs:
           export CPLUS_INCLUDE_PATH=/usr/local/include
           # Used to run the newer GNUMake version from brew that supports --output-sync
           export PATH="/opt/homebrew/opt/make/libexec/gnubin:$PATH"
-          BUILD_TYPE="GITHUB_CI_HAS_BROKEN_METAL" CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF" make --jobs 4 --output-sync=target test
+          BUILD_TYPE="GITHUB_CI_HAS_BROKEN_METAL" CMAKE_ARGS="-DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF" make --jobs 4 --output-sync=target test
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
         uses: mxschmitt/action-tmate@v3.18

Dockerfile

@@ -5,12 +5,6 @@ ARG INTEL_BASE_IMAGE=${BASE_IMAGE}
 
 # The requirements-core target is common to all images.  It should not be placed in requirements-core unless every single build will use it.
 FROM ${BASE_IMAGE} AS requirements-core
-# TODO(mudler): install all accellerators here
-# and use make dist instead of build.
-# TODO(mudler): modify make dist to build also go-piper and stablediffusion
-# This way the same binary can work for everything(!)
-# TODO(mudler): also make sure that we bundle all the required libs in the backend-assets/lib
-# For the GPU-accell we are going to generate a tar file instead that will be extracted by the bash installer, and the libs will also be installed in the final docker image, so no need to pull ALL the dependencies
 
 USER root
 
@@ -39,7 +33,7 @@ RUN curl -L -s https://go.dev/dl/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz | ta
 ENV PATH $PATH:/root/go/bin:/usr/local/go/bin
 
 # Install grpc compilers
-RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2 && \
+RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.1 && \
     go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
 
 COPY --chmod=644 custom-ca-certs/* /usr/local/share/ca-certificates/
@@ -55,12 +49,10 @@ ENV PATH /usr/local/cuda/bin:${PATH}
 # HipBLAS requirements
 ENV PATH /opt/rocm/bin:${PATH}
 
-# OpenBLAS requirements and stable diffusion, tts (espeak)
+# OpenBLAS requirements and stable diffusion
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
         libopenblas-dev \
-        espeak-ng \
-        espeak \
         libopencv-dev && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
@@ -85,6 +77,8 @@ ENV PATH="/root/.cargo/bin:${PATH}"
 RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
+        espeak-ng \
+        espeak \
         python3-pip \
         python-is-python3 \
         python3-dev \
@@ -99,31 +93,16 @@ RUN pip install --user grpcio-tools
 ###################################
 ###################################
 
-# Base image for the build-type. 
+# The requirements-drivers target is for BUILD_TYPE specific items.  If you need to install something specific to CUDA, or specific to ROCM, it goes here.
-FROM requirements-${IMAGE_TYPE} AS run-requirements-drivers
+# This target will be built on top of requirements-core or requirements-extras as retermined by the IMAGE_TYPE build-arg
+FROM requirements-${IMAGE_TYPE} AS requirements-drivers
 
 ARG BUILD_TYPE
-ARG CUDA_MAJOR_VERSION=12
+ARG CUDA_MAJOR_VERSION=11
-ARG CUDA_MINOR_VERSION=5
+ARG CUDA_MINOR_VERSION=8
 
 ENV BUILD_TYPE=${BUILD_TYPE}
 
-# Vulkan requirements
-RUN <<EOT bash
-    if [ "${BUILD_TYPE}" = "vulkan" ]; then
-        apt-get update && \
-        apt-get install -y  --no-install-recommends \
-                        software-properties-common pciutils wget gpg-agent && \
-        wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
-        wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
-        apt-get update && \
-            apt-get install -y \
-            vulkan-sdk && \
-        apt-get clean && \
-        rm -rf /var/lib/apt/lists/*
-    fi
-EOT
-
 # CuBLAS requirements
 RUN <<EOT bash
     if [ "${BUILD_TYPE}" = "cublas" ]; then
@@ -191,82 +170,6 @@ RUN if [ "${BUILD_TYPE}" = "hipblas" ]; then \
         ldconfig \
     ; fi
 
-# The build-requirements-drivers target is for BUILD_TYPE specific items.  If you need to install something specific to CUDA, or specific to ROCM, it goes here.
-# This target will be built on top of requirements-core or requirements-extras as retermined by the IMAGE_TYPE build-arg
-FROM requirements-${IMAGE_TYPE} AS build-requirements-drivers
-
-ARG BUILD_TYPE
-ARG CUDA_MAJOR_VERSION=12
-ARG CUDA_MINOR_VERSION=5
-
-ENV BUILD_TYPE=${BUILD_TYPE}
-
-# Vulkan requirements
-RUN <<EOT bash
-        apt-get update && \
-        apt-get install -y  --no-install-recommends \
-                        software-properties-common pciutils wget gpg-agent && \
-        wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
-        wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
-        apt-get update && \
-            apt-get install -y \
-            vulkan-sdk && \
-        apt-get clean && \
-        rm -rf /var/lib/apt/lists/*
-EOT
-
-# CuBLAS requirements
-RUN <<EOT bash
-    apt-get update && \
-    apt-get install -y  --no-install-recommends \
-                    software-properties-common pciutils
-    if [ "amd64" = "$TARGETARCH" ]; then
-        curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
-        fi
-    if [ "arm64" = "$TARGETARCH" ]; then
-        curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/arm64/cuda-keyring_1.1-1_all.deb
-    fi
-    dpkg -i cuda-keyring_1.1-1_all.deb && \
-        rm -f cuda-keyring_1.1-1_all.deb && \
-        apt-get update && \
-        apt-get install -y --no-install-recommends \
-            cuda-nvcc-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
-            libcufft-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
-            libcurand-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
-            libcublas-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
-            libcusparse-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} \
-            libcusolver-dev-${CUDA_MAJOR_VERSION}-${CUDA_MINOR_VERSION} && \
-        apt-get clean && \
-    rm -rf /var/lib/apt/lists/*
-EOT
-
-# clblas
-RUN apt-get update && \
-        apt-get install -y --no-install-recommends \
-            libclblast-dev && \
-        apt-get clean && \
-        rm -rf /var/lib/apt/lists/*
-
-# intel
-RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list && apt update && apt install -y intel-basekit && apt-get clean && \
-rm -rf /var/lib/apt/lists/*
-
-# hipblas
-RUN wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | \
-        gpg --dearmor | tee /etc/apt/keyrings/rocm.gpg > /dev/null && apt-get update && \
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/6.1.2/ubuntu jammy main" \
-        | tee /etc/apt/sources.list.d/amdgpu.list && \
-        echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/6.1.2 jammy main" |  tee --append /etc/apt/sources.list.d/rocm.list && printf 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | tee /etc/apt/preferences.d/rocm-pin-600 && \
-        apt update && \
-        apt-get install -y --no-install-recommends \
-            hipblas-dev rocm-dev \
-            rocblas-dev && \
-        apt-get clean && \
-        rm -rf /var/lib/apt/lists/* && \
-        # I have no idea why, but the ROCM lib packages don't trigger ldconfig after they install, which results in local-ai and others not being able
-        # to locate the libraries. We run ldconfig ourselves to work around this packaging deficiency
-        ldconfig
-
 ###################################
 ###################################
 
@@ -318,7 +221,7 @@ RUN git clone --recurse-submodules --jobs 4 -b ${GRPC_VERSION} --depth 1 --shall
 
 # The builder target compiles LocalAI. This target is not the target that will be uploaded to the registry.
 # Adjustments to the build process should likely be made here.
-FROM build-requirements-drivers AS builder
+FROM requirements-drivers AS builder
 
 ARG GO_TAGS="stablediffusion tts p2p"
 ARG GRPC_BACKENDS
@@ -363,8 +266,7 @@ COPY --from=grpc /opt/grpc /usr/local
 
 # Rebuild with defaults backends
 WORKDIR /build
-# Need to build tts and stablediffusion separately first (?)
+RUN make build
-RUN make dist && rm release/*.sha256 && mv release/* local-ai
 
 RUN if [ ! -d "/build/sources/go-piper/piper-phonemize/pi/lib/" ]; then \
         mkdir -p /build/sources/go-piper/piper-phonemize/pi/lib/ \
@@ -376,7 +278,7 @@ RUN if [ ! -d "/build/sources/go-piper/piper-phonemize/pi/lib/" ]; then \
 
 # This is the final target. The result of this target will be the image uploaded to the registry.
 # If you cannot find a more suitable place for an addition, this layer is a suitable place for it.
-FROM run-requirements-drivers
+FROM requirements-drivers
 
 ARG FFMPEG
 ARG BUILD_TYPE
@@ -390,7 +292,7 @@ ENV REBUILD=false
 ENV HEALTHCHECK_ENDPOINT=http://localhost:8080/readyz
 ENV MAKEFLAGS=${MAKEFLAGS}
 
-ARG CUDA_MAJOR_VERSION=12
+ARG CUDA_MAJOR_VERSION=11
 ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
 ENV NVIDIA_REQUIRE_CUDA="cuda>=${CUDA_MAJOR_VERSION}.0"
 ENV NVIDIA_VISIBLE_DEVICES=all
@@ -421,7 +323,6 @@ RUN make prepare-sources
 COPY --from=builder /build/local-ai ./
 
 # Copy shared libraries for piper
-# TODO(mudler): bundle these libs in backend-assets/lib/ (like we do for llama.cpp deps)
 COPY --from=builder /build/sources/go-piper/piper-phonemize/pi/lib/* /usr/lib/
 
 # do not let stablediffusion rebuild (requires an older version of absl)

Makefile

@@ -5,7 +5,7 @@ BINARY_NAME=local-ai
 
 # llama.cpp versions
 GOLLAMA_STABLE_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=9ef07800622e4c371605f9419864d15667c3558f
+CPPLLAMA_VERSION?=172c8256840ffd882ab9992ecedbb587d9b21f15
 
 # gpt4all version
 GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
@@ -54,7 +54,7 @@ override LD_FLAGS += -X "github.com/go-skynet/LocalAI/internal.Commit=$(shell gi
 
 OPTIONAL_TARGETS?=
 
-export OS := $(shell uname -s)
+OS := $(shell uname -s)
 ARCH := $(shell uname -m)
 GREEN  := $(shell tput -Txterm setaf 2)
 YELLOW := $(shell tput -Txterm setaf 3)
@@ -80,8 +80,8 @@ ifeq ($(OS),Darwin)
 		BUILD_TYPE=metal
 	# disable metal if on Darwin and any other value is explicitly passed.
 	else ifneq ($(BUILD_TYPE),metal)
-		CMAKE_ARGS+=-DGGML_METAL=OFF
+		CMAKE_ARGS+=-DLLAMA_METAL=OFF
-		export GGML_NO_ACCELERATE=1
+		export LLAMA_NO_ACCELERATE=1
 	endif
 
 	ifeq ($(BUILD_TYPE),metal)
@@ -98,15 +98,11 @@ endif
 
 ifeq ($(BUILD_TYPE),cublas)
 	CGO_LDFLAGS+=-lcublas -lcudart -L$(CUDA_LIBPATH)
-	export GGML_CUDA=1
+	export LLAMA_CUBLAS=1
 	export WHISPER_CUDA=1
 	CGO_LDFLAGS_WHISPER+=-L$(CUDA_LIBPATH)/stubs/ -lcuda -lcufft
 endif
 
-ifeq ($(BUILD_TYPE),vulkan)
-	CMAKE_ARGS+=-DGGML_VULKAN=1
-endif
-
 ifeq ($(BUILD_TYPE),hipblas)
 	ROCM_HOME ?= /opt/rocm
 	ROCM_PATH ?= /opt/rocm
@@ -118,13 +114,13 @@ ifeq ($(BUILD_TYPE),hipblas)
 	export WHISPER_HIPBLAS=1
 	GPU_TARGETS ?= gfx900,gfx906,gfx908,gfx940,gfx941,gfx942,gfx90a,gfx1030,gfx1031,gfx1100,gfx1101
 	AMDGPU_TARGETS ?= "$(GPU_TARGETS)"
-	CMAKE_ARGS+=-DGGML_HIPBLAS=ON -DAMDGPU_TARGETS="$(AMDGPU_TARGETS)" -DGPU_TARGETS="$(GPU_TARGETS)"
+	CMAKE_ARGS+=-DLLAMA_HIPBLAS=ON -DAMDGPU_TARGETS="$(AMDGPU_TARGETS)" -DGPU_TARGETS="$(GPU_TARGETS)"
 	CGO_LDFLAGS += -O3 --rtlib=compiler-rt -unwindlib=libgcc -lhipblas -lrocblas --hip-link -L${ROCM_HOME}/lib/llvm/lib
 endif
 
 ifeq ($(BUILD_TYPE),metal)
 	CGO_LDFLAGS+=-framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
-	export GGML_METAL=1
+	export LLAMA_METAL=1
 	export WHISPER_METAL=1
 endif
 
@@ -317,10 +313,6 @@ build: prepare backend-assets grpcs ## Build the project
 	$(info ${GREEN}I BUILD_TYPE: ${YELLOW}$(BUILD_TYPE)${RESET})
 	$(info ${GREEN}I GO_TAGS: ${YELLOW}$(GO_TAGS)${RESET})
 	$(info ${GREEN}I LD_FLAGS: ${YELLOW}$(LD_FLAGS)${RESET})
-ifneq ($(BACKEND_LIBS),)
-	$(MAKE) backend-assets/lib
-	cp $(BACKEND_LIBS) backend-assets/lib/
-endif
 	CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o $(BINARY_NAME) ./
 
 build-minimal:
@@ -329,22 +321,17 @@ build-minimal:
 build-api:
 	BUILD_GRPC_FOR_BACKEND_LLAMA=true BUILD_API_ONLY=true GO_TAGS=none $(MAKE) build
 
-backend-assets/lib:
-	mkdir -p backend-assets/lib
-
 dist:
-	$(MAKE) backend-assets/grpc/llama-cpp-avx2
+	STATIC=true $(MAKE) backend-assets/grpc/llama-cpp-avx2
 ifeq ($(OS),Darwin)
 	$(info ${GREEN}I Skip CUDA/hipblas build on MacOS${RESET})
 else
-ifneq ($(ARCH),arm64)
 	$(MAKE) backend-assets/grpc/llama-cpp-cuda
 	$(MAKE) backend-assets/grpc/llama-cpp-hipblas
 	$(MAKE) backend-assets/grpc/llama-cpp-sycl_f16
 	$(MAKE) backend-assets/grpc/llama-cpp-sycl_f32
 endif
-endif
+	$(MAKE) build
-	STATIC=true $(MAKE) build
 	mkdir -p release
 # if BUILD_ID is empty, then we don't append it to the binary name
 ifeq ($(BUILD_ID),)
@@ -356,8 +343,8 @@ else
 endif
 
 dist-cross-linux-arm64: 
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_NATIVE=off" GRPC_BACKENDS="backend-assets/grpc/llama-cpp-fallback backend-assets/grpc/llama-cpp-grpc backend-assets/util/llama-cpp-rpc-server" \
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_NATIVE=off" GRPC_BACKENDS="backend-assets/grpc/llama-cpp-fallback backend-assets/grpc/llama-cpp-grpc backend-assets/util/llama-cpp-rpc-server" \
-	STATIC=true $(MAKE) build
+	$(MAKE) build
 	mkdir -p release
 # if BUILD_ID is empty, then we don't append it to the binary name
 ifeq ($(BUILD_ID),)
@@ -406,7 +393,7 @@ prepare-e2e:
 	mkdir -p $(TEST_DIR)
 	cp -rfv $(abspath ./tests/e2e-fixtures)/gpu.yaml $(TEST_DIR)/gpu.yaml
 	test -e $(TEST_DIR)/ggllm-test-model.bin || wget -q https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q2_K.gguf -O $(TEST_DIR)/ggllm-test-model.bin
-	docker build --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=5 --build-arg FFMPEG=true -t localai-tests .
+	docker build --build-arg GRPC_BACKENDS="$(GRPC_BACKENDS)" --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=11 --build-arg CUDA_MINOR_VERSION=7 --build-arg FFMPEG=true -t localai-tests .
 
 run-e2e-image:
 	ls -liah $(abspath ./tests/e2e-fixtures)
@@ -713,21 +700,21 @@ backend-assets/grpc/llama-cpp-avx2: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-avx2
 	$(MAKE) -C backend/cpp/llama-avx2 purge
 	$(info ${GREEN}I llama-cpp build info:avx2${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-avx2" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_AVX=on -DLLAMA_AVX2=on -DLLAMA_AVX512=off -DLLAMA_FMA=on -DLLAMA_F16C=on" $(MAKE) VARIANT="llama-avx2" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-avx2/grpc-server backend-assets/grpc/llama-cpp-avx2
 
 backend-assets/grpc/llama-cpp-avx: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-avx
 	$(MAKE) -C backend/cpp/llama-avx purge
 	$(info ${GREEN}I llama-cpp build info:avx${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off" $(MAKE) VARIANT="llama-avx" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off" $(MAKE) VARIANT="llama-avx" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-avx/grpc-server backend-assets/grpc/llama-cpp-avx
 
 backend-assets/grpc/llama-cpp-fallback: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-fallback
 	$(MAKE) -C backend/cpp/llama-fallback purge
 	$(info ${GREEN}I llama-cpp build info:fallback${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off" $(MAKE) VARIANT="llama-fallback" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_AVX=off -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off" $(MAKE) VARIANT="llama-fallback" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-fallback/grpc-server backend-assets/grpc/llama-cpp-fallback
 # TODO: every binary should have its own folder instead, so can have different metal implementations
 ifeq ($(BUILD_TYPE),metal)
@@ -738,7 +725,7 @@ backend-assets/grpc/llama-cpp-cuda: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-cuda
 	$(MAKE) -C backend/cpp/llama-cuda purge
 	$(info ${GREEN}I llama-cpp build info:cuda${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_CUDA=ON" $(MAKE) VARIANT="llama-cuda" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off -DLLAMA_CUDA=ON" $(MAKE) VARIANT="llama-cuda" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-cuda/grpc-server backend-assets/grpc/llama-cpp-cuda
 
 backend-assets/grpc/llama-cpp-hipblas: backend-assets/grpc
@@ -766,7 +753,7 @@ backend-assets/grpc/llama-cpp-grpc: backend-assets/grpc
 	cp -rf backend/cpp/llama backend/cpp/llama-grpc
 	$(MAKE) -C backend/cpp/llama-grpc purge
 	$(info ${GREEN}I llama-cpp build info:grpc${RESET})
-	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_RPC=ON -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off" TARGET="--target grpc-server --target rpc-server" $(MAKE) VARIANT="llama-grpc" build-llama-cpp-grpc-server
+	CMAKE_ARGS="$(CMAKE_ARGS) -DLLAMA_RPC=ON -DLLAMA_AVX=off -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off" $(MAKE) VARIANT="llama-grpc" build-llama-cpp-grpc-server
 	cp -rfv backend/cpp/llama-grpc/grpc-server backend-assets/grpc/llama-cpp-grpc
 
 backend-assets/util/llama-cpp-rpc-server: backend-assets/grpc/llama-cpp-grpc
@@ -816,17 +803,6 @@ docker:
 		--build-arg BUILD_TYPE=$(BUILD_TYPE) \
 		-t $(DOCKER_IMAGE) .
 
-docker-cuda11:
-	docker build \
-		--build-arg CUDA_MAJOR_VERSION=11 \
-		--build-arg CUDA_MINOR_VERSION=8 \
-		--build-arg BASE_IMAGE=$(BASE_IMAGE) \
-		--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
-		--build-arg GO_TAGS="$(GO_TAGS)" \
-		--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
-		--build-arg BUILD_TYPE=$(BUILD_TYPE) \
-		-t $(DOCKER_IMAGE)-cuda11 .
-
 docker-aio:
 	@echo "Building AIO image with base $(BASE_IMAGE) as $(DOCKER_AIO_IMAGE)"
 	docker build \

README.md

@@ -48,13 +48,6 @@
 
 ![screen](https://github.com/mudler/LocalAI/assets/2420543/20b5ccd2-8393-44f0-aaf6-87a23806381e)
 
-Run the installer script:
-
-```bash
-curl https://localai.io/install.sh | sh
-```
-
-Or run with docker:
 ```bash
 docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu
 # Alternative images:
@@ -72,7 +65,6 @@ docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu
 
 [Roadmap](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)
 
-- 🆕 You can browse now the model gallery without LocalAI! Check out https://models.localai.io
 - 🔥🔥 Decentralized llama.cpp:  https://github.com/mudler/LocalAI/pull/2343 (peer2peer llama.cpp!) 👉 Docs  https://localai.io/features/distribute/
 - 🔥🔥 Openvoice: https://github.com/mudler/LocalAI/pull/2334
 - 🆕 Function calls without grammars and mixed mode: https://github.com/mudler/LocalAI/pull/2328

backend/backend.proto

@@ -230,7 +230,6 @@ message TranscriptRequest {
   string dst = 2;
   string language = 3;
   uint32 threads = 4;
-  bool translate = 5;
 }
 
 message TranscriptResult {

backend/cpp/llama/Makefile

@@ -4,44 +4,34 @@ LLAMA_VERSION?=
 CMAKE_ARGS?=
 BUILD_TYPE?=
 ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
-TARGET?=--target grpc-server
 
-# Disable Shared libs as we are linking on static gRPC and we can't mix shared and static
+# If build type is cublas, then we set -DLLAMA_CUBLAS=ON to CMAKE_ARGS automatically
-CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
-
-# If build type is cublas, then we set -DGGML_CUDA=ON to CMAKE_ARGS automatically
 ifeq ($(BUILD_TYPE),cublas)
-	CMAKE_ARGS+=-DGGML_CUDA=ON
+	CMAKE_ARGS+=-DLLAMA_CUBLAS=ON
-# If build type is openblas then we set -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+# If build type is openblas then we set -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
 # to CMAKE_ARGS automatically
 else ifeq ($(BUILD_TYPE),openblas)
-	CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+	CMAKE_ARGS+=-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
-# If build type is clblas (openCL) we set -DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
+# If build type is clblas (openCL) we set -DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
 else ifeq ($(BUILD_TYPE),clblas)
-	CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
+	CMAKE_ARGS+=-DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
 # If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++ 
 else ifeq ($(BUILD_TYPE),hipblas)
-	CMAKE_ARGS+=-DGGML_HIPBLAS=ON
+	CMAKE_ARGS+=-DLLAMA_HIPBLAS=ON
-# If it's OSX, DO NOT embed the metal library - -DGGML_METAL_EMBED_LIBRARY=ON requires further investigation
+# If it's OSX, DO NOT embed the metal library - -DLLAMA_METAL_EMBED_LIBRARY=ON requires further investigation
 # But if it's OSX without metal, disable it here
-else ifeq ($(OS),Darwin)
+else ifeq ($(OS),darwin)
 	ifneq ($(BUILD_TYPE),metal)
-		CMAKE_ARGS+=-DGGML_METAL=OFF
+		CMAKE_ARGS+=-DLLAMA_METAL=OFF
-	else
-		CMAKE_ARGS+=-DGGML_METAL=ON
-# Until this is tested properly, we disable embedded metal file
-# as we already embed it as part of the LocalAI assets
-		CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=OFF
-		TARGET+=--target ggml-metal
 	endif
 endif
 
 ifeq ($(BUILD_TYPE),sycl_f16)
-	CMAKE_ARGS+=-DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON
+	CMAKE_ARGS+=-DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON
 endif
 
 ifeq ($(BUILD_TYPE),sycl_f32)
-	CMAKE_ARGS+=-DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
+	CMAKE_ARGS+=-DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
 endif
 
 llama.cpp:
@@ -72,8 +62,8 @@ grpc-server: llama.cpp llama.cpp/examples/grpc-server
 	@echo "Building grpc-server with $(BUILD_TYPE) build type and $(CMAKE_ARGS)"
 ifneq (,$(findstring sycl,$(BUILD_TYPE)))
 	bash -c "source $(ONEAPI_VARS); \
-	cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release $(TARGET)"
+	cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && $(MAKE)"
 else
-	cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release $(TARGET)
+	cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && $(MAKE)
 endif
 	cp llama.cpp/build/bin/grpc-server .

backend/cpp/llama/grpc-server.cpp

@@ -886,8 +886,6 @@ struct llama_server_context
             {"task_id", slot->task_id},
         });
 
-        LOG_TEE("sampling: \n%s\n", llama_sampling_print(slot->sparams).c_str());
-
         return true;
     }
 

backend/go/image/stablediffusion/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/image/stablediffusion/stablediffusion.go

@@ -3,9 +3,9 @@ package main
 // This is a wrapper to statisfy the GRPC service interface
 // It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
 import (
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/stablediffusion"
+	"github.com/go-skynet/LocalAI/pkg/stablediffusion"
 )
 
 type Image struct {

backend/go/image/tinydream/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/image/tinydream/tinydream.go

@@ -3,9 +3,9 @@ package main
 // This is a wrapper to statisfy the GRPC service interface
 // It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
 import (
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/tinydream"
+	"github.com/go-skynet/LocalAI/pkg/tinydream"
 )
 
 type Image struct {

backend/go/llm/bert/bert.go

@@ -5,8 +5,8 @@ package main
 import (
 	bert "github.com/go-skynet/go-bert.cpp"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 )
 
 type Embeddings struct {

backend/go/llm/bert/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/llm/gpt4all/gpt4all.go

@@ -5,8 +5,8 @@ package main
 import (
 	"fmt"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	gpt4all "github.com/nomic-ai/gpt4all/gpt4all-bindings/golang"
 )
 

backend/go/llm/gpt4all/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/llm/langchain/langchain.go

@@ -6,9 +6,9 @@ import (
 	"fmt"
 	"os"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/langchain"
+	"github.com/go-skynet/LocalAI/pkg/langchain"
 )
 
 type LLM struct {

backend/go/llm/langchain/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/llm/llama-ggml/llama.go

@@ -5,9 +5,9 @@ package main
 import (
 	"fmt"
 
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	"github.com/go-skynet/go-llama.cpp"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
 )
 
 type LLM struct {

backend/go/llm/llama-ggml/main.go

@@ -3,7 +3,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/llm/llama/llama.go

@@ -6,9 +6,9 @@ import (
 	"fmt"
 	"path/filepath"
 
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
 	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	"github.com/go-skynet/go-llama.cpp"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
 )
 
 type LLM struct {

backend/go/llm/llama/main.go

@@ -7,7 +7,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/llm/rwkv/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/llm/rwkv/rwkv.go

@@ -7,8 +7,8 @@ import (
 	"path/filepath"
 
 	"github.com/donomii/go-rwkv.cpp"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 )
 
 const tokenizerSuffix = ".tokenizer.json"
@@ -31,7 +31,7 @@ func (llm *LLM) Load(opts *pb.ModelOptions) error {
 	model := rwkv.LoadFiles(opts.ModelFile, tokenizerPath, uint32(opts.GetThreads()))
 
 	if model == nil {
-		return fmt.Errorf("rwkv could not load model")
+		return fmt.Errorf("could not load model")
 	}
 	llm.rwkv = model
 	return nil

backend/go/stores/main.go

@@ -6,7 +6,7 @@ import (
 	"flag"
 	"os"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 )

backend/go/stores/store.go

@@ -8,8 +8,8 @@ import (
 	"math"
 	"slices"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 
 	"github.com/rs/zerolog/log"
 )

backend/go/transcribe/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/transcribe/transcript.go

@@ -8,7 +8,7 @@ import (
 
 	"github.com/ggerganov/whisper.cpp/bindings/go/pkg/whisper"
 	"github.com/go-audio/wav"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
 )
 
 func ffmpegCommand(args []string) (string, error) {
@@ -29,7 +29,7 @@ func audioToWav(src, dst string) error {
 	return nil
 }
 
-func Transcript(model whisper.Model, audiopath, language string, translate bool, threads uint) (schema.TranscriptionResult, error) {
+func Transcript(model whisper.Model, audiopath, language string, threads uint) (schema.TranscriptionResult, error) {
 	res := schema.TranscriptionResult{}
 
 	dir, err := os.MkdirTemp("", "whisper")
@@ -75,10 +75,6 @@ func Transcript(model whisper.Model, audiopath, language string, translate bool,
 		context.SetLanguage("auto")
 	}
 
-	if translate {
-		context.SetTranslate(true)
-	}
-
 	if err := context.Process(data, nil, nil); err != nil {
 		return res, err
 	}

backend/go/transcribe/whisper.go

@@ -4,9 +4,9 @@ package main
 // It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
 import (
 	"github.com/ggerganov/whisper.cpp/bindings/go/pkg/whisper"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 )
 
 type Whisper struct {
@@ -22,5 +22,5 @@ func (sd *Whisper) Load(opts *pb.ModelOptions) error {
 }
 
 func (sd *Whisper) AudioTranscription(opts *pb.TranscriptRequest) (schema.TranscriptionResult, error) {
-	return Transcript(sd.whisper, opts.Dst, opts.Language, opts.Translate, uint(opts.Threads))
+	return Transcript(sd.whisper, opts.Dst, opts.Language, uint(opts.Threads))
 }

backend/go/tts/main.go

@@ -5,7 +5,7 @@ package main
 import (
 	"flag"
 
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	grpc "github.com/go-skynet/LocalAI/pkg/grpc"
 )
 
 var (

backend/go/tts/piper.go

@@ -7,8 +7,8 @@ import (
 	"os"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/pkg/grpc/base"
+	"github.com/go-skynet/LocalAI/pkg/grpc/base"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
 	piper "github.com/mudler/go-piper"
 )
 

backend/python/diffusers/backend.py

@@ -17,7 +17,7 @@ import backend_pb2_grpc
 
 import grpc
 
-from diffusers import StableDiffusion3Pipeline, StableDiffusionXLPipeline, StableDiffusionDepth2ImgPipeline, DPMSolverMultistepScheduler, StableDiffusionPipeline, DiffusionPipeline, EulerAncestralDiscreteScheduler
+from diffusers import StableDiffusionXLPipeline, StableDiffusionDepth2ImgPipeline, DPMSolverMultistepScheduler, StableDiffusionPipeline, DiffusionPipeline, EulerAncestralDiscreteScheduler
 from diffusers import StableDiffusionImg2ImgPipeline, AutoPipelineForText2Image, ControlNetModel, StableVideoDiffusionPipeline
 from diffusers.pipelines.stable_diffusion import safety_checker
 from diffusers.utils import load_image,export_to_video
@@ -225,17 +225,6 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                         torch_dtype=torchType, 
                         use_safetensors=True, 
                         variant=variant)
-            elif request.PipelineType == "StableDiffusion3Pipeline":
-                if fromSingleFile:
-                    self.pipe = StableDiffusion3Pipeline.from_single_file(modelFile,
-                                                               torch_dtype=torchType,
-                                                               use_safetensors=True)
-                else:
-                    self.pipe = StableDiffusion3Pipeline.from_pretrained(
-                        request.Model, 
-                        torch_dtype=torchType, 
-                        use_safetensors=True, 
-                        variant=variant)
 
             if CLIPSKIP and request.CLIPSkip != 0:
                 self.clip_skip = request.CLIPSkip

backend/python/diffusers/requirements.txt

@@ -5,7 +5,6 @@ grpcio==1.64.0
 opencv-python
 pillow
 protobuf
-sentencepiece
 torch
 transformers
-certifi
+certifi

core/application.go

@@ -1,9 +1,9 @@
 package core
 
 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 )
 
 // The purpose of this structure is to hold pointers to all initialized services, to make plumbing easy

core/backend/embeddings.go

@@ -3,10 +3,10 @@ package backend
 import (
 	"fmt"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/pkg/grpc"
+	"github.com/go-skynet/LocalAI/pkg/grpc"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func ModelEmbedding(s string, tokens []int, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (func() ([]float32, error), error) {

core/backend/image.go

@@ -1,10 +1,10 @@
 package backend
 
 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func ImageGeneration(height, width, mode, step, seed int, positive_prompt, negative_prompt, src, dst string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (func() error, error) {

core/backend/llm.go

@@ -9,14 +9,14 @@ import (
 	"sync"
 	"unicode/utf8"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
 
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/grpc"
+	"github.com/go-skynet/LocalAI/pkg/grpc"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 )
 
 type LLMResponse struct {

core/backend/options.go

@@ -5,9 +5,9 @@ import (
 	"os"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	pb "github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 
@@ -142,14 +142,12 @@ func gRPCPredictOpts(c config.BackendConfig, modelPath string) *pb.PredictOption
 		MirostatTAU:         float32(*c.LLMConfig.MirostatTAU),
 		Debug:               *c.Debug,
 		StopPrompts:         c.StopWords,
-		Repeat:              int32(c.RepeatLastN),
+		Repeat:              int32(c.RepeatPenalty),
-		FrequencyPenalty:    float32(c.FrequencyPenalty),
-		PresencePenalty:     float32(c.PresencePenalty),
-		Penalty:             float32(c.RepeatPenalty),
 		NKeep:               int32(c.Keep),
 		Batch:               int32(c.Batch),
 		IgnoreEOS:           c.IgnoreEOS,
 		Seed:                getSeed(c),
+		FrequencyPenalty:    float32(c.FrequencyPenalty),
 		MLock:               *c.MMlock,
 		MMap:                *c.MMap,
 		MainGPU:             c.MainGPU,

core/backend/rerank.go

@@ -4,9 +4,9 @@ import (
 	"context"
 	"fmt"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func Rerank(backend, modelFile string, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, backendConfig config.BackendConfig) (*proto.RerankResult, error) {

core/backend/stores.go

@@ -1,10 +1,10 @@
 package backend
 
 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/pkg/grpc"
+	"github.com/go-skynet/LocalAI/pkg/grpc"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func StoreBackend(sl *model.ModelLoader, appConfig *config.ApplicationConfig, storeName string) (grpc.Backend, error) {

core/backend/transcript.go

@@ -4,14 +4,14 @@ import (
 	"context"
 	"fmt"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
 
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
-func ModelTranscription(audio, language string, translate bool, ml *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (*schema.TranscriptionResult, error) {
+func ModelTranscription(audio, language string, ml *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (*schema.TranscriptionResult, error) {
 
 	opts := modelOpts(backendConfig, appConfig, []model.Option{
 		model.WithBackendString(model.WhisperBackend),
@@ -31,9 +31,8 @@ func ModelTranscription(audio, language string, translate bool, ml *model.ModelL
 	}
 
 	return whisperModel.AudioTranscription(context.Background(), &proto.TranscriptRequest{
-		Dst:       audio,
+		Dst:      audio,
-		Language:  language,
+		Language: language,
-		Translate: translate,
+		Threads:  uint32(*backendConfig.Threads),
-		Threads:   uint32(*backendConfig.Threads),
 	})
 }

core/backend/tts.go

@@ -6,11 +6,11 @@ import (
 	"os"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 )
 
 func generateUniqueFileName(dir, baseName, ext string) string {

core/cli/cli.go

@@ -1,8 +1,8 @@
 package cli
 
 import (
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/cli/worker"
+	"github.com/go-skynet/LocalAI/core/cli/worker"
 )
 
 var CLI struct {

core/cli/models.go

@@ -4,12 +4,10 @@ import (
 	"encoding/json"
 	"fmt"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/startup"
-	"github.com/mudler/LocalAI/pkg/startup"
 	"github.com/rs/zerolog/log"
 	"github.com/schollz/progressbar/v3"
 )
@@ -35,7 +33,7 @@ type ModelsCMD struct {
 }
 
 func (ml *ModelsList) Run(ctx *cliContext.Context) error {
-	var galleries []config.Gallery
+	var galleries []gallery.Gallery
 	if err := json.Unmarshal([]byte(ml.Galleries), &galleries); err != nil {
 		log.Error().Err(err).Msg("unable to load galleries")
 	}
@@ -55,11 +53,10 @@ func (ml *ModelsList) Run(ctx *cliContext.Context) error {
 }
 
 func (mi *ModelsInstall) Run(ctx *cliContext.Context) error {
-	var galleries []config.Gallery
+	var galleries []gallery.Gallery
 	if err := json.Unmarshal([]byte(mi.Galleries), &galleries); err != nil {
 		log.Error().Err(err).Msg("unable to load galleries")
 	}
-
 	for _, modelName := range mi.ModelArgs {
 
 		progressBar := progressbar.NewOptions(
@@ -81,15 +78,13 @@ func (mi *ModelsInstall) Run(ctx *cliContext.Context) error {
 			return err
 		}
 
-		if !downloader.LooksLikeOCI(modelName) {
+		model := gallery.FindModel(models, modelName, mi.ModelsPath)
-			model := gallery.FindModel(models, modelName, mi.ModelsPath)
+		if model == nil {
-			if model == nil {
+			log.Error().Str("model", modelName).Msg("model not found")
-				log.Error().Str("model", modelName).Msg("model not found")
+			return err
-				return err
-			}
-
-			log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
 		}
+
+		log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
 		err = startup.InstallModels(galleries, "", mi.ModelsPath, progressCallback, modelName)
 		if err != nil {
 			return err

core/cli/run.go

@@ -6,11 +6,11 @@ import (
 	"strings"
 	"time"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http"
+	"github.com/go-skynet/LocalAI/core/http"
-	"github.com/mudler/LocalAI/core/p2p"
+	"github.com/go-skynet/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/core/startup"
+	"github.com/go-skynet/LocalAI/core/startup"
 	"github.com/rs/zerolog"
 	"github.com/rs/zerolog/log"
 )
@@ -43,7 +43,6 @@ type RunCMD struct {
 	Address              string   `env:"LOCALAI_ADDRESS,ADDRESS" default:":8080" help:"Bind address for the API server" group:"api"`
 	CORS                 bool     `env:"LOCALAI_CORS,CORS" help:"" group:"api"`
 	CORSAllowOrigins     string   `env:"LOCALAI_CORS_ALLOW_ORIGINS,CORS_ALLOW_ORIGINS" group:"api"`
-	LibraryPath          string   `env:"LOCALAI_LIBRARY_PATH,LIBRARY_PATH" help:"Path to the library directory (for e.g. external libraries used by backends)" default:"/usr/share/local-ai/libs" group:"backends"`
 	CSRF                 bool     `env:"LOCALAI_CSRF" help:"Enables fiber CSRF middleware" group:"api"`
 	UploadLimit          int      `env:"LOCALAI_UPLOAD_LIMIT,UPLOAD_LIMIT" default:"15" help:"Default upload-limit in MB" group:"api"`
 	APIKeys              []string `env:"LOCALAI_API_KEY,API_KEY" help:"List of API Keys to enable API authentication. When this is set, all the requests must be authenticated with one of these API keys" group:"api"`
@@ -81,7 +80,6 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 		config.WithCors(r.CORS),
 		config.WithCorsAllowOrigins(r.CORSAllowOrigins),
 		config.WithCsrf(r.CSRF),
-		config.WithLibPath(r.LibraryPath),
 		config.WithThreads(r.Threads),
 		config.WithBackendAssets(ctx.BackendAssets),
 		config.WithBackendAssetsOutput(r.BackendAssetsPath),

core/cli/transcript.go

@@ -5,10 +5,10 @@ import (
 	"errors"
 	"fmt"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 
@@ -18,7 +18,6 @@ type TranscriptCMD struct {
 	Backend           string `short:"b" default:"whisper" help:"Backend to run the transcription model"`
 	Model             string `short:"m" required:"" help:"Model name to run the TTS"`
 	Language          string `short:"l" help:"Language of the audio file"`
-	Translate         bool   `short:"c" help:"Translate the transcription to english"`
 	Threads           int    `short:"t" default:"1" help:"Number of threads used for parallel computation"`
 	ModelsPath        string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
 	BackendAssetsPath string `env:"LOCALAI_BACKEND_ASSETS_PATH,BACKEND_ASSETS_PATH" type:"path" default:"/tmp/localai/backend_data" help:"Path used to extract libraries that are required by some of the backends in runtime" group:"storage"`
@@ -51,7 +50,7 @@ func (t *TranscriptCMD) Run(ctx *cliContext.Context) error {
 		}
 	}()
 
-	tr, err := backend.ModelTranscription(t.Filename, t.Language, t.Translate, ml, c, opts)
+	tr, err := backend.ModelTranscription(t.Filename, t.Language, ml, c, opts)
 	if err != nil {
 		return err
 	}

core/cli/tts.go

@@ -7,10 +7,10 @@ import (
 	"path/filepath"
 	"strings"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 

core/cli/util.go

@@ -5,7 +5,7 @@ import (
 
 	"github.com/rs/zerolog/log"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
 	gguf "github.com/thxcode/gguf-parser-go"
 )
 

core/cli/worker/worker_llamacpp.go

@@ -5,9 +5,8 @@ import (
 	"os"
 	"syscall"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/pkg/assets"
+	"github.com/go-skynet/LocalAI/pkg/assets"
-	"github.com/mudler/LocalAI/pkg/library"
 	"github.com/rs/zerolog/log"
 )
 
@@ -28,18 +27,17 @@ func (r *LLamaCPP) Run(ctx *cliContext.Context) error {
 		return fmt.Errorf("usage: local-ai worker llama-cpp-rpc -- <llama-rpc-server-args>")
 	}
 
-	grpcProcess := assets.ResolvePath(
-		r.BackendAssetsPath,
-		"util",
-		"llama-cpp-rpc-server",
-	)
-
-	args := os.Args[4:]
-	args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
-
-	args = append([]string{grpcProcess}, args...)
 	return syscall.Exec(
-		grpcProcess,
+		assets.ResolvePath(
-		args,
+			r.BackendAssetsPath,
+			"util",
+			"llama-cpp-rpc-server",
+		),
+		append([]string{
+			assets.ResolvePath(
+				r.BackendAssetsPath,
+				"util",
+				"llama-cpp-rpc-server",
+			)}, os.Args[4:]...),
 		os.Environ())
 }

core/cli/worker/worker_nop2p.go

@@ -6,7 +6,7 @@ package worker
 import (
 	"fmt"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
 )
 
 type P2P struct{}

core/cli/worker/worker_p2p.go

@@ -10,10 +10,9 @@ import (
 	"os/exec"
 	"time"
 
-	cliContext "github.com/mudler/LocalAI/core/cli/context"
+	cliContext "github.com/go-skynet/LocalAI/core/cli/context"
-	"github.com/mudler/LocalAI/core/p2p"
+	"github.com/go-skynet/LocalAI/core/p2p"
-	"github.com/mudler/LocalAI/pkg/assets"
+	"github.com/go-skynet/LocalAI/pkg/assets"
-	"github.com/mudler/LocalAI/pkg/library"
 	"github.com/phayes/freeport"
 	"github.com/rs/zerolog/log"
 )
@@ -72,18 +71,13 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
 	go func() {
 		for {
 			log.Info().Msgf("Starting llama-cpp-rpc-server on '%s:%d'", address, port)
-
-			grpcProcess := assets.ResolvePath(
-				r.BackendAssetsPath,
-				"util",
-				"llama-cpp-rpc-server",
-			)
-
-			args := append([]string{"--host", address, "--port", fmt.Sprint(port)}, r.ExtraLLamaCPPArgs...)
-			args, grpcProcess = library.LoadLDSO(r.BackendAssetsPath, args, grpcProcess)
-
 			cmd := exec.Command(
-				grpcProcess, args...,
+				assets.ResolvePath(
+					r.BackendAssetsPath,
+					"util",
+					"llama-cpp-rpc-server",
+				),
+				append([]string{"--host", address, "--port", fmt.Sprint(port)}, r.ExtraLLamaCPPArgs...)...,
 			)
 
 			cmd.Env = os.Environ()
@@ -92,7 +86,7 @@ func (r *P2P) Run(ctx *cliContext.Context) error {
 			cmd.Stdout = os.Stdout
 
 			if err := cmd.Start(); err != nil {
-				log.Error().Any("grpcProcess", grpcProcess).Any("args", args).Err(err).Msg("Failed to start llama-cpp-rpc-server")
+				log.Error().Err(err).Msg("Failed to start llama-cpp-rpc-server")
 			}
 
 			cmd.Wait()

core/config/application_config.go

@@ -6,7 +6,8 @@ import (
 	"encoding/json"
 	"time"
 
-	"github.com/mudler/LocalAI/pkg/xsysinfo"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/xsysinfo"
 	"github.com/rs/zerolog/log"
 )
 
@@ -14,7 +15,6 @@ type ApplicationConfig struct {
 	Context                             context.Context
 	ConfigFile                          string
 	ModelPath                           string
-	LibPath                             string
 	UploadLimitMB, Threads, ContextSize int
 	DisableWebUI                        bool
 	F16                                 bool
@@ -35,7 +35,7 @@ type ApplicationConfig struct {
 
 	ModelLibraryURL string
 
-	Galleries []Gallery
+	Galleries []gallery.Gallery
 
 	BackendAssets     embed.FS
 	AssetsDestination string
@@ -101,12 +101,6 @@ func WithModelLibraryURL(url string) AppOption {
 	}
 }
 
-func WithLibPath(path string) AppOption {
-	return func(o *ApplicationConfig) {
-		o.LibPath = path
-	}
-}
-
 var EnableWatchDog = func(o *ApplicationConfig) {
 	o.WatchDog = true
 }
@@ -179,10 +173,10 @@ func WithBackendAssets(f embed.FS) AppOption {
 func WithStringGalleries(galls string) AppOption {
 	return func(o *ApplicationConfig) {
 		if galls == "" {
-			o.Galleries = []Gallery{}
+			o.Galleries = []gallery.Gallery{}
 			return
 		}
-		var galleries []Gallery
+		var galleries []gallery.Gallery
 		if err := json.Unmarshal([]byte(galls), &galleries); err != nil {
 			log.Error().Err(err).Msg("failed loading galleries")
 		}
@@ -190,7 +184,7 @@ func WithStringGalleries(galls string) AppOption {
 	}
 }
 
-func WithGalleries(galleries []Gallery) AppOption {
+func WithGalleries(galleries []gallery.Gallery) AppOption {
 	return func(o *ApplicationConfig) {
 		o.Galleries = append(o.Galleries, galleries...)
 	}

core/config/backend_config.go

@@ -5,10 +5,10 @@ import (
 	"regexp"
 	"strings"
 
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/functions"
+	"github.com/go-skynet/LocalAI/pkg/functions"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 )
 
 const (
@@ -390,6 +390,10 @@ func (c *BackendConfig) Validate() bool {
 		}
 	}
 
+	if c.Name == "" {
+		return false
+	}
+
 	if c.Backend != "" {
 		// a regex that checks that is a string name with no special characters, except '-' and '_'
 		re := regexp.MustCompile(`^[a-zA-Z0-9-_]+$`)

core/config/backend_config_loader.go

@@ -11,9 +11,9 @@ import (
 	"sync"
 
 	"github.com/charmbracelet/glamour"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 	"gopkg.in/yaml.v3"
 )

core/config/backend_config_test.go

@@ -16,8 +16,7 @@ var _ = Describe("Test cases for config related functions", func() {
 			Expect(err).To(BeNil())
 			defer os.Remove(tmp.Name())
 			_, err = tmp.WriteString(
-				`backend: "../foo-bar"
+				`backend: "foo-bar"
-name: "foo"
 parameters:
   model: "foo-bar"`)
 			Expect(err).ToNot(HaveOccurred())

core/config/gallery.go

@@ -1,6 +0,0 @@
-package config
-
-type Gallery struct {
-	URL  string `json:"url" yaml:"url"`
-	Name string `json:"name" yaml:"name"`
-}

core/dependencies_manager/manager.go

@@ -5,8 +5,8 @@ import (
 	"os"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"gopkg.in/yaml.v3"
 )
 

core/http/app.go

@@ -6,16 +6,16 @@ import (
 	"net/http"
 	"strings"
 
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/http/endpoints/openai"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/openai"
-	"github.com/mudler/LocalAI/core/http/routes"
+	"github.com/go-skynet/LocalAI/core/http/routes"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
 	"github.com/gofiber/contrib/fiberzerolog"
 	"github.com/gofiber/fiber/v2"

core/http/app_test.go

@@ -13,15 +13,15 @@ import (
 	"path/filepath"
 	"runtime"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	. "github.com/mudler/LocalAI/core/http"
+	. "github.com/go-skynet/LocalAI/core/http"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/startup"
+	"github.com/go-skynet/LocalAI/core/startup"
 
+	"github.com/go-skynet/LocalAI/pkg/downloader"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/pkg/downloader"
-	"github.com/mudler/LocalAI/pkg/model"
 	. "github.com/onsi/ginkgo/v2"
 	. "github.com/onsi/gomega"
 	"gopkg.in/yaml.v3"
@@ -74,7 +74,7 @@ func getModelStatus(url string) (response map[string]interface{}) {
 
 func getModels(url string) (response []gallery.GalleryModel) {
 	// TODO: No tests currently seem to exercise file:// urls. Fix?
-	downloader.DownloadAndUnmarshal(url, "", func(url string, i []byte) error {
+	downloader.GetURI(url, "", func(url string, i []byte) error {
 		// Unmarshal YAML data into a struct
 		return json.Unmarshal(i, &response)
 	})
@@ -247,7 +247,7 @@ var _ = Describe("API test", func() {
 			err = os.WriteFile(filepath.Join(modelDir, "gallery_simple.yaml"), out, 0600)
 			Expect(err).ToNot(HaveOccurred())
 
-			galleries := []config.Gallery{
+			galleries := []gallery.Gallery{
 				{
 					Name: "test",
 					URL:  "file://" + filepath.Join(modelDir, "gallery_simple.yaml"),
@@ -603,7 +603,7 @@ var _ = Describe("API test", func() {
 
 			c, cancel = context.WithCancel(context.Background())
 
-			galleries := []config.Gallery{
+			galleries := []gallery.Gallery{
 				{
 					Name: "model-gallery",
 					URL:  "https://raw.githubusercontent.com/go-skynet/model-gallery/main/index.yaml",

core/http/ctx/fiber.go

@@ -4,8 +4,8 @@ import (
 	"fmt"
 	"strings"
 
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 

core/http/elements/gallery.go

@@ -6,9 +6,9 @@ import (
 
 	"github.com/chasefleming/elem-go"
 	"github.com/chasefleming/elem-go/attrs"
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/core/services"
-	"github.com/mudler/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/xsync"
+	"github.com/go-skynet/LocalAI/pkg/xsync"
 )
 
 const (

core/http/endpoints/elevenlabs/tts.go

@@ -1,13 +1,13 @@
 package elevenlabs
 
 import (
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
 	"github.com/rs/zerolog/log"
 )
 

core/http/endpoints/jina/rerank.go

@@ -1,14 +1,14 @@
 package jina
 
 import (
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 

core/http/endpoints/localai/backend_monitor.go

@@ -1,9 +1,9 @@
 package localai
 
 import (
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/services"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/services"
 )
 
 func BackendMonitorEndpoint(bm *services.BackendMonitorService) func(c *fiber.Ctx) error {

core/http/endpoints/localai/gallery.go

@@ -5,16 +5,15 @@ import (
 	"fmt"
 	"slices"
 
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/core/services"
 	"github.com/rs/zerolog/log"
 )
 
 type ModelGalleryEndpointService struct {
-	galleries      []config.Gallery
+	galleries      []gallery.Gallery
 	modelPath      string
 	galleryApplier *services.GalleryService
 }
@@ -25,7 +24,7 @@ type GalleryModel struct {
 	gallery.GalleryModel
 }
 
-func CreateModelGalleryEndpointService(galleries []config.Gallery, modelPath string, galleryApplier *services.GalleryService) ModelGalleryEndpointService {
+func CreateModelGalleryEndpointService(galleries []gallery.Gallery, modelPath string, galleryApplier *services.GalleryService) ModelGalleryEndpointService {
 	return ModelGalleryEndpointService{
 		galleries:      galleries,
 		modelPath:      modelPath,
@@ -130,12 +129,12 @@ func (mgs *ModelGalleryEndpointService) ListModelGalleriesEndpoint() func(c *fib
 
 func (mgs *ModelGalleryEndpointService) AddModelGalleryEndpoint() func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		input := new(config.Gallery)
+		input := new(gallery.Gallery)
 		// Get input data from the request body
 		if err := c.BodyParser(input); err != nil {
 			return err
 		}
-		if slices.ContainsFunc(mgs.galleries, func(gallery config.Gallery) bool {
+		if slices.ContainsFunc(mgs.galleries, func(gallery gallery.Gallery) bool {
 			return gallery.Name == input.Name
 		}) {
 			return fmt.Errorf("%s already exists", input.Name)
@@ -152,17 +151,17 @@ func (mgs *ModelGalleryEndpointService) AddModelGalleryEndpoint() func(c *fiber.
 
 func (mgs *ModelGalleryEndpointService) RemoveModelGalleryEndpoint() func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
-		input := new(config.Gallery)
+		input := new(gallery.Gallery)
 		// Get input data from the request body
 		if err := c.BodyParser(input); err != nil {
 			return err
 		}
-		if !slices.ContainsFunc(mgs.galleries, func(gallery config.Gallery) bool {
+		if !slices.ContainsFunc(mgs.galleries, func(gallery gallery.Gallery) bool {
 			return gallery.Name == input.Name
 		}) {
 			return fmt.Errorf("%s is not currently registered", input.Name)
 		}
-		mgs.galleries = slices.DeleteFunc(mgs.galleries, func(gallery config.Gallery) bool {
+		mgs.galleries = slices.DeleteFunc(mgs.galleries, func(gallery gallery.Gallery) bool {
 			return gallery.Name == input.Name
 		})
 		return c.Send(nil)

core/http/endpoints/localai/metrics.go

@@ -3,9 +3,9 @@ package localai
 import (
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/services"
 	"github.com/gofiber/fiber/v2"
 	"github.com/gofiber/fiber/v2/middleware/adaptor"
-	"github.com/mudler/LocalAI/core/services"
 	"github.com/prometheus/client_golang/prometheus/promhttp"
 )
 

core/http/endpoints/localai/stores.go

@@ -1,12 +1,12 @@
 package localai
 
 import (
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/store"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/store"
 )
 
 func StoresSetEndpoint(sl *model.ModelLoader, appConfig *config.ApplicationConfig) func(c *fiber.Ctx) error {

core/http/endpoints/localai/tts.go

@@ -1,13 +1,13 @@
 package localai
 
 import (
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
 	"github.com/rs/zerolog/log"
 )
 

core/http/endpoints/localai/welcome.go

@@ -1,11 +1,11 @@
 package localai
 
 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
-	"github.com/mudler/LocalAI/internal"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func WelcomeEndpoint(appConfig *config.ApplicationConfig,

core/http/endpoints/openai/assistant.go

@@ -9,10 +9,10 @@ import (
 	"sync/atomic"
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/config"
+	model "github.com/go-skynet/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	model "github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 )
 
@@ -339,7 +339,7 @@ func CreateAssistantFileEndpoint(cl *config.BackendConfigLoader, ml *model.Model
 			}
 		}
 
-		return c.Status(fiber.StatusNotFound).SendString(fmt.Sprintf("Unable to find %q", assistantID))
+		return c.Status(fiber.StatusNotFound).SendString(fmt.Sprintf("Unable to find "))
 	}
 }
 

core/http/endpoints/openai/assistant_test.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"io/ioutil"
 	"net/http"
 	"net/http/httptest"
 	"os"
@@ -12,9 +13,9 @@ import (
 	"testing"
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/stretchr/testify/assert"
 )
 
@@ -182,7 +183,7 @@ func TestAssistantEndpoints(t *testing.T) {
 				assert.NoError(t, err)
 				assert.Equal(t, tt.expectedStatus, response.StatusCode)
 				if tt.expectedStatus != fiber.StatusOK {
-					all, _ := io.ReadAll(response.Body)
+					all, _ := ioutil.ReadAll(response.Body)
 					assert.Equal(t, tt.expectedStringResult, string(all))
 				} else {
 					var result []Assistant
@@ -278,7 +279,6 @@ func TestAssistantEndpoints(t *testing.T) {
 		assert.NoError(t, err)
 		var getAssistant Assistant
 		err = json.NewDecoder(modifyResponse.Body).Decode(&getAssistant)
-		assert.NoError(t, err)
 
 		t.Cleanup(cleanupAllAssistants(t, app, []string{getAssistant.ID}))
 
@@ -391,10 +391,7 @@ func createAssistantFile(app *fiber.App, afr AssistantFileRequest, assistantId s
 	}
 
 	var assistantFile AssistantFile
-	all, err := io.ReadAll(resp.Body)
+	all, err := ioutil.ReadAll(resp.Body)
-	if err != nil {
-		return AssistantFile{}, resp, err
-	}
 	err = json.NewDecoder(strings.NewReader(string(all))).Decode(&assistantFile)
 	if err != nil {
 		return AssistantFile{}, resp, err
@@ -425,7 +422,8 @@ func createAssistant(app *fiber.App, ar AssistantRequest) (Assistant, *http.Resp
 
 	var resultAssistant Assistant
 	err = json.NewDecoder(strings.NewReader(string(bodyString))).Decode(&resultAssistant)
-	return resultAssistant, resp, err
+
+	return resultAssistant, resp, nil
 }
 
 func cleanupAllAssistants(t *testing.T, app *fiber.App, ids []string) func() {

core/http/endpoints/openai/chat.go

@@ -8,13 +8,13 @@ import (
 	"strings"
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/functions"
-	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 	"github.com/valyala/fasthttp"
 )

core/http/endpoints/openai/completion.go

@@ -8,14 +8,14 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/functions"
-	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 	"github.com/valyala/fasthttp"
 )

core/http/endpoints/openai/edit.go

@@ -5,13 +5,13 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	"github.com/go-skynet/LocalAI/core/schema"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/schema"
-	model "github.com/mudler/LocalAI/pkg/model"
 
 	"github.com/rs/zerolog/log"
 )

core/http/endpoints/openai/embeddings.go

@@ -5,12 +5,12 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/schema"
 
 	"github.com/gofiber/fiber/v2"
 	"github.com/rs/zerolog/log"

core/http/endpoints/openai/files.go

@@ -8,10 +8,10 @@ import (
 	"sync/atomic"
 	"time"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/pkg/utils"
 )
 
 var UploadedFiles []File

core/http/endpoints/openai/files_test.go

@@ -13,10 +13,10 @@ import (
 
 	"github.com/rs/zerolog/log"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
+	utils2 "github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/gofiber/fiber/v2"
-	utils2 "github.com/mudler/LocalAI/pkg/utils"
 	"github.com/stretchr/testify/assert"
 
 	"testing"

core/http/endpoints/openai/image.go

@@ -13,14 +13,14 @@ import (
 	"strings"
 	"time"
 
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/google/uuid"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
 
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	model "github.com/mudler/LocalAI/pkg/model"
 	"github.com/rs/zerolog/log"
 )
 

core/http/endpoints/openai/inference.go

@@ -1,11 +1,11 @@
 package openai
 
 import (
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
 
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 )
 
 func ComputeChoices(

core/http/endpoints/openai/list.go

@@ -1,9 +1,9 @@
 package openai
 
 import (
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/services"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/core/services"
 )
 
 func ListModelsEndpoint(lms *services.ListModelsService) func(ctx *fiber.Ctx) error {

core/http/endpoints/openai/request.go

@@ -2,16 +2,19 @@ package openai
 
 import (
 	"context"
+	"encoding/base64"
 	"encoding/json"
 	"fmt"
+	"io"
+	"net/http"
+	"strings"
 
+	"github.com/go-skynet/LocalAI/core/config"
+	fiberContext "github.com/go-skynet/LocalAI/core/http/ctx"
+	"github.com/go-skynet/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/pkg/functions"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	fiberContext "github.com/mudler/LocalAI/core/http/ctx"
-	"github.com/mudler/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/functions"
-	"github.com/mudler/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 )
 
@@ -36,6 +39,41 @@ func readRequest(c *fiber.Ctx, ml *model.ModelLoader, o *config.ApplicationConfi
 	return modelFile, input, err
 }
 
+// this function check if the string is an URL, if it's an URL downloads the image in memory
+// encodes it in base64 and returns the base64 string
+func getBase64Image(s string) (string, error) {
+	if strings.HasPrefix(s, "http") {
+		// download the image
+		resp, err := http.Get(s)
+		if err != nil {
+			return "", err
+		}
+		defer resp.Body.Close()
+
+		// read the image data into memory
+		data, err := io.ReadAll(resp.Body)
+		if err != nil {
+			return "", err
+		}
+
+		// encode the image data in base64
+		encoded := base64.StdEncoding.EncodeToString(data)
+
+		// return the base64 string
+		return encoded, nil
+	}
+
+	// if the string instead is prefixed with "data:image/...;base64,", drop it
+	dropPrefix := []string{"data:image/jpeg;base64,", "data:image/png;base64,"}
+	for _, prefix := range dropPrefix {
+		if strings.HasPrefix(s, prefix) {
+			return strings.ReplaceAll(s, prefix, ""), nil
+		}
+	}
+
+	return "", fmt.Errorf("not valid string")
+}
+
 func updateRequestConfig(config *config.BackendConfig, input *schema.OpenAIRequest) {
 	if input.Echo {
 		config.Echo = input.Echo
@@ -149,7 +187,7 @@ func updateRequestConfig(config *config.BackendConfig, input *schema.OpenAIReque
 					input.Messages[i].StringContent = pp.Text
 				} else if pp.Type == "image_url" {
 					// Detect if pp.ImageURL is an URL, if it is download the image and encode it in base64:
-					base64, err := utils.GetImageURLAsBase64(pp.ImageURL.URL)
+					base64, err := getBase64Image(pp.ImageURL.URL)
 					if err == nil {
 						input.Messages[i].StringImages = append(input.Messages[i].StringImages, base64) // TODO: make sure that we only return base64 stuff
 						// set a placeholder for each image
@@ -257,9 +295,5 @@ func mergeRequestWithConfig(modelFile string, input *schema.OpenAIRequest, cm *c
 	// Set the parameters for the language model prediction
 	updateRequestConfig(cfg, input)
 
-	if !cfg.Validate() {
-		return nil, nil, fmt.Errorf("failed to validate config")
-	}
-
 	return cfg, input, err
 }

core/http/endpoints/openai/transcription.go

@@ -8,9 +8,9 @@ import (
 	"path"
 	"path/filepath"
 
-	"github.com/mudler/LocalAI/core/backend"
+	"github.com/go-skynet/LocalAI/core/backend"
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	model "github.com/mudler/LocalAI/pkg/model"
+	model "github.com/go-skynet/LocalAI/pkg/model"
 
 	"github.com/gofiber/fiber/v2"
 	"github.com/rs/zerolog/log"
@@ -32,7 +32,7 @@ func TranscriptEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, a
 
 		config, input, err := mergeRequestWithConfig(m, input, cl, ml, appConfig.Debug, appConfig.Threads, appConfig.ContextSize, appConfig.F16)
 		if err != nil {
-			return fmt.Errorf("failed reading parameters from request: %w", err)
+			return fmt.Errorf("failed reading parameters from request:%w", err)
 		}
 		// retrieve the file data from the request
 		file, err := c.FormFile("file")
@@ -65,7 +65,7 @@ func TranscriptEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, a
 
 		log.Debug().Msgf("Audio file copied to: %+v", dst)
 
-		tr, err := backend.ModelTranscription(dst, input.Language, input.Translate, ml, *config, appConfig)
+		tr, err := backend.ModelTranscription(dst, input.Language, ml, *config, appConfig)
 		if err != nil {
 			return err
 		}

core/http/render.go

@@ -7,10 +7,10 @@ import (
 	"net/http"
 
 	"github.com/Masterminds/sprig/v3"
+	"github.com/go-skynet/LocalAI/core/schema"
 	"github.com/gofiber/fiber/v2"
 	fiberhtml "github.com/gofiber/template/html/v2"
 	"github.com/microcosm-cc/bluemonday"
-	"github.com/mudler/LocalAI/core/schema"
 	"github.com/russross/blackfriday"
 )
 
@@ -21,13 +21,14 @@ func notFoundHandler(c *fiber.Ctx) error {
 	// Check if the request accepts JSON
 	if string(c.Context().Request.Header.ContentType()) == "application/json" || len(c.Accepts("html")) == 0 {
 		// The client expects a JSON response
-		return c.Status(fiber.StatusNotFound).JSON(schema.ErrorResponse{
+		c.Status(fiber.StatusNotFound).JSON(schema.ErrorResponse{
 			Error: &schema.APIError{Message: "Resource not found", Code: fiber.StatusNotFound},
 		})
 	} else {
 		// The client expects an HTML response
-		return c.Status(fiber.StatusNotFound).Render("views/404", fiber.Map{})
+		c.Status(fiber.StatusNotFound).Render("views/404", fiber.Map{})
 	}
+	return nil
 }
 
 func renderEngine() *fiberhtml.Engine {

core/http/routes/elevenlabs.go

@@ -1,10 +1,10 @@
 package routes
 
 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/elevenlabs"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/elevenlabs"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func RegisterElevenLabsRoutes(app *fiber.App,

core/http/routes/jina.go

@@ -1,11 +1,11 @@
 package routes
 
 import (
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/jina"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/jina"
 
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func RegisterJINARoutes(app *fiber.App,

core/http/routes/localai.go

@@ -1,13 +1,13 @@
 package routes
 
 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
 	"github.com/gofiber/swagger"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/internal"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func RegisterLocalAIRoutes(app *fiber.App,

core/http/routes/openai.go

@@ -1,12 +1,12 @@
 package routes
 
 import (
+	"github.com/go-skynet/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/openai"
+	"github.com/go-skynet/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/pkg/model"
 	"github.com/gofiber/fiber/v2"
-	"github.com/mudler/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/http/endpoints/openai"
-	"github.com/mudler/LocalAI/core/services"
-	"github.com/mudler/LocalAI/pkg/model"
 )
 
 func RegisterOpenAIRoutes(app *fiber.App,

core/http/routes/ui.go

@@ -6,14 +6,14 @@ import (
 	"sort"
 	"strings"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/core/http/elements"
-	"github.com/mudler/LocalAI/core/http/elements"
+	"github.com/go-skynet/LocalAI/core/http/endpoints/localai"
-	"github.com/mudler/LocalAI/core/http/endpoints/localai"
+	"github.com/go-skynet/LocalAI/core/services"
-	"github.com/mudler/LocalAI/core/services"
+	"github.com/go-skynet/LocalAI/internal"
-	"github.com/mudler/LocalAI/internal"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
-	"github.com/mudler/LocalAI/pkg/xsync"
+	"github.com/go-skynet/LocalAI/pkg/xsync"
 	"github.com/rs/zerolog/log"
 
 	"github.com/gofiber/fiber/v2"
@@ -26,7 +26,6 @@ func RegisterUIRoutes(app *fiber.App,
 	appConfig *config.ApplicationConfig,
 	galleryService *services.GalleryService,
 	auth func(*fiber.Ctx) error) {
-	tmpLMS := services.NewListModelsService(ml, cl, appConfig) // TODO: once createApplication() is fully in use, reference the central instance.
 
 	// keeps the state of models that are being installed from the UI
 	var processingModels = xsync.NewSyncedMap[string, string]()
@@ -236,7 +235,7 @@ func RegisterUIRoutes(app *fiber.App,
 
 	// Show the Chat page
 	app.Get("/chat/:model", auth, func(c *fiber.Ctx) error {
-		backendConfigs, _ := tmpLMS.ListModels("", true)
+		backendConfigs := cl.GetAllBackendConfigs()
 
 		summary := fiber.Map{
 			"Title":        "LocalAI - Chat with " + c.Params("model"),
@@ -250,7 +249,7 @@ func RegisterUIRoutes(app *fiber.App,
 	})
 
 	app.Get("/talk/", auth, func(c *fiber.Ctx) error {
-		backendConfigs, _ := tmpLMS.ListModels("", true)
+		backendConfigs := cl.GetAllBackendConfigs()
 
 		if len(backendConfigs) == 0 {
 			// If no model is available redirect to the index which suggests how to install models
@@ -260,7 +259,7 @@ func RegisterUIRoutes(app *fiber.App,
 		summary := fiber.Map{
 			"Title":        "LocalAI - Talk",
 			"ModelsConfig": backendConfigs,
-			"Model":        backendConfigs[0].ID,
+			"Model":        backendConfigs[0].Name,
 			"Version":      internal.PrintableVersion(),
 		}
 
@@ -270,7 +269,7 @@ func RegisterUIRoutes(app *fiber.App,
 
 	app.Get("/chat/", auth, func(c *fiber.Ctx) error {
 
-		backendConfigs, _ := tmpLMS.ListModels("", true)
+		backendConfigs := cl.GetAllBackendConfigs()
 
 		if len(backendConfigs) == 0 {
 			// If no model is available redirect to the index which suggests how to install models
@@ -278,9 +277,9 @@ func RegisterUIRoutes(app *fiber.App,
 		}
 
 		summary := fiber.Map{
-			"Title":        "LocalAI - Chat with " + backendConfigs[0].ID,
+			"Title":        "LocalAI - Chat with " + backendConfigs[0].Name,
 			"ModelsConfig": backendConfigs,
-			"Model":        backendConfigs[0].ID,
+			"Model":        backendConfigs[0].Name,
 			"Version":      internal.PrintableVersion(),
 		}
 

core/http/views/chat.html

@@ -100,10 +100,10 @@ SOFTWARE.
         <option value="" disabled class="text-gray-400" >Select a model</option>
         {{ $model:=.Model}}
         {{ range .ModelsConfig }}
-        {{ if eq .ID $model }}
+        {{ if eq .Name $model }}
-        <option value="/chat/{{.ID}}" selected  class="bg-gray-700 text-white">{{.ID}}</option>
+        <option value="/chat/{{.Name}}" selected  class="bg-gray-700 text-white">{{.Name}}</option>
         {{ else }}
-        <option value="/chat/{{.ID}}" class="bg-gray-700 text-white">{{.ID}}</option>
+        <option value="/chat/{{.Name}}" class="bg-gray-700 text-white">{{.Name}}</option>
         {{ end }}
         {{ end }}
       </select>

core/http/views/talk.html

@@ -50,10 +50,6 @@
       </div>
       <div id="loader" class="my-2 loader" style="display: none;"></div>
       <div id="statustext" class="my-2 p-2 block text-white-700 text-sm font-bold mb-2" ></div>
-      <!-- Note for recording box -->
-      <div class="text-sm mb-4 text-white-500">
-        <strong>Note:</strong> You need an LLM a audio-transcription(whisper) and a tts model installed in order for this to work. Select the appropariate model from the toolbox and then click the 'Talk' button to start recording. The recording will continue until you click 'Stop recording'. Make sure your microphone is set up and enabled.
-      </div>
       <div class="mb-4" >
         <label for="modelSelect" class="block text-white-700 text-sm font-bold mb-2">LLM Model:</label>
         <select id="modelSelect"
@@ -62,7 +58,7 @@
           <option value="" disabled class="text-gray-400" >Select a model</option>
 
           {{ range .ModelsConfig }}
-          <option value="{{.ID}}"  class="bg-gray-700 text-white">{{.ID}}</option>
+          <option value="{{.Name}}"  class="bg-gray-700 text-white">{{.Name}}</option>
           {{ end }}
         </select>
       </div>
@@ -76,7 +72,7 @@
             <option value="" disabled class="text-gray-400" >Select a model</option>
 
             {{ range .ModelsConfig }}
-            <option value="{{.ID}}"  class="bg-gray-700 text-white">{{.ID}}</option>
+            <option value="{{.Name}}"  class="bg-gray-700 text-white">{{.Name}}</option>
             {{ end }}
           </select>
       </div>
@@ -89,7 +85,7 @@
         >
           <option value="" disabled class="text-gray-400" >Select a model</option>
           {{ range .ModelsConfig }}
-          <option value="{{.ID}}"  class="bg-gray-700 text-white">{{.ID}}</option>
+          <option value="{{.Name}}"  class="bg-gray-700 text-white">{{.Name}}</option>
           {{ end }}
         </select>
       </div>
@@ -99,7 +95,7 @@
         class="bg-red-500 hover:bg-red-700 text-white font-bold py-2 px-4 rounded focus:outline-none focus:shadow-outline"
       ><i class="fa-solid fa-microphone pr-2"></i>Talk</button>
       <a id="resetButton"
-      class="inline-block align-baseline font-bold text-sm text-blue-500 hover:text-gray-200"
+      class="inline-block align-baseline font-bold text-sm text-blue-500 hover:text-blue-800"
       href="#"
       >Reset conversation</a>
       <audio id="audioPlayback" controls hidden></audio>

core/p2p/p2p.go

@@ -13,8 +13,8 @@ import (
 	"strings"
 	"time"
 
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/libp2p/go-libp2p/core/peer"
-	"github.com/mudler/LocalAI/pkg/utils"
 	"github.com/mudler/edgevpn/pkg/node"
 	"github.com/mudler/edgevpn/pkg/protocol"
 	"github.com/mudler/edgevpn/pkg/types"

core/schema/openai.go

@@ -3,7 +3,7 @@ package schema
 import (
 	"context"
 
-	functions "github.com/mudler/LocalAI/pkg/functions"
+	functions "github.com/go-skynet/LocalAI/pkg/functions"
 )
 
 // APIError provides error information returned by the OpenAI API.

core/schema/prediction.go

@@ -8,9 +8,6 @@ type PredictionOptions struct {
 	// Also part of the OpenAI official spec
 	Language string `json:"language"`
 
-	// Only for audio transcription
-	Translate bool `json:"translate"`
-
 	// Also part of the OpenAI official spec. use it for returning multiple results
 	N int `json:"n"`
 
@@ -25,10 +22,7 @@ type PredictionOptions struct {
 	Batch         int     `json:"batch" yaml:"batch"`
 	IgnoreEOS     bool    `json:"ignore_eos" yaml:"ignore_eos"`
 	RepeatPenalty float64 `json:"repeat_penalty" yaml:"repeat_penalty"`
-
+	Keep          int     `json:"n_keep" yaml:"n_keep"`
-	RepeatLastN int `json:"repeat_last_n" yaml:"repeat_last_n"`
-
-	Keep int `json:"n_keep" yaml:"n_keep"`
 
 	FrequencyPenalty float64  `json:"frequency_penalty" yaml:"frequency_penalty"`
 	PresencePenalty  float64  `json:"presence_penalty" yaml:"presence_penalty"`

core/services/backend_monitor.go

@@ -5,10 +5,10 @@ import (
 	"fmt"
 	"strings"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/go-skynet/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 
 	"github.com/rs/zerolog/log"
 

core/services/gallery.go

@@ -8,10 +8,10 @@ import (
 	"path/filepath"
 	"sync"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/go-skynet/LocalAI/pkg/gallery"
-	"github.com/mudler/LocalAI/pkg/startup"
+	"github.com/go-skynet/LocalAI/pkg/startup"
-	"github.com/mudler/LocalAI/pkg/utils"
+	"github.com/go-skynet/LocalAI/pkg/utils"
 	"gopkg.in/yaml.v2"
 )
 
@@ -96,7 +96,6 @@ func (g *GalleryService) Start(c context.Context, cl *config.BackendConfigLoader
 				// delete a model
 				if op.Delete {
 					modelConfig := &config.BackendConfig{}
-
 					// Galleryname is the name of the model in this case
 					dat, err := os.ReadFile(filepath.Join(g.appConfig.ModelPath, op.GalleryModelName+".yaml"))
 					if err != nil {
@@ -175,7 +174,7 @@ type galleryModel struct {
 	ID                   string           `json:"id"`
 }
 
-func processRequests(modelPath string, galleries []config.Gallery, requests []galleryModel) error {
+func processRequests(modelPath string, galleries []gallery.Gallery, requests []galleryModel) error {
 	var err error
 	for _, r := range requests {
 		utils.ResetDownloadTimers()
@@ -190,7 +189,7 @@ func processRequests(modelPath string, galleries []config.Gallery, requests []ga
 	return err
 }
 
-func ApplyGalleryFromFile(modelPath, s string, galleries []config.Gallery) error {
+func ApplyGalleryFromFile(modelPath, s string, galleries []gallery.Gallery) error {
 	dat, err := os.ReadFile(s)
 	if err != nil {
 		return err
@@ -204,7 +203,7 @@ func ApplyGalleryFromFile(modelPath, s string, galleries []config.Gallery) error
 	return processRequests(modelPath, galleries, requests)
 }
 
-func ApplyGalleryFromString(modelPath, s string, galleries []config.Gallery) error {
+func ApplyGalleryFromString(modelPath, s string, galleries []gallery.Gallery) error {
 	var requests []galleryModel
 	err := json.Unmarshal([]byte(s), &requests)
 	if err != nil {

core/services/list_models.go

@@ -3,9 +3,9 @@ package services
 import (
 	"regexp"
 
-	"github.com/mudler/LocalAI/core/config"
+	"github.com/go-skynet/LocalAI/core/config"
-	"github.com/mudler/LocalAI/core/schema"
+	"github.com/go-skynet/LocalAI/core/schema"
-	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/go-skynet/LocalAI/pkg/model"
 )
 
 type ListModelsService struct {