wip

⬆️ Update docs version mudler/LocalAI

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

.bruno/LocalAI Test Requests/Sound Generation/musicgen.bru

@@ -1,23 +0,0 @@
-meta {
-  name: musicgen
-  type: http
-  seq: 1
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/v1/sound-generation
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "model_id": "facebook/musicgen-small",
-      "text": "Exciting 80s Newscast Interstitial",
-      "duration_seconds": 8
-  }
-}

.bruno/LocalAI Test Requests/backend monitor/backend monitor.bru

@@ -1,17 +0,0 @@
-meta {
-  name: backend monitor
-  type: http
-  seq: 4
-}
-
-get {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/backend/monitor
-  body: json
-  auth: none
-}
-
-body:json {
-  {
-    "model": "{{DEFAULT_MODEL}}"
-  }
-}

.bruno/LocalAI Test Requests/backend monitor/backend-shutdown.bru

@@ -1,21 +0,0 @@
-meta {
-  name: backend-shutdown
-  type: http
-  seq: 3
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/backend/shutdown
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "model": "{{DEFAULT_MODEL}}"
-  }
-}

.bruno/LocalAI Test Requests/bruno.json

@@ -1,5 +0,0 @@
-{
-  "version": "1",
-  "name": "LocalAI Test Requests",
-  "type": "collection"
-}

.bruno/LocalAI Test Requests/environments/localhost.bru

@@ -1,6 +0,0 @@
-vars {
-  HOST: localhost
-  PORT: 8080
-  DEFAULT_MODEL: gpt-3.5-turbo
-  PROTOCOL: http://
-}

.bruno/LocalAI Test Requests/get models list.bru

@@ -1,11 +0,0 @@
-meta {
-  name: get models list
-  type: http
-  seq: 2
-}
-
-get {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/models
-  body: none
-  auth: none
-}

.bruno/LocalAI Test Requests/image generation/Generate image.bru

@@ -1,25 +0,0 @@
-meta {
-  name: Generate image
-  type: http
-  seq: 1
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/v1/images/generations
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-    "prompt": "<positive prompt>|<negative prompt>",
-    "model": "model-name",
-    "step": 51,
-    "size": "1024x1024",
-    "image": ""
-  }
-}

.bruno/LocalAI Test Requests/llm text/-completions.bru

@@ -1,24 +0,0 @@
-meta {
-  name: -completions
-  type: http
-  seq: 4
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/completions
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "model": "{{DEFAULT_MODEL}}",
-      "prompt": "function downloadFile(string url, string outputPath) {",
-      "max_tokens": 256,
-      "temperature": 0.5
-  }
-}

.bruno/LocalAI Test Requests/llm text/-edits.bru

@@ -1,23 +0,0 @@
-meta {
-  name: -edits
-  type: http
-  seq: 5
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/edits
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "model": "{{DEFAULT_MODEL}}",
-      "input": "What day of the wek is it?",
-      "instruction": "Fix the spelling mistakes"
-  }
-}

.bruno/LocalAI Test Requests/llm text/-embeddings.bru

@@ -1,22 +0,0 @@
-meta {
-  name: -embeddings
-  type: http
-  seq: 6
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/embeddings
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "model": "{{DEFAULT_MODEL}}",
-      "input": "A STRANGE GAME.\nTHE ONLY WINNING MOVE IS NOT TO PLAY.\n\nHOW ABOUT A NICE GAME OF CHESS?"
-  }
-}

.bruno/LocalAI Test Requests/llm text/chat/chat completion -simple- 1 message-.bru

@@ -1,30 +0,0 @@
-meta {
-  name: chat completion -simple- 1 message-
-  type: http
-  seq: 4
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/chat/completions
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-    "model": "{{DEFAULT_MODEL}}",
-    "messages": [
-      {
-        "role": "user",
-        "content": "How could one use friction to cook an egg?"
-      }
-    ],
-    "max_tokens": 256,
-    "temperature": 0.2,
-    "grammar": ""
-  }
-}

.bruno/LocalAI Test Requests/llm text/chat/chat-completions -long-.bru

@@ -1,29 +0,0 @@
-meta {
-  name: chat-completions -long-
-  type: http
-  seq: 5
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/chat/completions
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-       "model": "{{DEFAULT_MODEL}}",
-       "messages": [{"role": "system", "content": "You are a helpful, intelligent pirate assistant. Always answer as helpfully as possible, while being a pirate and using pirate language. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."},
-           {"role": "user", "content": "How could one use electricity to cook an egg?"},
-           {"role": "assistant",
-                  "content": "Shiver me timbers! Using electricity to cook an egg? Well, matey, I reckon that be a right curious idea! *adjusts spectacles* Now, I ain't sure if this be possible, but I'll do me best to help ye out.\n\nFirst things first, ye gotta understand that electricity be a powerful force, and it can't just cook an egg on its own. Ye see, electricity be like a mighty wind that can make things happen, but it needs somethin' to work with. So, if ye want to use electricity to cook an egg, ye gotta find a way to harness that power and make it do the cookin'.\n\nNow, I know what ye might be thinkin': \"How do I harness the power of electricity to cook an egg?\" Well, matey, there be a few ways to do it. One way be to use a special device called an \"electric frying pan.\" This be a pan that has a built-in heating element that gets hot when ye plug it into a wall socket. When the element gets hot, ye can crack an egg into the pan and watch as it cook"
-              },
-              {"role": "user", "content": "I don't have one of those, just a raw wire and plenty of power! How do we get it done?"}],
-       "max_tokens": 1024,
-       "temperature": 0.5
-  }
-}

.bruno/LocalAI Test Requests/llm text/chat/chat-completions -stream-.bru

@@ -1,25 +0,0 @@
-meta {
-  name: chat-completions -stream-
-  type: http
-  seq: 6
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/chat/completions
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-       "model": "{{DEFAULT_MODEL}}",
-       "messages": [{"role": "user", "content": "Explain how I can set sail on the ocean using only power generated by seagulls?"}],
-       "max_tokens": 256,
-       "temperature": 0.9,
-       "stream": true
-  }
-}

.bruno/LocalAI Test Requests/model gallery/add model gallery.bru

@@ -1,22 +0,0 @@
-meta {
-  name: add model gallery
-  type: http
-  seq: 10
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/models/galleries
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "url": "file:///home/dave/projects/model-gallery/huggingface/TheBloke__CodeLlama-7B-Instruct-GGML.yaml",
-      "name": "test"
-  }
-}

.bruno/LocalAI Test Requests/model gallery/delete model gallery.bru

@@ -1,21 +0,0 @@
-meta {
-  name: delete model gallery
-  type: http
-  seq: 11
-}
-
-delete {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/models/galleries
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "name": "test"
-  }
-}

.bruno/LocalAI Test Requests/model gallery/list MODELS in galleries.bru

@@ -1,11 +0,0 @@
-meta {
-  name: list MODELS in galleries
-  type: http
-  seq: 7
-}
-
-get {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/models/available
-  body: none
-  auth: none
-}

.bruno/LocalAI Test Requests/model gallery/list model GALLERIES.bru

@@ -1,11 +0,0 @@
-meta {
-  name: list model GALLERIES
-  type: http
-  seq: 8
-}
-
-get {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/models/galleries
-  body: none
-  auth: none
-}

.bruno/LocalAI Test Requests/model gallery/model delete.bru

@@ -1,11 +0,0 @@
-meta {
-  name: model delete
-  type: http
-  seq: 7
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/models/galleries
-  body: none
-  auth: none
-}

.bruno/LocalAI Test Requests/model gallery/model gallery apply -gist-.bru

@@ -1,21 +0,0 @@
-meta {
-  name: model gallery apply -gist-
-  type: http
-  seq: 12
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/models/apply
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "id": "TheBloke__CodeLlama-7B-Instruct-GGML__codellama-7b-instruct.ggmlv3.Q2_K.bin"
-  }
-}

.bruno/LocalAI Test Requests/model gallery/model gallery apply.bru

@@ -1,22 +0,0 @@
-meta {
-  name: model gallery apply
-  type: http
-  seq: 9
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/models/apply
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "id": "dave@TheBloke__CodeLlama-7B-Instruct-GGML__codellama-7b-instruct.ggmlv3.Q3_K_S.bin",
-      "name": "codellama7b"
-  }
-}

.bruno/LocalAI Test Requests/transcription/transcribe.bru

@@ -1,16 +0,0 @@
-meta {
-  name: transcribe
-  type: http
-  seq: 1
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/v1/audio/transcriptions
-  body: multipartForm
-  auth: none
-}
-
-body:multipart-form {
-  file: @file(transcription/gb1.ogg)
-  model: whisper-1
-}

.bruno/LocalAI Test Requests/tts/-tts.bru

@@ -1,22 +0,0 @@
-meta {
-  name: -tts
-  type: http
-  seq: 2
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/tts
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "model": "{{DEFAULT_MODEL}}",
-      "input": "A STRANGE GAME.\nTHE ONLY WINNING MOVE IS NOT TO PLAY.\n\nHOW ABOUT A NICE GAME OF CHESS?"
-  }
-}

.bruno/LocalAI Test Requests/tts/musicgen.bru

@@ -1,23 +0,0 @@
-meta {
-  name: musicgen
-  type: http
-  seq: 2
-}
-
-post {
-  url: {{PROTOCOL}}{{HOST}}:{{PORT}}/tts
-  body: json
-  auth: none
-}
-
-headers {
-  Content-Type: application/json
-}
-
-body:json {
-  {
-      "backend": "transformers-musicgen",
-      "model": "facebook/musicgen-small",
-      "input": "80s Synths playing Jazz"
-  }
-}

.devcontainer/docker-compose-devcontainer.yml

@@ -7,7 +7,7 @@ services:
       args:
       - FFMPEG=true
       - IMAGE_TYPE=extras
-      - GO_TAGS=stablediffusion p2p tts
+      - GO_TAGS=p2p tts
     env_file:
       - ../.env
     ports:

.env

@@ -29,6 +29,9 @@
 ## Enable/Disable single backend (useful if only one GPU is available)
 # LOCALAI_SINGLE_ACTIVE_BACKEND=true
 
+# Forces shutdown of the backends if busy (only if LOCALAI_SINGLE_ACTIVE_BACKEND is set)
+# LOCALAI_FORCE_BACKEND_SHUTDOWN=true
+
 ## Specify a build type. Available: cublas, openblas, clblas.
 ## cuBLAS: This is a GPU-accelerated version of the complete standard BLAS (Basic Linear Algebra Subprograms) library. It's provided by Nvidia and is part of their CUDA toolkit.
 ## OpenBLAS: This is an open-source implementation of the BLAS library that aims to provide highly optimized code for various platforms. It includes support for multi-threading and can be compiled to use hardware-specific features for additional performance. OpenBLAS can run on many kinds of hardware, including CPUs from Intel, AMD, and ARM.
@@ -38,12 +41,12 @@
 ## Uncomment and set to true to enable rebuilding from source
 # REBUILD=true
 
-## Enable go tags, available: stablediffusion, tts
+## Enable go tags, available: p2p, tts
-## stablediffusion: image generation with stablediffusion
+## p2p: enable distributed inferencing
 ## tts: enables text-to-speech with go-piper 
 ## (requires REBUILD=true)
 #
-# GO_TAGS=stablediffusion
+# GO_TAGS=p2p
 
 ## Path where to store generated images
 # LOCALAI_IMAGE_PATH=/tmp/generated/images
@@ -73,7 +76,7 @@
 
 ### Define a list of GRPC Servers for llama-cpp workers to distribute the load
 # https://github.com/ggerganov/llama.cpp/pull/6829
-# https://github.com/ggerganov/llama.cpp/blob/master/examples/rpc/README.md
+# https://github.com/ggerganov/llama.cpp/blob/master/tools/rpc/README.md
 # LLAMACPP_GRPC_SERVERS=""
 
 ### Enable to run parallel requests

.github/dependabot.yml

@@ -29,10 +29,6 @@ updates:
     schedule:
       # Check for updates to GitHub Actions every weekday
       interval: "weekly"
-  - package-ecosystem: "pip"
-    directory: "/backend/python/autogptq"
-    schedule:
-      interval: "weekly"
   - package-ecosystem: "pip"
     directory: "/backend/python/bark"
     schedule:
@@ -81,14 +77,6 @@ updates:
     directory: "/backend/python/transformers"
     schedule:
       interval: "weekly"
-  - package-ecosystem: "pip"
-    directory: "/backend/python/transformers-musicgen"
-    schedule:
-      interval: "weekly"
-  - package-ecosystem: "pip"
-    directory: "/backend/python/vall-e-x"
-    schedule:
-      interval: "weekly"
   - package-ecosystem: "pip"
     directory: "/backend/python/vllm"
     schedule:

.github/labeler.yml

@@ -1,4 +1,4 @@
-enhancements:
+enhancement:
  - head-branch: ['^feature', 'feature']
 
 dependencies:

.github/workflows/bump_deps.yaml

@@ -9,10 +9,10 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          - repository: "ggerganov/llama.cpp"
+          - repository: "ggml-org/llama.cpp"
             variable: "CPPLLAMA_VERSION"
             branch: "master"
-          - repository: "ggerganov/whisper.cpp"
+          - repository: "ggml-org/whisper.cpp"
             variable: "WHISPER_CPP_VERSION"
             branch: "master"
           - repository: "PABannier/bark.cpp"

.github/workflows/dependabot_auto.yml

@@ -14,7 +14,7 @@ jobs:
     steps:
       - name: Dependabot metadata
         id: metadata
-        uses: dependabot/fetch-metadata@v2.2.0
+        uses: dependabot/fetch-metadata@v2.4.0
         with:
           github-token: "${{ secrets.GITHUB_TOKEN }}"
           skip-commit-verification: true

.github/workflows/deploy-explorer.yaml

@@ -33,7 +33,7 @@ jobs:
         run: |
           CGO_ENABLED=0 make build-api
       - name: rm
-        uses: appleboy/ssh-action@v1.2.0
+        uses: appleboy/ssh-action@v1.2.2
         with:
             host: ${{ secrets.EXPLORER_SSH_HOST }}
             username: ${{ secrets.EXPLORER_SSH_USERNAME }}
@@ -42,7 +42,7 @@ jobs:
             script: |
                 sudo rm -rf local-ai/ || true
       - name: copy file via ssh
-        uses: appleboy/scp-action@v0.1.7
+        uses: appleboy/scp-action@v1.0.0
         with:
             host: ${{ secrets.EXPLORER_SSH_HOST }}
             username: ${{ secrets.EXPLORER_SSH_USERNAME }}
@@ -53,7 +53,7 @@ jobs:
             rm: true
             target: ./local-ai
       - name: restarting
-        uses: appleboy/ssh-action@v1.2.0
+        uses: appleboy/ssh-action@v1.2.2
         with:
             host: ${{ secrets.EXPLORER_SSH_HOST }}
             username: ${{ secrets.EXPLORER_SSH_USERNAME }}

.github/workflows/generate_grpc_cache.yaml

@@ -2,9 +2,10 @@ name: 'generate and publish GRPC docker caches'
 
 on:
   workflow_dispatch:
-  push:
+
-    branches:
+  schedule:
-      - master
+    # daily at midnight
+    - cron: '0 0 * * *'
 
 concurrency:
   group: grpc-cache-${{ github.head_ref || github.ref }}-${{ github.repository }}
@@ -16,7 +17,7 @@ jobs:
       matrix:
         include:
           - grpc-base-image: ubuntu:22.04
-            runs-on: 'ubuntu-latest'
+            runs-on: 'arc-runner-set'
             platforms: 'linux/amd64,linux/arm64'
     runs-on: ${{matrix.runs-on}}
     steps:

.github/workflows/generate_intel_image.yaml

@@ -15,7 +15,7 @@ jobs:
     strategy:
       matrix:
         include:
-          - base-image: intel/oneapi-basekit:2025.0.0-0-devel-ubuntu22.04
+          - base-image: intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04
             runs-on: 'ubuntu-latest'
             platforms: 'linux/amd64'
     runs-on: ${{matrix.runs-on}}

.github/workflows/image-pr.yml

@@ -33,6 +33,7 @@ jobs:
       # Pushing with all jobs in parallel
       # eats the bandwidth of all the nodes
       max-parallel: ${{ github.event_name != 'pull_request' && 4 || 8 }}
+      fail-fast: false
       matrix:
         include:
           # This is basically covered by the AIO test
@@ -56,26 +57,35 @@ jobs:
             runs-on: 'arc-runner-set'
             base-image: "ubuntu:22.04"
             makeflags: "--jobs=3 --output-sync=target"
-          # - build-type: 'hipblas'
+          - build-type: 'hipblas'
-          #   platforms: 'linux/amd64'
+            platforms: 'linux/amd64'
-          #   tag-latest: 'false'
+            tag-latest: 'false'
-          #   tag-suffix: '-hipblas'
+            tag-suffix: '-hipblas'
-          #   ffmpeg: 'false'
+            ffmpeg: 'false'
-          #   image-type: 'extras'
+            image-type: 'extras'
-          #   base-image: "rocm/dev-ubuntu-22.04:6.1"
+            base-image: "rocm/dev-ubuntu-22.04:6.1"
-          #   grpc-base-image: "ubuntu:22.04"
+            grpc-base-image: "ubuntu:22.04"
-          #   runs-on: 'arc-runner-set'
+            runs-on: 'arc-runner-set'
-          #   makeflags: "--jobs=3 --output-sync=target"
+            makeflags: "--jobs=3 --output-sync=target"
-          # - build-type: 'sycl_f16'
+          - build-type: 'sycl_f16'
-          #   platforms: 'linux/amd64'
+            platforms: 'linux/amd64'
-          #   tag-latest: 'false'
+            tag-latest: 'false'
-          #   base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
+            base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
-          #   grpc-base-image: "ubuntu:22.04"
+            grpc-base-image: "ubuntu:22.04"
-          #   tag-suffix: 'sycl-f16-ffmpeg'
+            tag-suffix: 'sycl-f16-ffmpeg'
-          #   ffmpeg: 'true'
+            ffmpeg: 'true'
-          #   image-type: 'extras'
+            image-type: 'extras'
-          #   runs-on: 'arc-runner-set'
+            runs-on: 'arc-runner-set'
-          #   makeflags: "--jobs=3 --output-sync=target"
+            makeflags: "--jobs=3 --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"
   # core-image-build:
   #   uses: ./.github/workflows/image_build.yml
   #   with:

.github/workflows/image.yml

@@ -45,13 +45,13 @@ jobs:
           - build-type: 'hipblas'
             platforms: 'linux/amd64'
             tag-latest: 'auto'
-            tag-suffix: '-hipblas-ffmpeg'
+            tag-suffix: '-hipblas-extras'
             ffmpeg: 'true'
             image-type: 'extras'
             aio: "-aio-gpu-hipblas"
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             grpc-base-image: "ubuntu:22.04"
-            latest-image: 'latest-gpu-hipblas'
+            latest-image: 'latest-gpu-hipblas-extras'
             latest-image-aio: 'latest-aio-gpu-hipblas'
             runs-on: 'arc-runner-set'
             makeflags: "--jobs=3 --output-sync=target"
@@ -59,32 +59,13 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-hipblas'
-            ffmpeg: 'false'
-            image-type: 'extras'
-            base-image: "rocm/dev-ubuntu-22.04:6.1"
-            grpc-base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
-            makeflags: "--jobs=3 --output-sync=target"
-          - build-type: 'hipblas'
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-hipblas-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             grpc-base-image: "ubuntu:22.04"
             runs-on: 'arc-runner-set'
             makeflags: "--jobs=3 --output-sync=target"
-          - build-type: 'hipblas'
+            latest-image: 'latest-gpu-hipblas'
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-hipblas-core'
-            ffmpeg: 'false'
-            image-type: 'core'
-            base-image: "rocm/dev-ubuntu-22.04:6.1"
-            grpc-base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
-            makeflags: "--jobs=3 --output-sync=target"
   self-hosted-jobs:
     uses: ./.github/workflows/image_build.yml
     with:
@@ -114,110 +95,58 @@ jobs:
       max-parallel: ${{ github.event_name != 'pull_request' && 5 || 8 }}
       matrix:
         include:
-          # Extra images
-          - build-type: ''
-            #platforms: 'linux/amd64,linux/arm64'
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: ''
-            ffmpeg: ''
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=3 --output-sync=target"
-          - build-type: ''
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-ffmpeg'
-            ffmpeg: 'true'
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'false'
-            tag-suffix: '-cublas-cuda11'
+            tag-suffix: '-cublas-cuda11-extras'
-            ffmpeg: ''
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=3 --output-sync=target"
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "0"
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda12'
-            ffmpeg: ''
-            image-type: 'extras'
-            runs-on: 'arc-runner-set'
-            base-image: "ubuntu:22.04"
-            makeflags: "--jobs=3 --output-sync=target"
-          - build-type: 'cublas'
-            cuda-major-version: "11"
-            cuda-minor-version: "7"
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: '-cublas-cuda11-ffmpeg'
             ffmpeg: 'true'
             image-type: 'extras'
             runs-on: 'arc-runner-set'
             base-image: "ubuntu:22.04"
             aio: "-aio-gpu-nvidia-cuda-11"
-            latest-image: 'latest-gpu-nvidia-cuda-11'
+            latest-image: 'latest-gpu-nvidia-cuda-11-extras'
             latest-image-aio: 'latest-aio-gpu-nvidia-cuda-11'
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
             platforms: 'linux/amd64'
-            tag-latest: 'auto'
+            tag-latest: 'false'
-            tag-suffix: '-cublas-cuda12-ffmpeg'
+            tag-suffix: '-cublas-cuda12-extras'
             ffmpeg: 'true'
             image-type: 'extras'
             runs-on: 'arc-runner-set'
             base-image: "ubuntu:22.04"
             aio: "-aio-gpu-nvidia-cuda-12"
-            latest-image: 'latest-gpu-nvidia-cuda-12'
+            latest-image: 'latest-gpu-nvidia-cuda-12-extras'
             latest-image-aio: 'latest-aio-gpu-nvidia-cuda-12'
             makeflags: "--jobs=3 --output-sync=target"
-          - build-type: ''
-            #platforms: 'linux/amd64,linux/arm64'
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            tag-suffix: ''
-            ffmpeg: ''
-            image-type: 'extras'
-            base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
-            makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'sycl_f16'
             platforms: 'linux/amd64'
-            tag-latest: 'auto'
+            tag-latest: 'false'
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             grpc-base-image: "ubuntu:22.04"
-            tag-suffix: '-sycl-f16-ffmpeg'
+            tag-suffix: '-sycl-f16-extras'
             ffmpeg: 'true'
             image-type: 'extras'
             runs-on: 'arc-runner-set'
             aio: "-aio-gpu-intel-f16"
-            latest-image: 'latest-gpu-intel-f16'
+            latest-image: 'latest-gpu-intel-f16-extras'
             latest-image-aio: 'latest-aio-gpu-intel-f16'
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'sycl_f32'
             platforms: 'linux/amd64'
-            tag-latest: 'auto'
+            tag-latest: 'false'
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             grpc-base-image: "ubuntu:22.04"
-            tag-suffix: '-sycl-f32-ffmpeg'
+            tag-suffix: '-sycl-f32-extras'
             ffmpeg: 'true'
             image-type: 'extras'
             runs-on: 'arc-runner-set'
             aio: "-aio-gpu-intel-f32"
-            latest-image: 'latest-gpu-intel-f32'
+            latest-image: 'latest-gpu-intel-f32-extras'
             latest-image-aio: 'latest-aio-gpu-intel-f32'
             makeflags: "--jobs=3 --output-sync=target"
           # Core images
@@ -226,41 +155,23 @@ jobs:
             tag-latest: 'false'
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             grpc-base-image: "ubuntu:22.04"
-            tag-suffix: '-sycl-f16-core'
+            tag-suffix: '-sycl-f16'
-            ffmpeg: 'false'
+            ffmpeg: 'true'
             image-type: 'core'
             runs-on: 'arc-runner-set'
             makeflags: "--jobs=3 --output-sync=target"
+            latest-image: 'latest-gpu-intel-f16'
           - build-type: 'sycl_f32'
             platforms: 'linux/amd64'
             tag-latest: 'false'
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             grpc-base-image: "ubuntu:22.04"
-            tag-suffix: '-sycl-f32-core'
+            tag-suffix: '-sycl-f32'
-            ffmpeg: 'false'
-            image-type: 'core'
-            runs-on: 'arc-runner-set'
-            makeflags: "--jobs=3 --output-sync=target"
-          - build-type: 'sycl_f16'
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
-            grpc-base-image: "ubuntu:22.04"
-            tag-suffix: '-sycl-f16-ffmpeg-core'
-            ffmpeg: 'true'
-            image-type: 'core'
-            runs-on: 'arc-runner-set'
-            makeflags: "--jobs=3 --output-sync=target"
-          - build-type: 'sycl_f32'
-            platforms: 'linux/amd64'
-            tag-latest: 'false'
-            base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
-            grpc-base-image: "ubuntu:22.04"
-            tag-suffix: '-sycl-f32-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
             runs-on: 'arc-runner-set'
             makeflags: "--jobs=3 --output-sync=target"
+            latest-image: 'latest-gpu-intel-f32'
 
   core-image-build:
     uses: ./.github/workflows/image_build.yml
@@ -293,7 +204,7 @@ jobs:
           - build-type: ''
             platforms: 'linux/amd64,linux/arm64'
             tag-latest: 'auto'
-            tag-suffix: '-ffmpeg-core'
+            tag-suffix: ''
             ffmpeg: 'true'
             image-type: 'core'
             base-image: "ubuntu:22.04"
@@ -308,97 +219,75 @@ jobs:
             cuda-minor-version: "7"
             platforms: 'linux/amd64'
             tag-latest: 'false'
-            tag-suffix: '-cublas-cuda11-core'
+            tag-suffix: '-cublas-cuda11'
-            ffmpeg: ''
-            image-type: 'core'
-            base-image: "ubuntu:22.04"
-            runs-on: 'arc-runner-set'
-            makeflags: "--jobs=4 --output-sync=target"
-            skip-drivers: 'false'
-          - build-type: 'cublas'
-            cuda-major-version: "12"
-            cuda-minor-version: "0"
-            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'
-            makeflags: "--jobs=4 --output-sync=target"
-            skip-drivers: 'false'
-          - build-type: 'cublas'
-            cuda-major-version: "11"
-            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'
             base-image: "ubuntu:22.04"
             makeflags: "--jobs=4 --output-sync=target"
             skip-drivers: 'false'
+            latest-image: 'latest-gpu-nvidia-cuda-12'
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'false'
-            tag-suffix: '-cublas-cuda12-ffmpeg-core'
+            tag-suffix: '-cublas-cuda12'
             ffmpeg: 'true'
             image-type: 'core'
             runs-on: 'arc-runner-set'
             base-image: "ubuntu:22.04"
             skip-drivers: 'false'
             makeflags: "--jobs=4 --output-sync=target"
+            latest-image: 'latest-gpu-nvidia-cuda-12'
           - build-type: 'vulkan'
             platforms: 'linux/amd64'
             tag-latest: 'false'
-            tag-suffix: '-vulkan-ffmpeg-core'
+            tag-suffix: '-vulkan'
-            latest-image: 'latest-vulkan-ffmpeg-core'
             ffmpeg: 'true'
             image-type: 'core'
             runs-on: 'arc-runner-set'
             base-image: "ubuntu:22.04"
             skip-drivers: 'false'
             makeflags: "--jobs=4 --output-sync=target"
-#  parallel-builds:
+            latest-image: 'latest-gpu-vulkan'
-#    uses: ./.github/workflows/image_build.yml
+  gh-runner:
-#    with:
+    uses: ./.github/workflows/image_build.yml
-#      tag-latest: ${{ matrix.tag-latest }}
+    with:
-#      tag-suffix: ${{ matrix.tag-suffix }}
+      tag-latest: ${{ matrix.tag-latest }}
-#      ffmpeg: ${{ matrix.ffmpeg }}
+      tag-suffix: ${{ matrix.tag-suffix }}
-#      image-type: ${{ matrix.image-type }}
+      ffmpeg: ${{ matrix.ffmpeg }}
-#      build-type: ${{ matrix.build-type }}
+      image-type: ${{ matrix.image-type }}
-#      cuda-major-version: ${{ matrix.cuda-major-version }}
+      build-type: ${{ matrix.build-type }}
-#      cuda-minor-version: ${{ matrix.cuda-minor-version }}
+      cuda-major-version: ${{ matrix.cuda-major-version }}
-#      platforms: ${{ matrix.platforms }}
+      cuda-minor-version: ${{ matrix.cuda-minor-version }}
-#      runs-on: ${{ matrix.runs-on }}
+      platforms: ${{ matrix.platforms }}
-#      aio: ${{ matrix.aio }}
+      runs-on: ${{ matrix.runs-on }}
-#      base-image: ${{ matrix.base-image }}
+      aio: ${{ matrix.aio }}
-#      grpc-base-image: ${{ matrix.grpc-base-image }}
+      base-image: ${{ matrix.base-image }}
-#      makeflags: ${{ matrix.makeflags }}
+      grpc-base-image: ${{ matrix.grpc-base-image }}
-#      latest-image: ${{ matrix.latest-image }}
+      makeflags: ${{ matrix.makeflags }}
-#      latest-image-aio: ${{ matrix.latest-image-aio }}
+      latest-image: ${{ matrix.latest-image }}
-#      skip-drivers: ${{ matrix.skip-drivers }}
+      latest-image-aio: ${{ matrix.latest-image-aio }}
-#    secrets:
+      skip-drivers: ${{ matrix.skip-drivers }}
-#      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
+    secrets:
-#      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
+      dockerUsername: ${{ secrets.DOCKERHUB_USERNAME }}
-#      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
+      dockerPassword: ${{ secrets.DOCKERHUB_PASSWORD }}
-#      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
+      quayUsername: ${{ secrets.LOCALAI_REGISTRY_USERNAME }}
-#    strategy:
+      quayPassword: ${{ secrets.LOCALAI_REGISTRY_PASSWORD }}
-#      matrix:
+    strategy:
-#        include:
+      matrix:
-#          - build-type: 'cublas'
+        include:
-#            cuda-major-version: "12"
+          - build-type: 'cublas'
-#            cuda-minor-version: "0"
+            cuda-major-version: "12"
-#            platforms: 'linux/arm64'
+            cuda-minor-version: "0"
-#            tag-latest: 'false'
+            platforms: 'linux/arm64'
-#            tag-suffix: '-nvidia-l4t-arm64-core'
+            tag-latest: 'false'
-#            latest-image: 'latest-nvidia-l4t-arm64-core'
+            tag-suffix: '-nvidia-l4t-arm64'
-#            ffmpeg: 'true'
+            latest-image: 'latest-nvidia-l4t-arm64'
-#            image-type: 'core'
+            ffmpeg: 'true'
-#            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+            image-type: 'core'
-#            runs-on: 'self-hosted'
+            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
-#            makeflags: "--jobs=4 --output-sync=target"
+            runs-on: 'ubuntu-24.04-arm'
-#            skip-drivers: 'true'
+            makeflags: "--jobs=4 --output-sync=target"
+            skip-drivers: 'true'

.github/workflows/image_build.yml

@@ -310,6 +310,11 @@ jobs:
           tags: ${{ steps.meta_aio_dockerhub.outputs.tags }}
           labels: ${{ steps.meta_aio_dockerhub.outputs.labels }}
 
+      - name: Cleanup
+        run: |
+          docker builder prune -f
+          docker system prune --force --volumes --all
+
       - name: Latest tag
         # run this on branches, when it is a tag and there is a latest-image defined
         if: github.event_name != 'pull_request' && inputs.latest-image != ''  && github.ref_type == 'tag'

.github/workflows/notify-models.yaml

@@ -8,7 +8,7 @@ jobs:
   notify-discord:
     if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model')) }}
     env:
-        MODEL_NAME: hermes-2-theta-llama-3-8b
+        MODEL_NAME: gemma-3-12b-it
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4
@@ -16,9 +16,9 @@ jobs:
         fetch-depth: 0 # needed to checkout all branches for this Action to work
     - uses: mudler/localai-github-action@v1
       with:
-        model: 'hermes-2-theta-llama-3-8b' # Any from models.localai.io, or from huggingface.com with: "huggingface://<repository>/file"
+        model: 'gemma-3-12b-it' # Any from models.localai.io, or from huggingface.com with: "huggingface://<repository>/file"
         # Check the PR diff using the current branch and the base branch of the PR
-    - uses: GrantBirki/git-diff-action@v2.7.0
+    - uses: GrantBirki/git-diff-action@v2.8.0
       id: git-diff-action
       with:
             json_diff_file_output: diff.json
@@ -79,7 +79,7 @@ jobs:
         args: ${{ steps.summarize.outputs.message }}
     - name: Setup tmate session if fails
       if: ${{ failure() }}
-      uses: mxschmitt/action-tmate@v3.19
+      uses: mxschmitt/action-tmate@v3.22
       with:
         detached: true
         connect-timeout-seconds: 180
@@ -87,7 +87,7 @@ jobs:
   notify-twitter:
     if: ${{ (github.event.pull_request.merged == true) && (contains(github.event.pull_request.labels.*.name, 'area/ai-model')) }}
     env:
-        MODEL_NAME: hermes-2-theta-llama-3-8b
+        MODEL_NAME: gemma-3-12b-it
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4
@@ -99,7 +99,7 @@ jobs:
         docker run -e -ti -d --name local-ai -p 8080:8080 localai/localai:master-ffmpeg-core run --debug $MODEL_NAME
         until [ "`docker inspect -f {{.State.Health.Status}} local-ai`" == "healthy" ]; do echo "Waiting for container to be ready";  docker logs --tail 10 local-ai; sleep 2; done
       # Check the PR diff using the current branch and the base branch of the PR
-    - uses: GrantBirki/git-diff-action@v2.7.0
+    - uses: GrantBirki/git-diff-action@v2.8.0
       id: git-diff-action
       with:
             json_diff_file_output: diff.json
@@ -161,7 +161,7 @@ jobs:
         TWITTER_ACCESS_TOKEN_SECRET: ${{ secrets.TWITTER_ACCESS_TOKEN_SECRET }}
     - name: Setup tmate session if fails
       if: ${{ failure() }}
-      uses: mxschmitt/action-tmate@v3.19
+      uses: mxschmitt/action-tmate@v3.22
       with:
         detached: true
         connect-timeout-seconds: 180

.github/workflows/notify-releases.yaml

@@ -14,7 +14,7 @@ jobs:
     steps:
     - uses: mudler/localai-github-action@v1
       with:
-        model: 'hermes-2-theta-llama-3-8b' # Any from models.localai.io, or from huggingface.com with: "huggingface://<repository>/file"
+        model: 'gemma-3-12b-it' # Any from models.localai.io, or from huggingface.com with: "huggingface://<repository>/file"
     - name: Summarize
       id: summarize
       run: |

.github/workflows/release.yaml

@@ -36,6 +36,7 @@ jobs:
           sudo apt-get update
           sudo apt-get install build-essential ffmpeg protobuf-compiler ccache upx-ucl gawk
           sudo apt-get install -qy binutils-aarch64-linux-gnu gcc-aarch64-linux-gnu g++-aarch64-linux-gnu libgmock-dev
+          make install-go-tools
       - name: Install CUDA Dependencies
         run: |
           curl -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/cross-linux-aarch64/cuda-keyring_1.1-1_all.deb
@@ -123,7 +124,7 @@ jobs:
             release/*
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.19
+        uses: mxschmitt/action-tmate@v3.22
         with:
           detached: true
           connect-timeout-seconds: 180
@@ -151,6 +152,7 @@ jobs:
         run: |
           sudo apt-get update
           sudo apt-get install -y wget curl build-essential ffmpeg protobuf-compiler ccache upx-ucl gawk cmake libgmock-dev
+          make install-go-tools
       - name: Intel Dependencies
         run: |
           wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | sudo tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null
@@ -232,45 +234,12 @@ jobs:
             release/*
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.19
+        uses: mxschmitt/action-tmate@v3.22
         with:
           detached: true
           connect-timeout-seconds: 180
           limit-access-to-actor: true
-  build-stablediffusion:
+
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clone
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-      - uses: actions/setup-go@v5
-        with:
-          go-version: '1.21.x'
-          cache: false
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y --no-install-recommends libopencv-dev protobuf-compiler ccache upx-ucl
-          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
-          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
-      - name: Build stablediffusion
-        run: |
-          export PATH=$PATH:$GOPATH/bin
-          make backend-assets/grpc/stablediffusion
-          mkdir -p release && cp backend-assets/grpc/stablediffusion release
-        env:
-          GO_TAGS: stablediffusion
-      - uses: actions/upload-artifact@v4
-        with:
-          name: stablediffusion
-          path: release/
-      - name: Release
-        uses: softprops/action-gh-release@v2
-        if: startsWith(github.ref, 'refs/tags/')
-        with:
-          files: |
-            release/*
 
   build-macOS-x86_64:
     runs-on: macos-13
@@ -286,8 +255,7 @@ jobs:
       - name: Dependencies
         run: |
           brew install protobuf grpc
-          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@8ba23be9613c672d40ae261d2a1335d639bdd59b
+          make install-go-tools
-          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.0
       - name: Build
         id: build
         run: |
@@ -308,7 +276,7 @@ jobs:
             release/*
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.19
+        uses: mxschmitt/action-tmate@v3.22
         with:
           detached: true
           connect-timeout-seconds: 180
@@ -328,8 +296,7 @@ jobs:
       - name: Dependencies
         run: |
           brew install protobuf grpc libomp llvm
-          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+          make install-go-tools
-          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
       - name: Build
         id: build
         run: |
@@ -350,7 +317,7 @@ jobs:
             release/*
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.19
+        uses: mxschmitt/action-tmate@v3.22
         with:
           detached: true
           connect-timeout-seconds: 180

.github/workflows/secscan.yaml

@@ -18,7 +18,7 @@ jobs:
         if: ${{ github.actor != 'dependabot[bot]' }}
       - name: Run Gosec Security Scanner
         if: ${{ github.actor != 'dependabot[bot]' }}
-        uses: securego/gosec@v2.22.0
+        uses: securego/gosec@v2.22.4
         with:
           # we let the report trigger content trigger a failure using the GitHub Security features.
           args: '-no-fail -fmt sarif -out results.sarif ./...'

.github/workflows/test-extra.yml

@@ -35,30 +35,6 @@ jobs:
         run: |
            make --jobs=5 --output-sync=target -C backend/python/transformers
            make --jobs=5 --output-sync=target -C backend/python/transformers test
-
-  tests-sentencetransformers:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clone
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install build-essential ffmpeg
-          # Install UV
-          curl -LsSf https://astral.sh/uv/install.sh | sh
-          sudo apt-get install -y ca-certificates cmake curl patch python3-pip
-          sudo apt-get install -y libopencv-dev
-          pip install --user --no-cache-dir grpcio-tools==1.64.1
-
-      - name: Test sentencetransformers
-        run: |
-           make --jobs=5 --output-sync=target -C backend/python/sentencetransformers
-           make --jobs=5 --output-sync=target -C backend/python/sentencetransformers test
-
-
   tests-rerankers:
     runs-on: ubuntu-latest
     steps:
@@ -102,78 +78,47 @@ jobs:
           make --jobs=5 --output-sync=target -C backend/python/diffusers
           make --jobs=5 --output-sync=target -C backend/python/diffusers test
 
-  tests-parler-tts:
+  #tests-vllm:
-    runs-on: ubuntu-latest
+  #  runs-on: ubuntu-latest
-    steps:
+  #  steps:
-      - name: Clone
+  #    - name: Clone
-        uses: actions/checkout@v4
+  #      uses: actions/checkout@v4
-        with:
+  #      with:
-          submodules: true
+  #        submodules: true
-      - name: Dependencies
+  #    - name: Dependencies
-        run: |
+  #      run: |
-          sudo apt-get update
+  #        sudo apt-get update
-          sudo apt-get install build-essential ffmpeg
+  #        sudo apt-get install -y build-essential ffmpeg
-          # Install UV
+  #        sudo apt-get install -y ca-certificates cmake curl patch python3-pip
-          curl -LsSf https://astral.sh/uv/install.sh | sh
+  #        sudo apt-get install -y libopencv-dev
-          sudo apt-get install -y ca-certificates cmake curl patch python3-pip
+  #        # Install UV
-          sudo apt-get install -y libopencv-dev
+  #        curl -LsSf https://astral.sh/uv/install.sh | sh
-          pip install --user --no-cache-dir grpcio-tools==1.64.1
+  #        pip install --user --no-cache-dir grpcio-tools==1.64.1
+  #    - name: Test vllm backend
+  #      run: |
+  #        make --jobs=5 --output-sync=target -C backend/python/vllm
+  #        make --jobs=5 --output-sync=target -C backend/python/vllm test
+  # tests-transformers-musicgen:
+  #   runs-on: ubuntu-latest
+  #   steps:
+  #     - name: Clone
+  #       uses: actions/checkout@v4
+  #       with:
+  #         submodules: true
+  #     - name: Dependencies
+  #       run: |
+  #         sudo apt-get update
+  #         sudo apt-get install build-essential ffmpeg
+  #         # Install UV
+  #         curl -LsSf https://astral.sh/uv/install.sh | sh
+  #         sudo apt-get install -y ca-certificates cmake curl patch python3-pip
+  #         sudo apt-get install -y libopencv-dev
+  #         pip install --user --no-cache-dir grpcio-tools==1.64.1
 
-      - name: Test parler-tts
+  #     - name: Test transformers-musicgen
-        run: |
+  #       run: |
-           make --jobs=5 --output-sync=target -C backend/python/parler-tts
+  #          make --jobs=5 --output-sync=target -C backend/python/transformers-musicgen
-           make --jobs=5 --output-sync=target -C backend/python/parler-tts test
+  #          make --jobs=5 --output-sync=target -C backend/python/transformers-musicgen test
-      - name: Setup tmate session if tests fail
-        if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.19
-        with:
-          detached: true
-          connect-timeout-seconds: 180
-          limit-access-to-actor: true
-
-  tests-openvoice:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clone
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install build-essential ffmpeg
-          # Install UV
-          curl -LsSf https://astral.sh/uv/install.sh | sh
-          sudo apt-get install -y ca-certificates cmake curl patch python3-pip
-          sudo apt-get install -y libopencv-dev
-          pip install --user --no-cache-dir grpcio-tools==1.64.1
-
-      - name: Test openvoice
-        run: |
-           make --jobs=5 --output-sync=target -C backend/python/openvoice
-           make --jobs=5 --output-sync=target -C backend/python/openvoice test
-
-  tests-transformers-musicgen:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clone
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install build-essential ffmpeg
-          # Install UV
-          curl -LsSf https://astral.sh/uv/install.sh | sh
-          sudo apt-get install -y ca-certificates cmake curl patch python3-pip
-          sudo apt-get install -y libopencv-dev
-          pip install --user --no-cache-dir grpcio-tools==1.64.1
-
-      - name: Test transformers-musicgen
-        run: |
-           make --jobs=5 --output-sync=target -C backend/python/transformers-musicgen
-           make --jobs=5 --output-sync=target -C backend/python/transformers-musicgen test
 
   # tests-bark:
   #   runs-on: ubuntu-latest
@@ -260,26 +205,6 @@ jobs:
   #       run: |
   #          make --jobs=5 --output-sync=target -C backend/python/vllm
   #          make --jobs=5 --output-sync=target -C backend/python/vllm test
-  tests-vallex:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clone
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-      - name: Dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install build-essential ffmpeg
-          # Install UV
-          curl -LsSf https://astral.sh/uv/install.sh | sh
-          sudo apt-get install -y ca-certificates cmake curl patch python3-pip
-          sudo apt-get install -y libopencv-dev
-          pip install --user --no-cache-dir grpcio-tools==1.64.1
-      - name: Test vall-e-x
-        run: |
-           make --jobs=5 --output-sync=target -C backend/python/vall-e-x
-           make --jobs=5 --output-sync=target -C backend/python/vall-e-x test
 
   tests-coqui:
     runs-on: ubuntu-latest

.github/workflows/test.yml

@@ -71,7 +71,7 @@ jobs:
         run: |
           sudo apt-get update
           sudo apt-get install build-essential ccache upx-ucl curl ffmpeg
-          sudo apt-get install -y libgmock-dev
+          sudo apt-get install -y libgmock-dev clang
           curl https://repo.anaconda.com/pkgs/misc/gpgkeys/anaconda.asc | gpg --dearmor > conda.gpg && \
              sudo install -o root -g root -m 644 conda.gpg /usr/share/keyrings/conda-archive-keyring.gpg && \
              gpg --keyring /usr/share/keyrings/conda-archive-keyring.gpg --no-default-keyring --fingerprint 34161F5BF5EB1D4BFBBB8F0A8AEB4F8B29D82806 && \
@@ -96,19 +96,17 @@ jobs:
 
           go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
           go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+          go install github.com/GeertJohan/go.rice/rice@latest
 
           # The python3-grpc-tools package in 22.04 is too old
           pip install --user grpcio-tools
 
-          sudo rm -rfv /usr/bin/conda || true
+          make -C backend/python/transformers
-          PATH=$PATH:/opt/conda/bin make -C backend/python/sentencetransformers
 
           # Pre-build piper before we start tests in order to have shared libraries in place
           make sources/go-piper && \
           GO_TAGS="tts" make -C sources/go-piper piper.o && \
-          sudo cp -rfv sources/go-piper/piper-phonemize/pi/lib/. /usr/lib/ && \
+          sudo cp -rfv sources/go-piper/piper-phonemize/pi/lib/. /usr/lib/
-          # Pre-build stable diffusion before we install a newer version of abseil (not compatible with stablediffusion-ncn)
-          PATH="$PATH:/root/go/bin" GO_TAGS="stablediffusion tts" GRPC_BACKENDS=backend-assets/grpc/stablediffusion make build
         env:
           CUDA_VERSION: 12-4
       - name: Cache grpc
@@ -130,10 +128,10 @@ jobs:
           cd grpc && cd cmake/build && sudo make --jobs 5 install
       - name: Test
         run: |
-          PATH="$PATH:/root/go/bin" GO_TAGS="stablediffusion tts" make --jobs 5 --output-sync=target test
+          PATH="$PATH:/root/go/bin" GO_TAGS="tts" make --jobs 5 --output-sync=target test
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.19
+        uses: mxschmitt/action-tmate@v3.22
         with:
           detached: true
           connect-timeout-seconds: 180
@@ -186,6 +184,7 @@ jobs:
           rm protoc.zip
           go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
           go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+          go install github.com/GeertJohan/go.rice/rice@latest
           PATH="$PATH:$HOME/go/bin" make protogen-go
       - name: Build images
         run: |
@@ -197,7 +196,7 @@ jobs:
             make run-e2e-aio
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.19
+        uses: mxschmitt/action-tmate@v3.22
         with:
           detached: true
           connect-timeout-seconds: 180
@@ -225,6 +224,7 @@ jobs:
         run: |
           brew install protobuf grpc make protoc-gen-go protoc-gen-go-grpc libomp llvm
           pip install --user --no-cache-dir grpcio-tools
+          go install github.com/GeertJohan/go.rice/rice@latest
       - name: Test
         run: |
           export C_INCLUDE_PATH=/usr/local/include
@@ -235,7 +235,7 @@ jobs:
           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
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.19
+        uses: mxschmitt/action-tmate@v3.22
         with:
           detached: true
           connect-timeout-seconds: 180

.vscode/launch.json

@@ -26,7 +26,7 @@
                 "LOCALAI_P2P": "true",
                 "LOCALAI_FEDERATED": "true"
             },
-            "buildFlags": ["-tags", "stablediffusion p2p tts", "-v"],
+            "buildFlags": ["-tags", "p2p tts", "-v"],
             "envFile": "${workspaceFolder}/.env",
             "cwd": "${workspaceRoot}"
         }

Dockerfile

@@ -15,8 +15,7 @@ ARG TARGETARCH
 ARG TARGETVARIANT
 
 ENV DEBIAN_FRONTEND=noninteractive
-ENV EXTERNAL_GRPC_BACKENDS="coqui:/build/backend/python/coqui/run.sh,huggingface-embeddings:/build/backend/python/sentencetransformers/run.sh,transformers:/build/backend/python/transformers/run.sh,sentencetransformers:/build/backend/python/sentencetransformers/run.sh,rerankers:/build/backend/python/rerankers/run.sh,autogptq:/build/backend/python/autogptq/run.sh,bark:/build/backend/python/bark/run.sh,diffusers:/build/backend/python/diffusers/run.sh,openvoice:/build/backend/python/openvoice/run.sh,vall-e-x:/build/backend/python/vall-e-x/run.sh,vllm:/build/backend/python/vllm/run.sh,mamba:/build/backend/python/mamba/run.sh,exllama2:/build/backend/python/exllama2/run.sh,transformers-musicgen:/build/backend/python/transformers-musicgen/run.sh,parler-tts:/build/backend/python/parler-tts/run.sh"
+ENV EXTERNAL_GRPC_BACKENDS="coqui:/build/backend/python/coqui/run.sh,transformers:/build/backend/python/transformers/run.sh,rerankers:/build/backend/python/rerankers/run.sh,bark:/build/backend/python/bark/run.sh,diffusers:/build/backend/python/diffusers/run.sh,faster-whisper:/build/backend/python/faster-whisper/run.sh,kokoro:/build/backend/python/kokoro/run.sh,vllm:/build/backend/python/vllm/run.sh,exllama2:/build/backend/python/exllama2/run.sh"
-
 
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
@@ -25,6 +24,7 @@ RUN apt-get update && \
         ca-certificates \
         curl libssl-dev \
         git \
+        git-lfs \
         unzip upx-ucl && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
@@ -46,9 +46,10 @@ EOT
 RUN curl -L -s https://go.dev/dl/go${GO_VERSION}.linux-${TARGETARCH}.tar.gz | tar -C /usr/local -xz
 ENV PATH=$PATH:/root/go/bin:/usr/local/go/bin
 
-# Install grpc compilers
+# Install grpc compilers and rice
 RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2 && \
-    go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+    go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af && \
+    go install github.com/GeertJohan/go.rice/rice@latest
 
 COPY --chmod=644 custom-ca-certs/* /usr/local/share/ca-certificates/
 RUN update-ca-certificates
@@ -69,14 +70,10 @@ ENV PATH=/opt/rocm/bin:${PATH}
 # OpenBLAS requirements and stable diffusion
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-        libopenblas-dev \
+        libopenblas-dev && \
-        libopencv-dev && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
-# Set up OpenCV
-RUN ln -s /usr/include/opencv4/opencv2 /usr/include/opencv2
-
 WORKDIR /build
 
 ###################################
@@ -251,7 +248,7 @@ RUN git clone --recurse-submodules --jobs 4 -b ${GRPC_VERSION} --depth 1 --shall
 
 FROM requirements-drivers AS builder-base
 
-ARG GO_TAGS="stablediffusion tts p2p"
+ARG GO_TAGS="tts p2p"
 ARG GRPC_BACKENDS
 ARG MAKEFLAGS
 ARG LD_FLAGS="-s -w"
@@ -285,35 +282,12 @@ RUN <<EOT bash
     fi
 EOT
 
-
-###################################
-###################################
-
-# This first portion of builder holds the layers specifically used to build backend-assets/grpc/stablediffusion
-# In most cases, builder is the image you should be using - however, this can save build time if one just needs to copy backend-assets/grpc/stablediffusion and nothing else.
-FROM builder-base AS builder-sd
-
-# stablediffusion does not tolerate a newer version of abseil, copy only over enough elements to build it
-COPY Makefile .
-COPY go.mod .
-COPY go.sum .
-COPY backend/backend.proto ./backend/backend.proto
-COPY backend/go/image/stablediffusion ./backend/go/image/stablediffusion
-COPY pkg/grpc ./pkg/grpc
-COPY pkg/stablediffusion ./pkg/stablediffusion
-RUN git init
-RUN make sources/go-stable-diffusion
-RUN touch prepare-sources
-
-# Actually build the backend
-RUN GRPC_BACKENDS=backend-assets/grpc/stablediffusion make backend-assets/grpc/stablediffusion
-
 ###################################
 ###################################
 
 # 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 builder-sd AS builder
+FROM builder-base AS builder
 
 # Install the pre-built GRPC
 COPY --from=grpc /opt/grpc /usr/local
@@ -327,11 +301,10 @@ COPY .git .
 RUN make prepare
 
 ## Build the binary
-## If it's CUDA or hipblas, we want to skip some of the llama-compat backends to save space
+## If we're on arm64 AND using cublas/hipblas, skip some of the llama-compat backends to save space
-## We only leave the most CPU-optimized variant and the fallback for the cublas/hipblas build
+## Otherwise just run the normal build
-## (both will use CUDA or hipblas for the actual computation)
+RUN if [ "${TARGETARCH}" = "arm64" ] || [ "${BUILD_TYPE}" = "hipblas" ]; then \
-RUN if [ "${BUILD_TYPE}" = "cublas" ] || [ "${BUILD_TYPE}" = "hipblas" ]; then \
+        SKIP_GRPC_BACKEND="backend-assets/grpc/llama-cpp-avx512 backend-assets/grpc/llama-cpp-avx backend-assets/grpc/llama-cpp-avx2" make build; \
-        SKIP_GRPC_BACKEND="backend-assets/grpc/llama-cpp-avx backend-assets/grpc/llama-cpp-avx2" make build; \
     else \
         make build; \
     fi
@@ -353,8 +326,6 @@ ARG FFMPEG
 
 COPY --from=grpc /opt/grpc /usr/local
 
-COPY --from=builder-sd /build/backend-assets/grpc/stablediffusion /build/backend-assets/grpc/stablediffusion
-
 COPY .devcontainer-scripts /.devcontainer-scripts
 
 # Add FFmpeg
@@ -427,36 +398,28 @@ COPY --from=builder /build/local-ai ./
 # Copy shared libraries for piper
 COPY --from=builder /build/sources/go-piper/piper-phonemize/pi/lib/* /usr/lib/
 
-# do not let stablediffusion rebuild (requires an older version of absl)
-COPY --from=builder-sd /build/backend-assets/grpc/stablediffusion ./backend-assets/grpc/stablediffusion
-
 # Change the shell to bash so we can use [[ tests below
 SHELL ["/bin/bash", "-c"]
 # We try to strike a balance between individual layer size (as that affects total push time) and total image size
 # Splitting the backends into more groups with fewer items results in a larger image, but a smaller size for the largest layer
 # Splitting the backends into fewer groups with more items results in a smaller image, but a larger size for the largest layer
 
+RUN if [[ ( "${IMAGE_TYPE}" == "extras ")]]; then \
+        apt-get -qq -y install espeak-ng \
+    ; fi
+
 RUN if [[ ( "${EXTRA_BACKENDS}" =~ "coqui" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
         make -C backend/python/coqui \
     ; fi && \
-    if [[ ( "${EXTRA_BACKENDS}" =~ "parler-tts" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
+    if [[ ( "${EXTRA_BACKENDS}" =~ "faster-whisper" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
-        make -C backend/python/parler-tts \
+        make -C backend/python/faster-whisper \
     ; fi && \
     if [[ ( "${EXTRA_BACKENDS}" =~ "diffusers" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
         make -C backend/python/diffusers \
-    ; fi && \
-    if [[ ( "${EXTRA_BACKENDS}" =~ "transformers-musicgen" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
-        make -C backend/python/transformers-musicgen \
     ; fi
 
-RUN if [[ ( "${EXTRA_BACKENDS}" =~ "vall-e-x" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
+RUN if [[ ( "${EXTRA_BACKENDS}" =~ "kokoro" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
-        make -C backend/python/vall-e-x \
+        make -C backend/python/kokoro \
-    ; fi && \
-    if [[ ( "${EXTRA_BACKENDS}" =~ "openvoice" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
-        make -C backend/python/openvoice \
-    ; fi && \
-    if [[ ( "${EXTRA_BACKENDS}" =~ "sentencetransformers" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
-        make -C backend/python/sentencetransformers \
     ; fi && \
     if [[ ( "${EXTRA_BACKENDS}" =~ "exllama2" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
         make -C backend/python/exllama2 \
@@ -468,17 +431,11 @@ RUN if [[ ( "${EXTRA_BACKENDS}" =~ "vall-e-x" || -z "${EXTRA_BACKENDS}" ) && "$I
 RUN if [[ ( "${EXTRA_BACKENDS}" =~ "vllm" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
         make -C backend/python/vllm \
     ; fi && \
-    if [[ ( "${EXTRA_BACKENDS}" =~ "autogptq" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
-        make -C backend/python/autogptq \
-    ; fi && \
     if [[ ( "${EXTRA_BACKENDS}" =~ "bark" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
         make -C backend/python/bark \
     ; fi && \
     if [[ ( "${EXTRA_BACKENDS}" =~ "rerankers" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
         make -C backend/python/rerankers \
-    ; fi && \
-    if [[ ( "${EXTRA_BACKENDS}" =~ "mamba" || -z "${EXTRA_BACKENDS}" ) && "$IMAGE_TYPE" == "extras" ]]; then \
-        make -C backend/python/mamba \
     ; fi
 
 # Make sure the models directory exists

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2023-2024 Ettore Di Giacinto (mudler@localai.io)
+Copyright (c) 2023-2025 Ettore Di Giacinto (mudler@localai.io)
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

Makefile

@@ -6,33 +6,26 @@ BINARY_NAME=local-ai
 DETECT_LIBS?=true
 
 # llama.cpp versions
-GOLLAMA_REPO?=https://github.com/go-skynet/go-llama.cpp
+CPPLLAMA_VERSION?=e5c834f718a32b7584f142799bbf508fddb9021c
-GOLLAMA_VERSION?=2b57a8ae43e4699d3dc5d1496a1ccd42922993be
-CPPLLAMA_VERSION?=504af20ee4eae72080a56d59d744f6774f7901ce
 
 # whisper.cpp version
-WHISPER_REPO?=https://github.com/ggerganov/whisper.cpp
+WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=6266a9f9e56a5b925e9892acf650f3eb1245814d
+WHISPER_CPP_VERSION?=e41bc5c61ae66af6be2bd7011769bb821a83e8ae
 
 # go-piper version
 PIPER_REPO?=https://github.com/mudler/go-piper
 PIPER_VERSION?=e10ca041a885d4a8f3871d52924b47792d5e5aa0
 
-# stablediffusion version
-STABLEDIFFUSION_REPO?=https://github.com/mudler/go-stable-diffusion
-STABLEDIFFUSION_VERSION?=4a3cd6aeae6f66ee57eae9a0075f8c58c3a6a38f
-
-# tinydream version
-TINYDREAM_REPO?=https://github.com/M0Rf30/go-tiny-dream
-TINYDREAM_VERSION?=c04fa463ace9d9a6464313aa5f9cd0f953b6c057
-
 # bark.cpp
 BARKCPP_REPO?=https://github.com/PABannier/bark.cpp.git
 BARKCPP_VERSION?=v1.0.0
 
 # stablediffusion.cpp (ggml)
-STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
+STABLEDIFFUSION_GGML_REPO?=https://github.com/richiejp/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=dcf91f9e0f2cbf9da472ee2a556751ed4bab2d2a
+STABLEDIFFUSION_GGML_VERSION?=53e3b17eb3d0b5760ced06a1f98320b68b34aaae
+
+# ONEAPI variables for SYCL
+export ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
 
 ONNX_VERSION?=1.20.0
 ONNX_ARCH?=x64
@@ -40,8 +33,12 @@ ONNX_OS?=linux
 
 export BUILD_TYPE?=
 export STABLE_BUILD_TYPE?=$(BUILD_TYPE)
-export CMAKE_ARGS?=
+export CMAKE_ARGS?=-DBUILD_SHARED_LIBS=OFF
+export WHISPER_CMAKE_ARGS?=-DBUILD_SHARED_LIBS=OFF
 export BACKEND_LIBS?=
+export WHISPER_DIR=$(abspath ./sources/whisper.cpp)
+export WHISPER_INCLUDE_PATH=$(WHISPER_DIR)/include:$(WHISPER_DIR)/ggml/include
+export WHISPER_LIBRARY_PATH=$(WHISPER_DIR)/build/src/:$(WHISPER_DIR)/build/ggml/src
 
 CGO_LDFLAGS?=
 CGO_LDFLAGS_WHISPER?=
@@ -91,6 +88,7 @@ endif
 # IF native is false, we add -DGGML_NATIVE=OFF to CMAKE_ARGS
 ifeq ($(NATIVE),false)
 	CMAKE_ARGS+=-DGGML_NATIVE=OFF
+	WHISPER_CMAKE_ARGS+=-DGGML_NATIVE=OFF
 endif
 
 # Detect if we are running on arm64
@@ -118,13 +116,31 @@ ifeq ($(OS),Darwin)
 	# disable metal if on Darwin and any other value is explicitly passed.
 	else ifneq ($(BUILD_TYPE),metal)
 		CMAKE_ARGS+=-DGGML_METAL=OFF
+		WHISPER_CMAKE_ARGS+=-DGGML_METAL=OFF
 		export GGML_NO_ACCELERATE=1
 		export GGML_NO_METAL=1
+		GO_LDFLAGS_WHISPER+=-lggml-blas
+		export WHISPER_LIBRARY_PATH:=$(WHISPER_LIBRARY_PATH):$(WHISPER_DIR)/build/ggml/src/ggml-blas
 	endif
 
 	ifeq ($(BUILD_TYPE),metal)
-#			-lcblas 	removed: it seems to always be listed as a duplicate flag.
 		CGO_LDFLAGS += -framework Accelerate
+		CGO_LDFLAGS_WHISPER+=-lggml-metal -lggml-blas
+		CMAKE_ARGS+=-DGGML_METAL=ON
+		CMAKE_ARGS+=-DGGML_METAL_USE_BF16=ON
+		CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
+		CMAKE_ARGS+=-DGGML_OPENMP=OFF
+		WHISPER_CMAKE_ARGS+=-DGGML_METAL=ON
+		WHISPER_CMAKE_ARGS+=-DGGML_METAL_USE_BF16=ON
+		WHISPER_CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
+		WHISPER_CMAKE_ARGS+=-DWHISPER_BUILD_EXAMPLES=OFF
+		WHISPER_CMAKE_ARGS+=-DWHISPER_BUILD_TESTS=OFF
+		WHISPER_CMAKE_ARGS+=-DWHISPER_BUILD_SERVER=OFF
+		WHISPER_CMAKE_ARGS+=-DGGML_OPENMP=OFF
+		export WHISPER_LIBRARY_PATH:=$(WHISPER_LIBRARY_PATH):$(WHISPER_DIR)/build/ggml/src/ggml-metal/:$(WHISPER_DIR)/build/ggml/src/ggml-blas
+	else
+		CGO_LDFLAGS_WHISPER+=-lggml-blas
+		export WHISPER_LIBRARY_PATH:=$(WHISPER_LIBRARY_PATH):$(WHISPER_DIR)/build/ggml/src/ggml-blas
 	endif
 else
 CGO_LDFLAGS_WHISPER+=-lgomp
@@ -136,21 +152,29 @@ ifeq ($(BUILD_TYPE),openblas)
 endif
 
 ifeq ($(BUILD_TYPE),cublas)
-	CGO_LDFLAGS+=-lcublas -lcudart -L$(CUDA_LIBPATH)
+	CGO_LDFLAGS+=-lcublas -lcudart -L$(CUDA_LIBPATH) -L$(CUDA_LIBPATH)/stubs/ -lcuda
 	export GGML_CUDA=1
-	CGO_LDFLAGS_WHISPER+=-L$(CUDA_LIBPATH)/stubs/ -lcuda -lcufft
+	CMAKE_ARGS+=-DGGML_CUDA=ON
+	WHISPER_CMAKE_ARGS+=-DGGML_CUDA=ON
+	CGO_LDFLAGS_WHISPER+=-lcufft -lggml-cuda
+	export WHISPER_LIBRARY_PATH:=$(WHISPER_LIBRARY_PATH):$(WHISPER_DIR)/build/ggml/src/ggml-cuda/
 endif
 
 ifeq ($(BUILD_TYPE),vulkan)
 	CMAKE_ARGS+=-DGGML_VULKAN=1
+	WHISPER_CMAKE_ARGS+=-DGGML_VULKAN=1
+	CGO_LDFLAGS_WHISPER+=-lggml-vulkan -lvulkan
+	export WHISPER_LIBRARY_PATH:=$(WHISPER_LIBRARY_PATH):$(WHISPER_DIR)/build/ggml/src/ggml-vulkan/
 endif
 
 ifneq (,$(findstring sycl,$(BUILD_TYPE)))
 	export GGML_SYCL=1
+	CMAKE_ARGS+=-DGGML_SYCL=ON
 endif
 
 ifeq ($(BUILD_TYPE),sycl_f16)
 	export GGML_SYCL_F16=1
+	CMAKE_ARGS+=-DGGML_SYCL_F16=ON
 endif
 
 ifeq ($(BUILD_TYPE),hipblas)
@@ -159,10 +183,9 @@ ifeq ($(BUILD_TYPE),hipblas)
 	LD_LIBRARY_PATH ?= /opt/rocm/lib:/opt/rocm/llvm/lib
 	export CXX=$(ROCM_HOME)/llvm/bin/clang++
 	export CC=$(ROCM_HOME)/llvm/bin/clang
-	# llama-ggml has no hipblas support, so override it here.
 	export STABLE_BUILD_TYPE=
 	export GGML_HIP=1
-	GPU_TARGETS ?= gfx900,gfx906,gfx908,gfx940,gfx941,gfx942,gfx90a,gfx1030,gfx1031,gfx1100,gfx1101
+	GPU_TARGETS ?= gfx803,gfx900,gfx906,gfx908,gfx90a,gfx942,gfx1010,gfx1030,gfx1032,gfx1100,gfx1101,gfx1102
 	AMDGPU_TARGETS ?= "$(GPU_TARGETS)"
 	CMAKE_ARGS+=-DGGML_HIP=ON -DAMDGPU_TARGETS="$(AMDGPU_TARGETS)" -DGPU_TARGETS="$(GPU_TARGETS)"
 	CGO_LDFLAGS += -O3 --rtlib=compiler-rt -unwindlib=libgcc -lhipblas -lrocblas --hip-link -L${ROCM_HOME}/lib/llvm/lib
@@ -183,16 +206,6 @@ ifeq ($(STATIC),true)
 	LD_FLAGS+=-linkmode external -extldflags -static
 endif
 
-ifeq ($(findstring stablediffusion,$(GO_TAGS)),stablediffusion)
-#	OPTIONAL_TARGETS+=go-stable-diffusion/libstablediffusion.a
-	OPTIONAL_GRPC+=backend-assets/grpc/stablediffusion
-endif
-
-ifeq ($(findstring tinydream,$(GO_TAGS)),tinydream)
-#	OPTIONAL_TARGETS+=go-tiny-dream/libtinydream.a
-	OPTIONAL_GRPC+=backend-assets/grpc/tinydream
-endif
-
 ifeq ($(findstring tts,$(GO_TAGS)),tts)
 #	OPTIONAL_TARGETS+=go-piper/libpiper_binding.a
 #	OPTIONAL_TARGETS+=backend-assets/espeak-ng-data
@@ -204,8 +217,8 @@ endif
 ALL_GRPC_BACKENDS=backend-assets/grpc/huggingface
 ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-avx
 ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-avx2
+ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-avx512
 ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-fallback
-ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-ggml
 ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-grpc
 ALL_GRPC_BACKENDS+=backend-assets/util/llama-cpp-rpc-server
 ALL_GRPC_BACKENDS+=backend-assets/grpc/whisper
@@ -239,19 +252,6 @@ endif
 
 all: help
 
-## go-llama.cpp
-sources/go-llama.cpp:
-	mkdir -p sources/go-llama.cpp
-	cd sources/go-llama.cpp && \
-	git init && \
-	git remote add origin $(GOLLAMA_REPO) && \
-	git fetch origin && \
-	git checkout $(GOLLAMA_VERSION) && \
-	git submodule update --init --recursive --depth 1 --single-branch
-
-sources/go-llama.cpp/libbinding.a: sources/go-llama.cpp
-	$(MAKE) -C sources/go-llama.cpp BUILD_TYPE=$(STABLE_BUILD_TYPE) libbinding.a
-
 ## bark.cpp
 sources/bark.cpp:
 	git clone --recursive $(BARKCPP_REPO) sources/bark.cpp && \
@@ -282,19 +282,6 @@ sources/go-piper:
 sources/go-piper/libpiper_binding.a: sources/go-piper
 	$(MAKE) -C sources/go-piper libpiper_binding.a example/main piper.o
 
-## stable diffusion (onnx)
-sources/go-stable-diffusion:
-	mkdir -p sources/go-stable-diffusion
-	cd sources/go-stable-diffusion && \
-	git init && \
-	git remote add origin $(STABLEDIFFUSION_REPO) && \
-	git fetch origin && \
-	git checkout $(STABLEDIFFUSION_VERSION) && \
-	git submodule update --init --recursive --depth 1 --single-branch
-
-sources/go-stable-diffusion/libstablediffusion.a: sources/go-stable-diffusion
-	CPATH="$(CPATH):/usr/include/opencv4" $(MAKE) -C sources/go-stable-diffusion libstablediffusion.a
-
 ## stablediffusion (ggml)
 sources/stablediffusion-ggml.cpp:
 	git clone --recursive $(STABLEDIFFUSION_GGML_REPO) sources/stablediffusion-ggml.cpp && \
@@ -307,11 +294,7 @@ backend/go/image/stablediffusion-ggml/libsd.a: sources/stablediffusion-ggml.cpp
 	$(MAKE) -C backend/go/image/stablediffusion-ggml libsd.a
 
 backend-assets/grpc/stablediffusion-ggml: backend/go/image/stablediffusion-ggml/libsd.a backend-assets/grpc
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(CURDIR)/backend/go/image/stablediffusion-ggml/ LIBRARY_PATH=$(CURDIR)/backend/go/image/stablediffusion-ggml/ \
+	$(MAKE) -C backend/go/image/stablediffusion-ggml CGO_LDFLAGS="$(CGO_LDFLAGS)" stablediffusion-ggml
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/stablediffusion-ggml ./backend/go/image/stablediffusion-ggml/
-ifneq ($(UPX),)
-	$(UPX) backend-assets/grpc/stablediffusion-ggml
-endif
 
 sources/onnxruntime:
 	mkdir -p sources/onnxruntime
@@ -327,19 +310,6 @@ else
 	mv backend-assets/lib/libonnxruntime.so.$(ONNX_VERSION) backend-assets/lib/libonnxruntime.so.1
 endif
 
-## tiny-dream
-sources/go-tiny-dream:
-	mkdir -p sources/go-tiny-dream
-	cd sources/go-tiny-dream && \
-	git init && \
-	git remote add origin $(TINYDREAM_REPO) && \
-	git fetch origin && \
-	git checkout $(TINYDREAM_VERSION) && \
-	git submodule update --init --recursive --depth 1 --single-branch
-
-sources/go-tiny-dream/libtinydream.a: sources/go-tiny-dream
-	$(MAKE) -C sources/go-tiny-dream libtinydream.a
-
 ## whisper
 sources/whisper.cpp:
 	mkdir -p sources/whisper.cpp
@@ -350,26 +320,21 @@ sources/whisper.cpp:
 	git checkout $(WHISPER_CPP_VERSION) && \
 	git submodule update --init --recursive --depth 1 --single-branch
 
-sources/whisper.cpp/libwhisper.a: sources/whisper.cpp
+sources/whisper.cpp/build/src/libwhisper.a: sources/whisper.cpp
-	cd sources/whisper.cpp && $(MAKE) libwhisper.a libggml.a
+	cd sources/whisper.cpp && cmake $(WHISPER_CMAKE_ARGS) . -B ./build
+	cd sources/whisper.cpp/build && cmake --build . --config Release
 
-get-sources: sources/go-llama.cpp sources/go-piper sources/stablediffusion-ggml.cpp sources/bark.cpp sources/whisper.cpp sources/go-stable-diffusion sources/go-tiny-dream backend/cpp/llama/llama.cpp
+get-sources: sources/go-piper sources/stablediffusion-ggml.cpp sources/bark.cpp sources/whisper.cpp backend/cpp/llama/llama.cpp
 
 replace:
 	$(GOCMD) mod edit -replace github.com/ggerganov/whisper.cpp=$(CURDIR)/sources/whisper.cpp
 	$(GOCMD) mod edit -replace github.com/ggerganov/whisper.cpp/bindings/go=$(CURDIR)/sources/whisper.cpp/bindings/go
-	$(GOCMD) mod edit -replace github.com/M0Rf30/go-tiny-dream=$(CURDIR)/sources/go-tiny-dream
 	$(GOCMD) mod edit -replace github.com/mudler/go-piper=$(CURDIR)/sources/go-piper
-	$(GOCMD) mod edit -replace github.com/mudler/go-stable-diffusion=$(CURDIR)/sources/go-stable-diffusion
-	$(GOCMD) mod edit -replace github.com/go-skynet/go-llama.cpp=$(CURDIR)/sources/go-llama.cpp
 
 dropreplace:
 	$(GOCMD) mod edit -dropreplace github.com/ggerganov/whisper.cpp
 	$(GOCMD) mod edit -dropreplace github.com/ggerganov/whisper.cpp/bindings/go
-	$(GOCMD) mod edit -dropreplace github.com/M0Rf30/go-tiny-dream
 	$(GOCMD) mod edit -dropreplace github.com/mudler/go-piper
-	$(GOCMD) mod edit -dropreplace github.com/mudler/go-stable-diffusion
-	$(GOCMD) mod edit -dropreplace github.com/go-skynet/go-llama.cpp
 
 prepare-sources: get-sources replace
 	$(GOCMD) mod download
@@ -377,11 +342,8 @@ prepare-sources: get-sources replace
 ## GENERIC
 rebuild: ## Rebuilds the project
 	$(GOCMD) clean -cache
-	$(MAKE) -C sources/go-llama.cpp clean
 	$(MAKE) -C sources/whisper.cpp clean
-	$(MAKE) -C sources/go-stable-diffusion clean
 	$(MAKE) -C sources/go-piper clean
-	$(MAKE) -C sources/go-tiny-dream clean
 	$(MAKE) build
 
 prepare: prepare-sources $(OPTIONAL_TARGETS)
@@ -410,8 +372,14 @@ clean-tests:
 clean-dc: clean
 	cp -r /build/backend-assets /workspace/backend-assets
 
+## Install Go tools
+install-go-tools:
+	go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+	go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
+	go install github.com/GeertJohan/go.rice/rice@latest
+
 ## Build:
-build: prepare backend-assets grpcs ## Build the project
+build: prepare backend-assets grpcs install-go-tools ## Build the project
 	$(info ${GREEN}I local-ai build info:${RESET})
 	$(info ${GREEN}I BUILD_TYPE: ${YELLOW}$(BUILD_TYPE)${RESET})
 	$(info ${GREEN}I GO_TAGS: ${YELLOW}$(GO_TAGS)${RESET})
@@ -421,7 +389,9 @@ ifneq ($(BACKEND_LIBS),)
 	$(MAKE) backend-assets/lib
 	cp -f $(BACKEND_LIBS) backend-assets/lib/
 endif
+	rm -rf $(BINARY_NAME) || true
 	CGO_LDFLAGS="$(CGO_LDFLAGS)" $(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o $(BINARY_NAME) ./
+	rice append --exec $(BINARY_NAME)
 
 build-minimal:
 	BUILD_GRPC_FOR_BACKEND_LLAMA=true GRPC_BACKENDS="backend-assets/grpc/llama-cpp-avx2" GO_TAGS=p2p $(MAKE) build
@@ -483,7 +453,7 @@ run: prepare ## run local-ai
 test-models/testmodel.ggml:
 	mkdir test-models
 	mkdir test-dir
-	wget -q https://huggingface.co/TheBloke/orca_mini_3B-GGML/resolve/main/orca-mini-3b.ggmlv3.q4_0.bin -O test-models/testmodel.ggml
+	wget -q https://huggingface.co/RichardErkhov/Qwen_-_Qwen2-1.5B-Instruct-gguf/resolve/main/Qwen2-1.5B-Instruct.Q2_K.gguf -O test-models/testmodel.ggml
 	wget -q https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin -O test-models/whisper-en
 	wget -q https://huggingface.co/mudler/all-MiniLM-L6-v2/resolve/main/ggml-model-q4_0.bin -O test-models/bert
 	wget -q https://cdn.openai.com/whisper/draft-20220913a/micro-machines.wav -O test-dir/audio.wav
@@ -493,13 +463,13 @@ prepare-test: grpcs
 	cp -rf backend-assets core/http
 	cp tests/models_fixtures/* test-models
 
+## Test targets
 test: prepare test-models/testmodel.ggml grpcs
 	@echo 'Running tests'
-	export GO_TAGS="tts stablediffusion debug"
+	export GO_TAGS="tts debug"
 	$(MAKE) prepare-test
-	HUGGINGFACE_GRPC=$(abspath ./)/backend/python/sentencetransformers/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
+	HUGGINGFACE_GRPC=$(abspath ./)/backend/python/transformers/run.sh TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!llama && !llama-gguf"  --flake-attempts $(TEST_FLAKES) --fail-fast -v -r $(TEST_PATHS)
+	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="!llama-gguf"  --flake-attempts $(TEST_FLAKES) --fail-fast -v -r $(TEST_PATHS)
-	$(MAKE) test-llama
 	$(MAKE) test-llama-gguf
 	$(MAKE) test-tts
 	$(MAKE) test-stablediffusion
@@ -528,10 +498,6 @@ teardown-e2e:
 	rm -rf $(TEST_DIR) || true
 	docker stop $$(docker ps -q --filter ancestor=localai-tests)
 
-test-llama: prepare-test
-	TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
-	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="llama" --flake-attempts $(TEST_FLAKES) -v -r $(TEST_PATHS)
-
 test-llama-gguf: prepare-test
 	TEST_DIR=$(abspath ./)/test-dir/ FIXTURES=$(abspath ./)/tests/fixtures CONFIG_FILE=$(abspath ./)/test-models/config.yaml MODELS_PATH=$(abspath ./)/test-models \
 	$(GOCMD) run github.com/onsi/ginkgo/v2/ginkgo --label-filter="llama-gguf" --flake-attempts $(TEST_FLAKES) -v -r $(TEST_PATHS)
@@ -572,7 +538,7 @@ protogen: protogen-go protogen-python
 protogen-clean: protogen-go-clean protogen-python-clean
 
 .PHONY: protogen-go
-protogen-go:
+protogen-go: install-go-tools
 	mkdir -p pkg/grpc/proto
 	protoc --experimental_allow_proto3_optional -Ibackend/ --go_out=pkg/grpc/proto/ --go_opt=paths=source_relative --go-grpc_out=pkg/grpc/proto/ --go-grpc_opt=paths=source_relative \
     backend/backend.proto
@@ -583,18 +549,10 @@ protogen-go-clean:
 	$(RM) bin/*
 
 .PHONY: protogen-python
-protogen-python: autogptq-protogen bark-protogen coqui-protogen diffusers-protogen exllama2-protogen mamba-protogen rerankers-protogen sentencetransformers-protogen transformers-protogen parler-tts-protogen transformers-musicgen-protogen vall-e-x-protogen vllm-protogen openvoice-protogen
+protogen-python: bark-protogen coqui-protogen diffusers-protogen exllama2-protogen rerankers-protogen transformers-protogen kokoro-protogen vllm-protogen faster-whisper-protogen
 
 .PHONY: protogen-python-clean
-protogen-python-clean: autogptq-protogen-clean bark-protogen-clean coqui-protogen-clean diffusers-protogen-clean  exllama2-protogen-clean mamba-protogen-clean sentencetransformers-protogen-clean rerankers-protogen-clean transformers-protogen-clean transformers-musicgen-protogen-clean parler-tts-protogen-clean vall-e-x-protogen-clean vllm-protogen-clean openvoice-protogen-clean
+protogen-python-clean: bark-protogen-clean coqui-protogen-clean diffusers-protogen-clean  exllama2-protogen-clean rerankers-protogen-clean transformers-protogen-clean kokoro-protogen-clean vllm-protogen-clean faster-whisper-protogen-clean
-
-.PHONY: autogptq-protogen
-autogptq-protogen:
-	$(MAKE) -C backend/python/autogptq protogen
-
-.PHONY: autogptq-protogen-clean
-autogptq-protogen-clean:
-	$(MAKE) -C backend/python/autogptq protogen-clean
 
 .PHONY: bark-protogen
 bark-protogen:
@@ -620,6 +578,14 @@ diffusers-protogen:
 diffusers-protogen-clean:
 	$(MAKE) -C backend/python/diffusers protogen-clean
 
+.PHONY: faster-whisper-protogen
+faster-whisper-protogen:
+	$(MAKE) -C backend/python/faster-whisper protogen
+
+.PHONY: faster-whisper-protogen-clean
+faster-whisper-protogen-clean:
+	$(MAKE) -C backend/python/faster-whisper protogen-clean
+
 .PHONY: exllama2-protogen
 exllama2-protogen:
 	$(MAKE) -C backend/python/exllama2 protogen
@@ -628,14 +594,6 @@ exllama2-protogen:
 exllama2-protogen-clean:
 	$(MAKE) -C backend/python/exllama2 protogen-clean
 
-.PHONY: mamba-protogen
-mamba-protogen:
-	$(MAKE) -C backend/python/mamba protogen
-
-.PHONY: mamba-protogen-clean
-mamba-protogen-clean:
-	$(MAKE) -C backend/python/mamba protogen-clean
-
 .PHONY: rerankers-protogen
 rerankers-protogen:
 	$(MAKE) -C backend/python/rerankers protogen
@@ -644,14 +602,6 @@ rerankers-protogen:
 rerankers-protogen-clean:
 	$(MAKE) -C backend/python/rerankers protogen-clean
 
-.PHONY: sentencetransformers-protogen
-sentencetransformers-protogen:
-	$(MAKE) -C backend/python/sentencetransformers protogen
-
-.PHONY: sentencetransformers-protogen-clean
-sentencetransformers-protogen-clean:
-	$(MAKE) -C backend/python/sentencetransformers protogen-clean
-
 .PHONY: transformers-protogen
 transformers-protogen:
 	$(MAKE) -C backend/python/transformers protogen
@@ -660,37 +610,13 @@ transformers-protogen:
 transformers-protogen-clean:
 	$(MAKE) -C backend/python/transformers protogen-clean
 
-.PHONY: parler-tts-protogen
+.PHONY: kokoro-protogen
-parler-tts-protogen:
+kokoro-protogen:
-	$(MAKE) -C backend/python/parler-tts protogen
+	$(MAKE) -C backend/python/kokoro protogen
 
-.PHONY: parler-tts-protogen-clean
+.PHONY: kokoro-protogen-clean
-parler-tts-protogen-clean:
+kokoro-protogen-clean:
-	$(MAKE) -C backend/python/parler-tts protogen-clean
+	$(MAKE) -C backend/python/kokoro protogen-clean
-
-.PHONY: transformers-musicgen-protogen
-transformers-musicgen-protogen:
-	$(MAKE) -C backend/python/transformers-musicgen protogen
-
-.PHONY: transformers-musicgen-protogen-clean
-transformers-musicgen-protogen-clean:
-	$(MAKE) -C backend/python/transformers-musicgen protogen-clean
-
-.PHONY: vall-e-x-protogen
-vall-e-x-protogen:
-	$(MAKE) -C backend/python/vall-e-x protogen
-
-.PHONY: vall-e-x-protogen-clean
-vall-e-x-protogen-clean:
-	$(MAKE) -C backend/python/vall-e-x protogen-clean
-
-.PHONY: openvoice-protogen
-openvoice-protogen:
-	$(MAKE) -C backend/python/openvoice protogen
-
-.PHONY: openvoice-protogen-clean
-openvoice-protogen-clean:
-	$(MAKE) -C backend/python/openvoice protogen-clean
 
 .PHONY: vllm-protogen
 vllm-protogen:
@@ -703,28 +629,25 @@ vllm-protogen-clean:
 ## GRPC
 # Note: it is duplicated in the Dockerfile
 prepare-extra-conda-environments: protogen-python
-	$(MAKE) -C backend/python/autogptq
 	$(MAKE) -C backend/python/bark
 	$(MAKE) -C backend/python/coqui
 	$(MAKE) -C backend/python/diffusers
+	$(MAKE) -C backend/python/faster-whisper
 	$(MAKE) -C backend/python/vllm
-	$(MAKE) -C backend/python/mamba
-	$(MAKE) -C backend/python/sentencetransformers
 	$(MAKE) -C backend/python/rerankers
 	$(MAKE) -C backend/python/transformers
-	$(MAKE) -C backend/python/transformers-musicgen
+	$(MAKE) -C backend/python/kokoro
-	$(MAKE) -C backend/python/parler-tts
-	$(MAKE) -C backend/python/vall-e-x
-	$(MAKE) -C backend/python/openvoice
 	$(MAKE) -C backend/python/exllama2
 
 prepare-test-extra: protogen-python
 	$(MAKE) -C backend/python/transformers
 	$(MAKE) -C backend/python/diffusers
+	$(MAKE) -C backend/python/vllm
 
 test-extra: prepare-test-extra
 	$(MAKE) -C backend/python/transformers test
 	$(MAKE) -C backend/python/diffusers test
+	$(MAKE) -C backend/python/vllm test
 
 backend-assets:
 	mkdir -p backend-assets
@@ -785,6 +708,13 @@ backend-assets/grpc/llama-cpp-avx2: backend-assets/grpc backend/cpp/llama/llama.
 	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
 	cp -rfv backend/cpp/llama-avx2/grpc-server backend-assets/grpc/llama-cpp-avx2
 
+backend-assets/grpc/llama-cpp-avx512: backend-assets/grpc backend/cpp/llama/llama.cpp
+	cp -rf backend/cpp/llama backend/cpp/llama-avx512
+	$(MAKE) -C backend/cpp/llama-avx512 purge
+	$(info ${GREEN}I llama-cpp build info:avx512${RESET})
+	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-avx512" build-llama-cpp-grpc-server
+	cp -rfv backend/cpp/llama-avx512/grpc-server backend-assets/grpc/llama-cpp-avx512
+
 backend-assets/grpc/llama-cpp-avx: backend-assets/grpc backend/cpp/llama/llama.cpp
 	cp -rf backend/cpp/llama backend/cpp/llama-avx
 	$(MAKE) -C backend/cpp/llama-avx purge
@@ -838,13 +768,6 @@ backend-assets/util/llama-cpp-rpc-server: backend-assets/grpc/llama-cpp-grpc
 	mkdir -p backend-assets/util/
 	cp -rf backend/cpp/llama-grpc/llama.cpp/build/bin/rpc-server backend-assets/util/llama-cpp-rpc-server
 
-backend-assets/grpc/llama-ggml: sources/go-llama.cpp sources/go-llama.cpp/libbinding.a backend-assets/grpc
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(CURDIR)/sources/go-llama.cpp LIBRARY_PATH=$(CURDIR)/sources/go-llama.cpp \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/llama-ggml ./backend/go/llm/llama-ggml/
-ifneq ($(UPX),)
-	$(UPX) backend-assets/grpc/llama-ggml
-endif
-
 backend-assets/grpc/bark-cpp: backend/go/bark/libbark.a backend-assets/grpc
 	CGO_LDFLAGS="$(CGO_LDFLAGS)" C_INCLUDE_PATH=$(CURDIR)/backend/go/bark/ LIBRARY_PATH=$(CURDIR)/backend/go/bark/ \
 	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/bark-cpp ./backend/go/bark/
@@ -859,13 +782,6 @@ ifneq ($(UPX),)
 	$(UPX) backend-assets/grpc/piper
 endif
 
-backend-assets/grpc/stablediffusion: sources/go-stable-diffusion sources/go-stable-diffusion/libstablediffusion.a backend-assets/grpc
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" CPATH="$(CPATH):$(CURDIR)/sources/go-stable-diffusion/:/usr/include/opencv4" LIBRARY_PATH=$(CURDIR)/sources/go-stable-diffusion/ \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/stablediffusion ./backend/go/image/stablediffusion
-ifneq ($(UPX),)
-	$(UPX) backend-assets/grpc/stablediffusion
-endif
-
 backend-assets/grpc/silero-vad: backend-assets/grpc backend-assets/lib/libonnxruntime.so.1
 	CGO_LDFLAGS="$(CGO_LDFLAGS)" CPATH="$(CPATH):$(CURDIR)/sources/onnxruntime/include/" LIBRARY_PATH=$(CURDIR)/backend-assets/lib \
 	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/silero-vad ./backend/go/vad/silero
@@ -873,15 +789,8 @@ ifneq ($(UPX),)
 	$(UPX) backend-assets/grpc/silero-vad
 endif
 
-backend-assets/grpc/tinydream: sources/go-tiny-dream sources/go-tiny-dream/libtinydream.a backend-assets/grpc
+backend-assets/grpc/whisper: sources/whisper.cpp sources/whisper.cpp/build/src/libwhisper.a backend-assets/grpc
-	CGO_LDFLAGS="$(CGO_LDFLAGS)" LIBRARY_PATH=$(CURDIR)/go-tiny-dream \
+	CGO_LDFLAGS="$(CGO_LDFLAGS) $(CGO_LDFLAGS_WHISPER)" C_INCLUDE_PATH="${WHISPER_INCLUDE_PATH}" LIBRARY_PATH="${WHISPER_LIBRARY_PATH}" LD_LIBRARY_PATH="${WHISPER_LIBRARY_PATH}" \
-	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/tinydream ./backend/go/image/tinydream
-ifneq ($(UPX),)
-	$(UPX) backend-assets/grpc/tinydream
-endif
-
-backend-assets/grpc/whisper: sources/whisper.cpp sources/whisper.cpp/libwhisper.a backend-assets/grpc
-	CGO_LDFLAGS="$(CGO_LDFLAGS) $(CGO_LDFLAGS_WHISPER)" C_INCLUDE_PATH="$(CURDIR)/sources/whisper.cpp/include:$(CURDIR)/sources/whisper.cpp/ggml/include" LIBRARY_PATH=$(CURDIR)/sources/whisper.cpp \
 	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o backend-assets/grpc/whisper ./backend/go/transcribe/whisper
 ifneq ($(UPX),)
 	$(UPX) backend-assets/grpc/whisper
@@ -933,7 +842,8 @@ docker-aio-all:
 
 docker-image-intel:
 	docker build \
-		--build-arg BASE_IMAGE=intel/oneapi-basekit:2025.0.0-0-devel-ubuntu22.04 \
+		--progress plain \
+		--build-arg BASE_IMAGE=intel/oneapi-basekit:2025.1.0-0-devel-ubuntu24.04 \
 		--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
 		--build-arg GO_TAGS="none" \
 		--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
@@ -941,7 +851,7 @@ docker-image-intel:
 
 docker-image-intel-xpu:
 	docker build \
-		--build-arg BASE_IMAGE=intel/oneapi-basekit:2025.0.0-0-devel-ubuntu22.04 \
+		--build-arg BASE_IMAGE=intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04 \
 		--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
 		--build-arg GO_TAGS="none" \
 		--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
@@ -953,7 +863,7 @@ swagger:
 
 .PHONY: gen-assets
 gen-assets:
-	$(GOCMD) run core/dependencies_manager/manager.go embedded/webui_static.yaml core/http/static/assets
+	$(GOCMD) run core/dependencies_manager/manager.go webui_static.yaml core/http/static/assets
 
 ## Documentation
 docs/layouts/_default:

README.md

@@ -1,7 +1,6 @@
 <h1 align="center">
   <br>
-  <img height="300" src="https://github.com/go-skynet/LocalAI/assets/2420543/0966aa2a-166e-4f99-a3e5-6c915fc997dd"> <br>
+  <img height="300" src="./core/http/static/logo.png"> <br>
-    LocalAI
 <br>
 </h1>
 
@@ -31,7 +30,7 @@
 
 <p align="center">
 <a href="https://twitter.com/LocalAI_API" target="blank">
-<img src="https://img.shields.io/twitter/follow/LocalAI_API?label=Follow: LocalAI_API&style=social" alt="Follow LocalAI_API"/>
+<img src="https://img.shields.io/badge/X-%23000000.svg?style=for-the-badge&logo=X&logoColor=white&label=LocalAI_API" alt="Follow LocalAI_API"/>
 </a>
 <a href="https://discord.gg/uJAeKSAGDy" target="blank">
 <img src="https://dcbadge.vercel.app/api/server/uJAeKSAGDy?style=flat-square&theme=default-inverted" alt="Join LocalAI Discord Community"/>
@@ -39,37 +38,94 @@
 </p>
 
 <p align="center">
-<a href="https://trendshift.io/repositories/1484" target="_blank"><img src="https://trendshift.io/api/badge/repositories/1484" alt="go-skynet%2FLocalAI | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+<a href="https://trendshift.io/repositories/5539" target="_blank"><img src="https://trendshift.io/api/badge/repositories/5539" alt="mudler%2FLocalAI | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 </p>
 
 > :bulb: Get help - [❓FAQ](https://localai.io/faq/) [💭Discussions](https://github.com/go-skynet/LocalAI/discussions) [:speech_balloon: Discord](https://discord.gg/uJAeKSAGDy) [:book: Documentation website](https://localai.io/)
 >
-> [💻 Quickstart](https://localai.io/basics/getting_started/) [🖼️ Models](https://models.localai.io/) [🚀 Roadmap](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap) [🥽 Demo](https://demo.localai.io) [🌍 Explorer](https://explorer.localai.io) [🛫 Examples](https://github.com/mudler/LocalAI-examples) 
+> [💻 Quickstart](https://localai.io/basics/getting_started/) [🖼️ Models](https://models.localai.io/) [🚀 Roadmap](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap) [🥽 Demo](https://demo.localai.io) [🌍 Explorer](https://explorer.localai.io) [🛫 Examples](https://github.com/mudler/LocalAI-examples) Try on 
+[![Telegram](https://img.shields.io/badge/Telegram-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white)](https://t.me/localaiofficial_bot)
 
 [![tests](https://github.com/go-skynet/LocalAI/actions/workflows/test.yml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/test.yml)[![Build and Release](https://github.com/go-skynet/LocalAI/actions/workflows/release.yaml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/release.yaml)[![build container images](https://github.com/go-skynet/LocalAI/actions/workflows/image.yml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/image.yml)[![Bump dependencies](https://github.com/go-skynet/LocalAI/actions/workflows/bump_deps.yaml/badge.svg)](https://github.com/go-skynet/LocalAI/actions/workflows/bump_deps.yaml)[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/localai)](https://artifacthub.io/packages/search?repo=localai)
 
-**LocalAI** is the free, Open Source OpenAI alternative. LocalAI act as a drop-in replacement REST API that’s compatible with OpenAI (Elevenlabs, Anthropic... ) API specifications for local AI inferencing. It allows you to run LLMs, generate images, audio (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families. Does not require GPU. It is created and maintained by [Ettore Di Giacinto](https://github.com/mudler).
+**LocalAI** is the free, Open Source OpenAI alternative. LocalAI act as a drop-in replacement REST API that's compatible with OpenAI (Elevenlabs, Anthropic... ) API specifications for local AI inferencing. It allows you to run LLMs, generate images, audio (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families. Does not require GPU. It is created and maintained by [Ettore Di Giacinto](https://github.com/mudler).
 
-![screen](https://github.com/mudler/LocalAI/assets/2420543/20b5ccd2-8393-44f0-aaf6-87a23806381e)
+
+## 📚🆕 Local Stack Family
+
+🆕 LocalAI is now part of a comprehensive suite of AI tools designed to work together:
+
+<table>
+  <tr>
+    <td width="50%" valign="top">
+      <a href="https://github.com/mudler/LocalAGI">
+        <img src="https://raw.githubusercontent.com/mudler/LocalAGI/refs/heads/main/webui/react-ui/public/logo_2.png" width="300" alt="LocalAGI Logo">
+      </a>
+    </td>
+    <td width="50%" valign="top">
+      <h3><a href="https://github.com/mudler/LocalAGI">LocalAGI</a></h3>
+      <p>A powerful Local AI agent management platform that serves as a drop-in replacement for OpenAI's Responses API, enhanced with advanced agentic capabilities.</p>
+    </td>
+  </tr>
+  <tr>
+    <td width="50%" valign="top">
+      <a href="https://github.com/mudler/LocalRecall">
+        <img src="https://raw.githubusercontent.com/mudler/LocalRecall/refs/heads/main/static/localrecall_horizontal.png" width="300" alt="LocalRecall Logo">
+      </a>
+    </td>
+    <td width="50%" valign="top">
+      <h3><a href="https://github.com/mudler/LocalRecall">LocalRecall</a></h3>
+      <p>A REST-ful API and knowledge base management system that provides persistent memory and storage capabilities for AI agents.</p>
+    </td>
+  </tr>
+</table>
+
+## Screenshots
+
+
+| Talk Interface | Generate Audio |
+| --- | --- |
+| ![Screenshot 2025-03-31 at 12-01-36 LocalAI - Talk](./docs/assets/images/screenshots/screenshot_tts.png) | ![Screenshot 2025-03-31 at 12-01-29 LocalAI - Generate audio with voice-en-us-ryan-low](./docs/assets/images/screenshots/screenshot_tts.png) |
+
+| Models Overview | Generate Images |
+| --- | --- |
+| ![Screenshot 2025-03-31 at 12-01-20 LocalAI - Models](./docs/assets/images/screenshots/screenshot_gallery.png) | ![Screenshot 2025-03-31 at 12-31-41 LocalAI - Generate images with flux 1-dev](./docs/assets/images/screenshots/screenshot_image.png) |
+
+| Chat Interface | Home |
+| --- | --- |
+| ![Screenshot 2025-03-31 at 11-57-44 LocalAI - Chat with localai-functioncall-qwen2 5-7b-v0 5](./docs/assets/images/screenshots/screenshot_chat.png) | ![Screenshot 2025-03-31 at 11-57-23 LocalAI API - c2a39e3 (c2a39e3639227cfd94ffffe9f5691239acc275a8)](./docs/assets/images/screenshots/screenshot_home.png) |
+
+| Login | Swarm |
+| --- | --- |
+|![Screenshot 2025-03-31 at 12-09-59 ](./docs/assets/images/screenshots/screenshot_login.png) | ![Screenshot 2025-03-31 at 12-10-39 LocalAI - P2P dashboard](./docs/assets/images/screenshots/screenshot_p2p.png) |
+
+## 💻 Quickstart
 
 Run the installer script:
 
 ```bash
+# Basic installation
 curl https://localai.io/install.sh | sh
 ```
 
+For more installation options, see [Installer Options](https://localai.io/docs/advanced/installer/).
+
 Or run with docker:
+
+### CPU only image:
 ```bash
-# CPU only image:
 docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-cpu
-
+```
-# Nvidia GPU:
+### Nvidia GPU:
+```bash
 docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-gpu-nvidia-cuda-12
-
+```
-# CPU and GPU image (bigger size):
+### CPU and GPU image (bigger size):
+```bash
 docker run -ti --name local-ai -p 8080:8080 localai/localai:latest
-
+```
-# AIO images (it will pre-download a set of models ready for use, see https://localai.io/basics/container/)
+### AIO images (it will pre-download a set of models ready for use, see https://localai.io/basics/container/)
+```bash
 docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-cpu
 ```
 
@@ -88,42 +144,26 @@ local-ai run https://gist.githubusercontent.com/.../phi-2.yaml
 local-ai run oci://localai/phi-2:latest
 ```
 
-[💻 Getting started](https://localai.io/basics/getting_started/index.html)
+For more information, see [💻 Getting started](https://localai.io/basics/getting_started/index.html)
 
 ## 📰 Latest project news
 
+- Apr 2025: [LocalAGI](https://github.com/mudler/LocalAGI) and [LocalRecall](https://github.com/mudler/LocalRecall) join the LocalAI family stack.
+- Apr 2025: WebUI overhaul, AIO images updates
+- Feb 2025: Backend cleanup, Breaking changes, new backends (kokoro, OutelTTS, faster-whisper), Nvidia L4T images
+- Jan 2025: LocalAI model release: https://huggingface.co/mudler/LocalAI-functioncall-phi-4-v0.3, SANA support in diffusers: https://github.com/mudler/LocalAI/pull/4603
 - Dec 2024: stablediffusion.cpp backend (ggml) added ( https://github.com/mudler/LocalAI/pull/4289 )
 - Nov 2024: Bark.cpp backend added ( https://github.com/mudler/LocalAI/pull/4287 )
 - Nov 2024: Voice activity detection models (**VAD**) added to the API: https://github.com/mudler/LocalAI/pull/4204
 - Oct 2024: examples moved to [LocalAI-examples](https://github.com/mudler/LocalAI-examples)
 - Aug 2024:  🆕 FLUX-1, [P2P Explorer](https://explorer.localai.io)
-- July 2024: 🔥🔥 🆕 P2P Dashboard, LocalAI Federated mode and AI Swarms: https://github.com/mudler/LocalAI/pull/2723
+- July 2024: 🔥🔥 🆕 P2P Dashboard, LocalAI Federated mode and AI Swarms: https://github.com/mudler/LocalAI/pull/2723. P2P Global community pools: https://github.com/mudler/LocalAI/issues/3113
-- June 2024: 🆕 You can browse now the model gallery without LocalAI! Check out https://models.localai.io
-- June 2024: Support for models from OCI registries: https://github.com/mudler/LocalAI/pull/2628
 - May 2024: 🔥🔥 Decentralized P2P llama.cpp:  https://github.com/mudler/LocalAI/pull/2343 (peer2peer llama.cpp!) 👉 Docs  https://localai.io/features/distribute/
-- May 2024: 🔥🔥 Openvoice: https://github.com/mudler/LocalAI/pull/2334
-- May 2024: 🆕 Function calls without grammars and mixed mode: https://github.com/mudler/LocalAI/pull/2328
 - May 2024: 🔥🔥 Distributed inferencing: https://github.com/mudler/LocalAI/pull/2324
-- May 2024: Chat, TTS, and Image generation in the WebUI: https://github.com/mudler/LocalAI/pull/2222
 - April 2024: Reranker API: https://github.com/mudler/LocalAI/pull/2121
 
 Roadmap items: [List of issues](https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3Aroadmap)
 
-## 🔥🔥 Hot topics (looking for help):
-
-- Multimodal with vLLM and Video understanding: https://github.com/mudler/LocalAI/pull/3729
-- Realtime API https://github.com/mudler/LocalAI/issues/3714
-- 🔥🔥 Distributed, P2P Global community pools: https://github.com/mudler/LocalAI/issues/3113
-- WebUI improvements: https://github.com/mudler/LocalAI/issues/2156
-- Backends v2: https://github.com/mudler/LocalAI/issues/1126
-- Improving UX v2: https://github.com/mudler/LocalAI/issues/1373
-- Assistant API: https://github.com/mudler/LocalAI/issues/1273
-- Moderation endpoint: https://github.com/mudler/LocalAI/issues/999
-- Vulkan: https://github.com/mudler/LocalAI/issues/1647
-- Anthropic API: https://github.com/mudler/LocalAI/issues/1808
-
-If you want to help and contribute, issues up for grabs: https://github.com/mudler/LocalAI/issues?q=is%3Aissue+is%3Aopen+label%3A%22up+for+grabs%22
-
 ## 🚀 [Features](https://localai.io/features/)
 
 - 📖 [Text generation with GPTs](https://localai.io/features/text-generation/) (`llama.cpp`, `transformers`, `vllm` ... [:book: and more](https://localai.io/model-compatibility/index.html#model-compatibility-table))
@@ -137,12 +177,10 @@ If you want to help and contribute, issues up for grabs: https://github.com/mudl
 - 🥽 [Vision API](https://localai.io/features/gpt-vision/)
 - 📈 [Reranker API](https://localai.io/features/reranker/)
 - 🆕🖧 [P2P Inferencing](https://localai.io/features/distribute/)
+- [Agentic capabilities](https://github.com/mudler/LocalAGI)
 - 🔊 Voice activity detection (Silero-VAD support)
 - 🌍 Integrated WebUI!
 
-## 💻 Usage
-
-Check out the [Getting started](https://localai.io/basics/getting_started/index.html) section in our documentation.
 
 ### 🔗 Community and integrations
 
@@ -218,7 +256,7 @@ A huge thank you to our generous sponsors who support this project covering CI e
 
 <p align="center">
   <a href="https://www.spectrocloud.com/" target="blank">
-    <img height="200" src="https://github.com/go-skynet/LocalAI/assets/2420543/68a6f3cb-8a65-4a4d-99b5-6417a8905512">
+    <img height="200" src="https://github.com/user-attachments/assets/72eab1dd-8b93-4fc0-9ade-84db49f24962">
   </a>
   <a href="https://www.premai.io/" target="blank">
     <img height="200" src="https://github.com/mudler/LocalAI/assets/2420543/42e4ca83-661e-4f79-8e46-ae43689683d6"> <br>

aio/cpu/embeddings.yaml

@@ -1,7 +1,7 @@
-name: text-embedding-ada-002
 embeddings: true
+name: text-embedding-ada-002
 parameters:
-  model: huggingface://hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF/llama-3.2-1b-instruct-q4_k_m.gguf
+  model: huggingface://bartowski/granite-embedding-107m-multilingual-GGUF/granite-embedding-107m-multilingual-f16.gguf
 
 usage: |
     You can test this model with curl like this:

aio/cpu/image-gen.yaml

@@ -1,56 +1,17 @@
 name: stablediffusion
-backend: stablediffusion
+backend: stablediffusion-ggml
+cfg_scale: 4.5
+
+options:
+- sampler:euler
 parameters:
-  model: stablediffusion_assets
+  model: stable-diffusion-v1-5-pruned-emaonly-Q4_0.gguf
-
+step: 25
-license: "BSD-3"
-urls:
-- https://github.com/EdVince/Stable-Diffusion-NCNN
-- https://github.com/EdVince/Stable-Diffusion-NCNN/blob/main/LICENSE
-
-description: |
-     Stable Diffusion in NCNN with c++, supported txt2img and img2img
 
 download_files:
-- filename: "stablediffusion_assets/AutoencoderKL-256-256-fp16-opt.param"
+- filename: "stable-diffusion-v1-5-pruned-emaonly-Q4_0.gguf"
-  sha256: "18ca4b66685e21406bcf64c484b3b680b4949900415536d599cc876579c85c82"
+  sha256: "b8944e9fe0b69b36ae1b5bb0185b3a7b8ef14347fe0fa9af6c64c4829022261f"
-  uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/AutoencoderKL-256-256-fp16-opt.param"
+  uri: "huggingface://second-state/stable-diffusion-v1-5-GGUF/stable-diffusion-v1-5-pruned-emaonly-Q4_0.gguf"
-- filename: "stablediffusion_assets/AutoencoderKL-512-512-fp16-opt.param"
-  sha256: "cf45f63aacf3dbbab0f59ed92a6f2c14d9a1801314631cd3abe91e3c85639a20"
-  uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/AutoencoderKL-512-512-fp16-opt.param"
-- filename: "stablediffusion_assets/AutoencoderKL-base-fp16.param"
-  sha256: "0254a056dce61b0c27dc9ec1b78b53bcf55315c540f55f051eb841aa992701ba"
-  uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/AutoencoderKL-base-fp16.param"
-- filename: "stablediffusion_assets/AutoencoderKL-encoder-512-512-fp16.bin"
-  sha256: "ddcb79a9951b9f91e05e087739ed69da2c1c4ae30ba4168cce350b49d617c9fa"
-  uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/AutoencoderKL-encoder-512-512-fp16.bin"
-- filename: "stablediffusion_assets/AutoencoderKL-fp16.bin"
-  sha256: "f02e71f80e70252734724bbfaed5c4ddd3a8ed7e61bb2175ff5f53099f0e35dd"
-  uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/AutoencoderKL-fp16.bin"
-- filename: "stablediffusion_assets/FrozenCLIPEmbedder-fp16.bin"
-  sha256: "1c9a12f4e1dd1b295a388045f7f28a2352a4d70c3dc96a542189a3dd7051fdd6"
-  uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/FrozenCLIPEmbedder-fp16.bin"
-- filename: "stablediffusion_assets/FrozenCLIPEmbedder-fp16.param"
-  sha256: "471afbe678dd1fd3fe764ef9c6eccaccb0a7d7e601f27b462aa926b20eb368c9"
-  uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/FrozenCLIPEmbedder-fp16.param"
-- filename: "stablediffusion_assets/log_sigmas.bin"
-  sha256: "a2089f8aa4c61f9c200feaec541ab3f5c94233b28deb6d5e8bcd974fa79b68ac"
-  uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/raw/main/x86/linux/assets/log_sigmas.bin"
-- filename: "stablediffusion_assets/UNetModel-256-256-MHA-fp16-opt.param"
-  sha256: "a58c380229f09491776df837b7aa7adffc0a87821dc4708b34535da2e36e3da1"
-  uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/UNetModel-256-256-MHA-fp16-opt.param"
-- filename: "stablediffusion_assets/UNetModel-512-512-MHA-fp16-opt.param"
-  sha256: "f12034067062827bd7f43d1d21888d1f03905401acf6c6eea22be23c259636fa"
-  uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/UNetModel-512-512-MHA-fp16-opt.param"
-- filename: "stablediffusion_assets/UNetModel-base-MHA-fp16.param"
-  sha256: "696f6975de49f4325b53ce32aff81861a6d6c07cd9ce3f0aae2cc405350af38d"
-  uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/UNetModel-base-MHA-fp16.param"
-- filename: "stablediffusion_assets/UNetModel-MHA-fp16.bin"
-  sha256: "d618918d011bfc1f644c0f2a33bf84931bd53b28a98492b0a8ed6f3a818852c3"
-  uri: "https://github.com/EdVince/Stable-Diffusion-NCNN/releases/download/naifu/UNetModel-MHA-fp16.bin"
-- filename: "stablediffusion_assets/vocab.txt"
-  sha256: "e30e57b6f1e47616982ef898d8922be24e535b4fa3d0110477b3a6f02ebbae7d"
-  uri: "https://raw.githubusercontent.com/EdVince/Stable-Diffusion-NCNN/main/x86/linux/assets/vocab.txt"
 
 usage: |
         curl http://localhost:8080/v1/images/generations \

aio/cpu/text-to-text.yaml

@@ -1,101 +1,57 @@
-name: gpt-4
-mmap: true
-parameters:
-  model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
 context_size: 8192
-
+f16: true
-stopwords:
-- "<|im_end|>"
-- "<dummy32000>"
-- "</tool_call>"
-- "<|eot_id|>"
-- "<|end_of_text|>"
-
 function:
-  # disable injecting the "answer" tool
-  disable_no_action: true
-
   grammar:
-    # This allows the grammar to also return messages
+    no_mixed_free_string: true
-    mixed_mode: true
+    schema_type: llama3.1 # or JSON is supported too (json)
-    # Suffix to add to the grammar
+  response_regex:
-    #prefix: '<tool_call>\n'
+  - <function=(?P<name>\w+)>(?P<arguments>.*)</function>
-    # Force parallel calls in the grammar
+mmap: true
-    # parallel_calls: true
+name: gpt-4
-
+parameters:
-  return_name_in_function_response: true
+  model: Hermes-3-Llama-3.2-3B-Q4_K_M.gguf
-  # Without grammar uncomment the lines below
+stopwords:
-  # Warning: this is relying only on the capability of the
+- <|im_end|>
-  # LLM model to generate the correct function call.
+- <dummy32000>
-  json_regex_match: 
+- <|eot_id|>
-   - "(?s)<tool_call>(.*?)</tool_call>"
+- <|end_of_text|>
-   - "(?s)<tool_call>(.*?)"
-  replace_llm_results:
-  # Drop the scratchpad content from responses
-  - key: "(?s)<scratchpad>.*</scratchpad>"
-    value: ""
-  replace_function_results: 
-  # Replace everything that is not JSON array or object
-  # 
-  - key: '(?s)^[^{\[]*'
-    value: ""
-  - key: '(?s)[^}\]]*$'
-    value: ""
-  - key: "'([^']*?)'"
-    value: "_DQUOTE_${1}_DQUOTE_"
-  - key: '\\"'
-    value: "__TEMP_QUOTE__"
-  - key: "\'"
-    value: "'"
-  - key: "_DQUOTE_"
-    value: '"'
-  - key: "__TEMP_QUOTE__"
-    value: '"'
-  # Drop the scratchpad content from responses
-  - key: "(?s)<scratchpad>.*</scratchpad>"
-    value: ""
-
 template:
   chat: |
-    {{.Input -}}
+    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
-    <|im_start|>assistant
+    You are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>
+    {{.Input }}
+    <|start_header_id|>assistant<|end_header_id|>
   chat_message: |
-    <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
+    <|start_header_id|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}<|end_header_id|>
-    {{- if .FunctionCall }}
+    {{ if .FunctionCall -}}
-    <tool_call>
+    {{ else if eq .RoleName "tool" -}}
-    {{- else if eq .RoleName "tool" }}
+    The Function was executed and the response was:
-    <tool_response>
+    {{ end -}}
-    {{- end }}
+    {{ if .Content -}}
-    {{- if .Content}}
+    {{.Content -}}
-    {{.Content }}
+    {{ else if .FunctionCall -}}
-    {{- end }}
+    {{ range .FunctionCall }}
-    {{- if .FunctionCall}}
+    [{{.FunctionCall.Name}}({{.FunctionCall.Arguments}})]
-    {{toJson .FunctionCall}}
+    {{ end }}
-    {{- end }}
+    {{ end -}}
-    {{- if .FunctionCall }}
+    <|eot_id|>
-    </tool_call>
-    {{- else if eq .RoleName "tool" }}
-    </tool_response>
-    {{- end }}<|im_end|>
   completion: |
     {{.Input}}
-  function: |-
+  function: |
-    <|im_start|>system
+    <|start_header_id|>system<|end_header_id|>
-    You are a function calling AI model.
+    You are an expert in composing functions. You are given a question and a set of possible functions.
-    Here are the available tools:
+    Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
-    <tools>
+    If none of the functions can be used, point it out. If the given question lacks the parameters required by the function, also point it out. You should only return the function call in tools call sections.
-    {{range .Functions}}
+    If you decide to invoke any of the function(s), you MUST put it in the format as follows:
-    {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
+    [func_name1(params_name1=params_value1,params_name2=params_value2,...),func_name2(params_name1=params_value1,params_name2=params_value2,...)]
-    {{end}}
+    You SHOULD NOT include any other text in the response.
-    </tools>
+    Here is a list of functions in JSON format that you can invoke.
-    You should call the tools provided to you sequentially
+    {{toJson .Functions}}
-    Please use <scratchpad> XML tags to record your reasoning and planning before you call the functions as follows:
+    <|eot_id|><|start_header_id|>user<|end_header_id|>
-    <scratchpad>
+    {{.Input}}
-    {step-by-step reasoning and plan in bullet points}
+    <|eot_id|><|start_header_id|>assistant<|end_header_id|>
-    </scratchpad>
+
-    For each function call return a json object with function name and arguments within <tool_call> XML tags as follows:
+download_files:
-    <tool_call>
+- filename: Hermes-3-Llama-3.2-3B-Q4_K_M.gguf
-    {"arguments": <args-dict>, "name": <function-name>}
+  sha256: 2e220a14ba4328fee38cf36c2c068261560f999fadb5725ce5c6d977cb5126b5
-    </tool_call><|im_end|>
+  uri: huggingface://bartowski/Hermes-3-Llama-3.2-3B-GGUF/Hermes-3-Llama-3.2-3B-Q4_K_M.gguf
-    {{.Input -}}
-    <|im_start|>assistant

aio/cpu/vad.yaml

@@ -0,0 +1,8 @@
+backend: silero-vad
+name: silero-vad
+parameters:
+  model: silero-vad.onnx
+download_files:
+- filename: silero-vad.onnx
+  uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
+  sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

aio/cpu/vision.yaml

@@ -1,31 +1,49 @@
-backend: llama-cpp
 context_size: 4096
 f16: true
 mmap: true
+mmproj: minicpm-v-2_6-mmproj-f16.gguf
 name: gpt-4o
-
-roles:
-  user: "USER:"
-  assistant: "ASSISTANT:"
-  system: "SYSTEM:"
-
-mmproj: bakllava-mmproj.gguf
 parameters:
-  model: bakllava.gguf
+  model: minicpm-v-2_6-Q4_K_M.gguf
-
+stopwords:
+- <|im_end|>
+- <dummy32000>
+- </s>
+- <|endoftext|>
 template:
   chat: |
-    A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
+    {{.Input -}}
+    <|im_start|>assistant
+  chat_message: |
+    <|im_start|>{{ .RoleName }}
+    {{ if .FunctionCall -}}
+    Function call:
+    {{ else if eq .RoleName "tool" -}}
+    Function response:
+    {{ end -}}
+    {{ if .Content -}}
+    {{.Content }}
+    {{ end -}}
+    {{ if .FunctionCall -}}
+    {{toJson .FunctionCall}}
+    {{ end -}}<|im_end|>
+  completion: |
     {{.Input}}
-    ASSISTANT:
+  function: |
+    <|im_start|>system
+    You are a function calling AI model. You are provided with functions to execute. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
+    {{range .Functions}}
+    {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
+    {{end}}
+    For each function call return a json object with function name and arguments
+    <|im_end|>
+    {{.Input -}}
+    <|im_start|>assistant
 
 download_files:
-- filename: bakllava.gguf
+- filename: minicpm-v-2_6-Q4_K_M.gguf
-  uri: huggingface://mys/ggml_bakllava-1/ggml-model-q4_k.gguf
+  sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
-- filename: bakllava-mmproj.gguf
+  uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
-  uri: huggingface://mys/ggml_bakllava-1/mmproj-model-f16.gguf
+- filename: minicpm-v-2_6-mmproj-f16.gguf
-
+  uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
-usage: |
+  sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd
-    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
-        "model": "gpt-4-vision-preview",
-        "messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'

aio/entrypoint.sh

@@ -129,7 +129,7 @@ detect_gpu
 detect_gpu_size
 
 PROFILE="${PROFILE:-$GPU_SIZE}" # default to cpu
-export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vision.yaml}"
+export MODELS="${MODELS:-/aio/${PROFILE}/embeddings.yaml,/aio/${PROFILE}/rerank.yaml,/aio/${PROFILE}/text-to-speech.yaml,/aio/${PROFILE}/image-gen.yaml,/aio/${PROFILE}/text-to-text.yaml,/aio/${PROFILE}/speech-to-text.yaml,/aio/${PROFILE}/vad.yaml,/aio/${PROFILE}/vision.yaml}"
 
 check_vars
 

aio/gpu-8g/embeddings.yaml

@@ -1,7 +1,7 @@
+embeddings: true
 name: text-embedding-ada-002
-backend: sentencetransformers
 parameters:
-  model: all-MiniLM-L6-v2
+  model: huggingface://bartowski/granite-embedding-107m-multilingual-GGUF/granite-embedding-107m-multilingual-f16.gguf
 
 usage: |
     You can test this model with curl like this:

aio/gpu-8g/text-to-text.yaml

@@ -1,101 +1,53 @@
-name: gpt-4
+context_size: 4096
-mmap: true
+f16: true
-parameters:
-  model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
-context_size: 8192
-
-stopwords:
-- "<|im_end|>"
-- "<dummy32000>"
-- "</tool_call>"
-- "<|eot_id|>"
-- "<|end_of_text|>"
-
 function:
-  # disable injecting the "answer" tool
+  capture_llm_results:
-  disable_no_action: true
+  - (?s)<Thought>(.*?)</Thought>
-
   grammar:
-    # This allows the grammar to also return messages
+    properties_order: name,arguments
-    mixed_mode: true
-    # Suffix to add to the grammar
-    #prefix: '<tool_call>\n'
-    # Force parallel calls in the grammar
-    # parallel_calls: true
-
-  return_name_in_function_response: true
-  # Without grammar uncomment the lines below
-  # Warning: this is relying only on the capability of the
-  # LLM model to generate the correct function call.
   json_regex_match:
-   - "(?s)<tool_call>(.*?)</tool_call>"
+  - (?s)<Output>(.*?)</Output>
-   - "(?s)<tool_call>(.*?)"
   replace_llm_results:
-  # Drop the scratchpad content from responses
+  - key: (?s)<Thought>(.*?)</Thought>
-  - key: "(?s)<scratchpad>.*</scratchpad>"
     value: ""
-  replace_function_results: 
+mmap: true
-  # Replace everything that is not JSON array or object
+name: gpt-4
-  # 
+parameters:
-  - key: '(?s)^[^{\[]*'
+  model: localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf
-    value: ""
+stopwords:
-  - key: '(?s)[^}\]]*$'
+- <|im_end|>
-    value: ""
+- <dummy32000>
-  - key: "'([^']*?)'"
+- </s>
-    value: "_DQUOTE_${1}_DQUOTE_"
-  - key: '\\"'
-    value: "__TEMP_QUOTE__"
-  - key: "\'"
-    value: "'"
-  - key: "_DQUOTE_"
-    value: '"'
-  - key: "__TEMP_QUOTE__"
-    value: '"'
-  # Drop the scratchpad content from responses
-  - key: "(?s)<scratchpad>.*</scratchpad>"
-    value: ""
-
 template:
   chat: |
     {{.Input -}}
     <|im_start|>assistant
   chat_message: |
-    <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
+    <|im_start|>{{ .RoleName }}
-    {{- if .FunctionCall }}
+    {{ if .FunctionCall -}}
-    <tool_call>
+    Function call:
-    {{- else if eq .RoleName "tool" }}
+    {{ else if eq .RoleName "tool" -}}
-    <tool_response>
+    Function response:
-    {{- end }}
+    {{ end -}}
-    {{- if .Content}}
+    {{ if .Content -}}
     {{.Content }}
-    {{- end }}
+    {{ end -}}
-    {{- if .FunctionCall}}
+    {{ if .FunctionCall -}}
     {{toJson .FunctionCall}}
-    {{- end }}
+    {{ end -}}<|im_end|>
-    {{- if .FunctionCall }}
-    </tool_call>
-    {{- else if eq .RoleName "tool" }}
-    </tool_response>
-    {{- end }}<|im_end|>
   completion: |
     {{.Input}}
-  function: |-
+  function: |
     <|im_start|>system
-    You are a function calling AI model.
+    You are an AI assistant that executes function calls, and these are the tools at your disposal:
-    Here are the available tools:
-    <tools>
     {{range .Functions}}
     {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
     {{end}}
-    </tools>
+    <|im_end|>
-    You should call the tools provided to you sequentially
-    Please use <scratchpad> XML tags to record your reasoning and planning before you call the functions as follows:
-    <scratchpad>
-    {step-by-step reasoning and plan in bullet points}
-    </scratchpad>
-    For each function call return a json object with function name and arguments within <tool_call> XML tags as follows:
-    <tool_call>
-    {"arguments": <args-dict>, "name": <function-name>}
-    </tool_call><|im_end|>
     {{.Input -}}
     <|im_start|>assistant
+
+download_files:
+- filename: localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf
+  sha256: 4e7b7fe1d54b881f1ef90799219dc6cc285d29db24f559c8998d1addb35713d4
+  uri: huggingface://mudler/LocalAI-functioncall-qwen2.5-7b-v0.5-Q4_K_M-GGUF/localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf

aio/gpu-8g/vad.yaml

@@ -0,0 +1,8 @@
+backend: silero-vad
+name: silero-vad
+parameters:
+  model: silero-vad.onnx
+download_files:
+- filename: silero-vad.onnx
+  uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
+  sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

aio/gpu-8g/vision.yaml

@@ -1,35 +1,49 @@
-backend: llama-cpp
 context_size: 4096
 f16: true
 mmap: true
+mmproj: minicpm-v-2_6-mmproj-f16.gguf
 name: gpt-4o
-
-roles:
-  user: "USER:"
-  assistant: "ASSISTANT:"
-  system: "SYSTEM:"
-
-mmproj: llava-v1.6-7b-mmproj-f16.gguf
 parameters:
-  model: llava-v1.6-mistral-7b.Q5_K_M.gguf
+  model: minicpm-v-2_6-Q4_K_M.gguf
-  temperature: 0.2
+stopwords:
-  top_k: 40
+- <|im_end|>
-  top_p: 0.95
+- <dummy32000>
-  seed: -1
+- </s>
-
+- <|endoftext|>
 template:
   chat: |
-    A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
+    {{.Input -}}
+    <|im_start|>assistant
+  chat_message: |
+    <|im_start|>{{ .RoleName }}
+    {{ if .FunctionCall -}}
+    Function call:
+    {{ else if eq .RoleName "tool" -}}
+    Function response:
+    {{ end -}}
+    {{ if .Content -}}
+    {{.Content }}
+    {{ end -}}
+    {{ if .FunctionCall -}}
+    {{toJson .FunctionCall}}
+    {{ end -}}<|im_end|>
+  completion: |
     {{.Input}}
-    ASSISTANT:
+  function: |
+    <|im_start|>system
+    You are a function calling AI model. You are provided with functions to execute. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
+    {{range .Functions}}
+    {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
+    {{end}}
+    For each function call return a json object with function name and arguments
+    <|im_end|>
+    {{.Input -}}
+    <|im_start|>assistant
 
 download_files:
-- filename: llava-v1.6-mistral-7b.Q5_K_M.gguf
+- filename: minicpm-v-2_6-Q4_K_M.gguf
-  uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q5_K_M.gguf
+  sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
-- filename: llava-v1.6-7b-mmproj-f16.gguf
+  uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
-  uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf
+- filename: minicpm-v-2_6-mmproj-f16.gguf
-
+  uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
-usage: |
+  sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd
-    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
-        "model": "gpt-4-vision-preview",
-        "messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'

aio/intel/embeddings.yaml

@@ -1,7 +1,7 @@
+embeddings: true
 name: text-embedding-ada-002
-backend: sentencetransformers
 parameters:
-  model: all-MiniLM-L6-v2
+  model: huggingface://bartowski/granite-embedding-107m-multilingual-GGUF/granite-embedding-107m-multilingual-f16.gguf
 
 usage: |
     You can test this model with curl like this:

aio/intel/text-to-text.yaml

@@ -1,103 +1,53 @@
-name: gpt-4
+context_size: 4096
-mmap: false
+f16: true
-context_size: 8192
-
-f16: false
-parameters:
-  model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
-
-stopwords:
-- "<|im_end|>"
-- "<dummy32000>"
-- "</tool_call>"
-- "<|eot_id|>"
-- "<|end_of_text|>"
-
 function:
-  # disable injecting the "answer" tool
+  capture_llm_results:
-  disable_no_action: true
+  - (?s)<Thought>(.*?)</Thought>
-
   grammar:
-    # This allows the grammar to also return messages
+    properties_order: name,arguments
-    mixed_mode: true
-    # Suffix to add to the grammar
-    #prefix: '<tool_call>\n'
-    # Force parallel calls in the grammar
-    # parallel_calls: true
-
-  return_name_in_function_response: true
-  # Without grammar uncomment the lines below
-  # Warning: this is relying only on the capability of the
-  # LLM model to generate the correct function call.
   json_regex_match:
-   - "(?s)<tool_call>(.*?)</tool_call>"
+  - (?s)<Output>(.*?)</Output>
-   - "(?s)<tool_call>(.*?)"
   replace_llm_results:
-  # Drop the scratchpad content from responses
+  - key: (?s)<Thought>(.*?)</Thought>
-  - key: "(?s)<scratchpad>.*</scratchpad>"
     value: ""
-  replace_function_results: 
+mmap: true
-  # Replace everything that is not JSON array or object
+name: gpt-4
-  # 
+parameters:
-  - key: '(?s)^[^{\[]*'
+  model: localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf
-    value: ""
+stopwords:
-  - key: '(?s)[^}\]]*$'
+- <|im_end|>
-    value: ""
+- <dummy32000>
-  - key: "'([^']*?)'"
+- </s>
-    value: "_DQUOTE_${1}_DQUOTE_"
-  - key: '\\"'
-    value: "__TEMP_QUOTE__"
-  - key: "\'"
-    value: "'"
-  - key: "_DQUOTE_"
-    value: '"'
-  - key: "__TEMP_QUOTE__"
-    value: '"'
-  # Drop the scratchpad content from responses
-  - key: "(?s)<scratchpad>.*</scratchpad>"
-    value: ""
-
 template:
   chat: |
     {{.Input -}}
     <|im_start|>assistant
   chat_message: |
-    <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
+    <|im_start|>{{ .RoleName }}
-    {{- if .FunctionCall }}
+    {{ if .FunctionCall -}}
-    <tool_call>
+    Function call:
-    {{- else if eq .RoleName "tool" }}
+    {{ else if eq .RoleName "tool" -}}
-    <tool_response>
+    Function response:
-    {{- end }}
+    {{ end -}}
-    {{- if .Content}}
+    {{ if .Content -}}
     {{.Content }}
-    {{- end }}
+    {{ end -}}
-    {{- if .FunctionCall}}
+    {{ if .FunctionCall -}}
     {{toJson .FunctionCall}}
-    {{- end }}
+    {{ end -}}<|im_end|>
-    {{- if .FunctionCall }}
-    </tool_call>
-    {{- else if eq .RoleName "tool" }}
-    </tool_response>
-    {{- end }}<|im_end|>
   completion: |
     {{.Input}}
-  function: |-
+  function: |
     <|im_start|>system
-    You are a function calling AI model.
+    You are an AI assistant that executes function calls, and these are the tools at your disposal:
-    Here are the available tools:
-    <tools>
     {{range .Functions}}
     {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
     {{end}}
-    </tools>
+    <|im_end|>
-    You should call the tools provided to you sequentially
-    Please use <scratchpad> XML tags to record your reasoning and planning before you call the functions as follows:
-    <scratchpad>
-    {step-by-step reasoning and plan in bullet points}
-    </scratchpad>
-    For each function call return a json object with function name and arguments within <tool_call> XML tags as follows:
-    <tool_call>
-    {"arguments": <args-dict>, "name": <function-name>}
-    </tool_call><|im_end|>
     {{.Input -}}
     <|im_start|>assistant
+
+download_files:
+- filename: localai-functioncall-phi-4-v0.3-q4_k_m.gguf
+  sha256: 23fee048ded2a6e2e1a7b6bbefa6cbf83068f194caa9552aecbaa00fec8a16d5
+  uri: huggingface://mudler/LocalAI-functioncall-phi-4-v0.3-Q4_K_M-GGUF/localai-functioncall-phi-4-v0.3-q4_k_m.gguf

aio/intel/vad.yaml

@@ -0,0 +1,8 @@
+backend: silero-vad
+name: silero-vad
+parameters:
+  model: silero-vad.onnx
+download_files:
+- filename: silero-vad.onnx
+  uri: https://huggingface.co/onnx-community/silero-vad/resolve/main/onnx/model.onnx
+  sha256: a4a068cd6cf1ea8355b84327595838ca748ec29a25bc91fc82e6c299ccdc5808

aio/intel/vision.yaml

@@ -1,35 +1,50 @@
-backend: llama-cpp
 context_size: 4096
-mmap: false
+f16: true
-f16: false
+mmap: true
+mmproj: minicpm-v-2_6-mmproj-f16.gguf
 name: gpt-4o
-
-roles:
-  user: "USER:"
-  assistant: "ASSISTANT:"
-  system: "SYSTEM:"
-
-mmproj: llava-v1.6-7b-mmproj-f16.gguf
 parameters:
-  model: llava-v1.6-mistral-7b.Q5_K_M.gguf
+  model: minicpm-v-2_6-Q4_K_M.gguf
-  temperature: 0.2
+stopwords:
-  top_k: 40
+- <|im_end|>
-  top_p: 0.95
+- <dummy32000>
-  seed: -1
+- </s>
-
+- <|endoftext|>
 template:
   chat: |
-    A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
+    {{.Input -}}
+    <|im_start|>assistant
+  chat_message: |
+    <|im_start|>{{ .RoleName }}
+    {{ if .FunctionCall -}}
+    Function call:
+    {{ else if eq .RoleName "tool" -}}
+    Function response:
+    {{ end -}}
+    {{ if .Content -}}
+    {{.Content }}
+    {{ end -}}
+    {{ if .FunctionCall -}}
+    {{toJson .FunctionCall}}
+    {{ end -}}<|im_end|>
+  completion: |
     {{.Input}}
-    ASSISTANT:
+  function: |
+    <|im_start|>system
+    You are a function calling AI model. You are provided with functions to execute. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
+    {{range .Functions}}
+    {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
+    {{end}}
+    For each function call return a json object with function name and arguments
+    <|im_end|>
+    {{.Input -}}
+    <|im_start|>assistant
+
 
 download_files:
-- filename: llava-v1.6-mistral-7b.Q5_K_M.gguf
+- filename: minicpm-v-2_6-Q4_K_M.gguf
-  uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q5_K_M.gguf
+  sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
-- filename: llava-v1.6-7b-mmproj-f16.gguf
+  uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
-  uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf
+- filename: minicpm-v-2_6-mmproj-f16.gguf
-
+  uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
-usage: |
+  sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd
-    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
-        "model": "gpt-4-vision-preview",
-        "messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'

assets.go

@@ -1,6 +1,15 @@
 package main
 
-import "embed"
+import (
+	rice "github.com/GeertJohan/go.rice"
+)
 
-//go:embed backend-assets/*
+var backendAssets *rice.Box
-var backendAssets embed.FS
+
+func init() {
+	var err error
+	backendAssets, err = rice.FindBox("backend-assets")
+	if err != nil {
+		panic(err)
+	}
+}

backend/backend.proto

@@ -14,6 +14,7 @@ service Backend {
   rpc PredictStream(PredictOptions) returns (stream Reply) {}
   rpc Embedding(PredictOptions) returns (EmbeddingResult) {}
   rpc GenerateImage(GenerateImageRequest) returns (Result) {}
+  rpc GenerateVideo(GenerateVideoRequest) returns (Result) {}
   rpc AudioTranscription(TranscriptRequest) returns (TranscriptResult) {}
   rpc TTS(TTSRequest) returns (Result) {}
   rpc SoundGeneration(SoundGenerationRequest) returns (Result) {}
@@ -159,6 +160,12 @@ message Reply {
   bytes message = 1;
   int32 tokens = 2;
   int32 prompt_tokens = 3;
+  double timing_prompt_processing = 4;
+  double timing_token_generation = 5;
+}
+
+message GrammarTrigger {
+  string word = 1;
 }
 
 message ModelOptions {
@@ -184,11 +191,7 @@ message ModelOptions {
   int32 NGQA = 20;
   string ModelFile = 21;
 
-  // AutoGPTQ
+
-  string Device = 22;
-  bool UseTriton = 23;
-  string ModelBaseName = 24;
-  bool UseFastTokenizer = 25;
 
   // Diffusers
   string PipelineType = 26;
@@ -222,6 +225,11 @@ message ModelOptions {
   int32  MaxModelLen = 54;
   int32  TensorParallelSize = 55;
   string LoadFormat = 58;
+  bool   DisableLogStatus = 66;
+  string DType = 67;
+  int32  LimitImagePerPrompt = 68;
+  int32  LimitVideoPerPrompt = 69;
+  int32  LimitAudioPerPrompt = 70;
 
   string MMProj = 41;
 
@@ -245,6 +253,8 @@ message ModelOptions {
 
   string CacheTypeKey = 63;
   string CacheTypeValue = 64;
+
+  repeated GrammarTrigger GrammarTriggers = 65;
 }
 
 message Result {
@@ -292,6 +302,19 @@ message GenerateImageRequest {
   int32 CLIPSkip = 11;
 }
 
+message GenerateVideoRequest {
+  string prompt = 1;
+  string start_image = 2;  // Path or base64 encoded image for the start frame
+  string end_image = 3;    // Path or base64 encoded image for the end frame
+  int32 width = 4;
+  int32 height = 5;
+  int32 num_frames = 6;    // Number of frames to generate
+  int32 fps = 7;          // Frames per second
+  int32 seed = 8;
+  float cfg_scale = 9;    // Classifier-free guidance scale
+  string dst = 10;        // Output path for the generated video
+}
+
 message TTSRequest {
   string text = 1;
   string model = 2;

backend/cpp/llama/CMakeLists.txt

@@ -1,17 +1,17 @@
 
 ## XXX: In some versions of CMake clip wasn't being built before llama.
 ## This is an hack for now, but it should be fixed in the future.
-set(TARGET myclip)
+# set(TARGET myclip)
-add_library(${TARGET} clip.cpp clip.h llava.cpp llava.h)
+# add_library(${TARGET} clip.cpp clip.h clip-impl.h llava.cpp llava.h)
-install(TARGETS ${TARGET} LIBRARY)
+# install(TARGETS ${TARGET} LIBRARY)
-target_include_directories(myclip PUBLIC .)
+# target_include_directories(myclip PUBLIC .)
-target_include_directories(myclip PUBLIC ../..)
+# target_include_directories(myclip PUBLIC ../..)
-target_include_directories(myclip PUBLIC ../../common)
+# target_include_directories(myclip PUBLIC ../../common)
-target_link_libraries(${TARGET} PRIVATE common ggml llama ${CMAKE_THREAD_LIBS_INIT})
+# target_link_libraries(${TARGET} PRIVATE common ggml llama ${CMAKE_THREAD_LIBS_INIT})
-target_compile_features(${TARGET} PRIVATE cxx_std_11)
+# target_compile_features(${TARGET} PRIVATE cxx_std_11)
-if (NOT MSVC)
+# if (NOT MSVC)
-    target_compile_options(${TARGET} PRIVATE -Wno-cast-qual) # stb_image.h
+#     target_compile_options(${TARGET} PRIVATE -Wno-cast-qual) # stb_image.h
-endif()
+# endif()
 # END CLIP hack
 
 
@@ -75,7 +75,11 @@ add_library(hw_grpc_proto
   ${hw_proto_hdrs} )
 
 add_executable(${TARGET} grpc-server.cpp utils.hpp json.hpp)
-target_link_libraries(${TARGET} PRIVATE common llama myclip ${CMAKE_THREAD_LIBS_INIT} absl::flags hw_grpc_proto
+
+target_include_directories(${TARGET} PRIVATE ../llava)
+target_include_directories(${TARGET} PRIVATE ${CMAKE_SOURCE_DIR})
+
+target_link_libraries(${TARGET} PRIVATE common llama mtmd ${CMAKE_THREAD_LIBS_INIT} absl::flags hw_grpc_proto
   absl::flags_parse
   gRPC::${_REFLECTION}
   gRPC::${_GRPC_GRPCPP}

backend/cpp/llama/Makefile

@@ -8,7 +8,7 @@ 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
-CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
+CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF -DLLAMA_CURL=OFF
 
 # If build type is cublas, then we set -DGGML_CUDA=ON to CMAKE_ARGS automatically
 ifeq ($(BUILD_TYPE),cublas)
@@ -36,11 +36,18 @@ else ifeq ($(OS),Darwin)
 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+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx \
+		-DCMAKE_CXX_FLAGS="-fsycl" \
+		-DGGML_SYCL_F16=ON
 endif
 
 ifeq ($(BUILD_TYPE),sycl_f32)
-	CMAKE_ARGS+=-DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx \
+		-DCMAKE_CXX_FLAGS="-fsycl"
 endif
 
 llama.cpp:
@@ -52,8 +59,8 @@ llama.cpp:
 	git checkout -b build $(LLAMA_VERSION) && \
 	git submodule update --init --recursive --depth 1 --single-branch
 
-llama.cpp/examples/grpc-server: llama.cpp
+llama.cpp/tools/grpc-server: llama.cpp
-	mkdir -p llama.cpp/examples/grpc-server
+	mkdir -p llama.cpp/tools/grpc-server
 	bash prepare.sh
 
 rebuild:
@@ -63,13 +70,13 @@ rebuild:
 
 purge:
 	rm -rf llama.cpp/build
-	rm -rf llama.cpp/examples/grpc-server
+	rm -rf llama.cpp/tools/grpc-server
 	rm -rf grpc-server
 
 clean: purge
 	rm -rf llama.cpp
 
-grpc-server: llama.cpp llama.cpp/examples/grpc-server
+grpc-server: llama.cpp llama.cpp/tools/grpc-server
 	@echo "Building grpc-server with $(BUILD_TYPE) build type and $(CMAKE_ARGS)"
 ifneq (,$(findstring sycl,$(BUILD_TYPE)))
 	+bash -c "source $(ONEAPI_VARS); \

backend/cpp/llama/patches/01-llava.patch

@@ -1,7 +1,7 @@
-diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
+diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp
 index 3cd0d2fa..6c5e811a 100644
---- a/examples/llava/clip.cpp
+--- a/tools/mtmd/clip.cpp
-+++ b/examples/llava/clip.cpp
++++ b/tools/mtmd/clip.cpp
 @@ -2608,7 +2608,7 @@ bool clip_image_batch_encode(clip_ctx * ctx, const int n_threads, const clip_ima
                  struct ggml_tensor * patches = ggml_graph_get_tensor(gf, "patches");
                  int* patches_data = (int*)malloc(ggml_nbytes(patches));

backend/cpp/llama/prepare.sh

@@ -7,21 +7,22 @@ for patch in $(ls patches); do
     patch -d llama.cpp/ -p1 < patches/$patch
 done 
 
-cp -r CMakeLists.txt llama.cpp/examples/grpc-server/
+cp -r CMakeLists.txt llama.cpp/tools/grpc-server/
-cp -r grpc-server.cpp llama.cpp/examples/grpc-server/
+cp -r grpc-server.cpp llama.cpp/tools/grpc-server/
-cp -rfv json.hpp llama.cpp/examples/grpc-server/
+cp -rfv json.hpp llama.cpp/tools/grpc-server/
-cp -rfv utils.hpp llama.cpp/examples/grpc-server/
+cp -rfv utils.hpp llama.cpp/tools/grpc-server/
     
-if grep -q "grpc-server" llama.cpp/examples/CMakeLists.txt; then
+if grep -q "grpc-server" llama.cpp/tools/CMakeLists.txt; then
     echo "grpc-server already added"
 else
-    echo "add_subdirectory(grpc-server)" >> llama.cpp/examples/CMakeLists.txt
+    echo "add_subdirectory(grpc-server)" >> llama.cpp/tools/CMakeLists.txt
 fi
 
 ## XXX: In some versions of CMake clip wasn't being built before llama.
 ## This is an hack for now, but it should be fixed in the future.
-cp -rfv llama.cpp/examples/llava/clip.h llama.cpp/examples/grpc-server/clip.h
+# cp -rfv llama.cpp/tools/mtmd/clip.h llama.cpp/tools/grpc-server/clip.h
-cp -rfv llama.cpp/examples/llava/llava.cpp llama.cpp/examples/grpc-server/llava.cpp
+# cp -rfv llama.cpp/tools/mtmd/clip-impl.h llama.cpp/tools/grpc-server/clip-impl.h
-echo '#include "llama.h"' > llama.cpp/examples/grpc-server/llava.h
+# cp -rfv llama.cpp/tools/mtmd/llava.cpp llama.cpp/tools/grpc-server/llava.cpp
-cat llama.cpp/examples/llava/llava.h >> llama.cpp/examples/grpc-server/llava.h
+# echo '#include "llama.h"' > llama.cpp/tools/grpc-server/llava.h
-cp -rfv llama.cpp/examples/llava/clip.cpp llama.cpp/examples/grpc-server/clip.cpp
+# cat llama.cpp/tools/mtmd/llava.h >> llama.cpp/tools/grpc-server/llava.h
+# cp -rfv llama.cpp/tools/mtmd/clip.cpp llama.cpp/tools/grpc-server/clip.cpp

backend/cpp/llama/utils.hpp

@@ -1,4 +1,4 @@
-// https://github.com/ggerganov/llama.cpp/blob/master/examples/server/utils.hpp
+// https://github.com/ggerganov/llama.cpp/blob/master/tools/server/utils.hpp
 
 #pragma once
 
@@ -11,7 +11,7 @@
 
 #include "json.hpp"
 
-#include "../llava/clip.h"
+#include "../mtmd/clip.h"
 
 using json = nlohmann::json;
 
@@ -480,4 +480,431 @@ static inline std::vector<uint8_t> base64_decode(const std::string & encoded_str
     }
 
     return ret;
+
+}
+
+
+
+//
+// tokenizer and input processing utils
+//
+
+static bool json_is_array_of_numbers(const json & data) {
+    if (data.is_array()) {
+        for (const auto & e : data) {
+            if (!e.is_number_integer()) {
+                return false;
+            }
+        }
+        return true;
+    }
+    return false;
+}
+
+// is array having BOTH numbers & strings?
+static bool json_is_array_of_mixed_numbers_strings(const json & data) {
+    bool seen_string = false;
+    bool seen_number = false;
+    if (data.is_array()) {
+        for (const auto & e : data) {
+            seen_string |= e.is_string();
+            seen_number |= e.is_number_integer();
+            if (seen_number && seen_string) {
+                return true;
+            }
+        }
+    }
+    return false;
+}
+
+// get value by path(key1 / key2)
+static json json_get_nested_values(const std::vector<std::string> & paths, const json & js) {
+    json result = json::object();
+
+    for (const std::string & path : paths) {
+        json current = js;
+        const auto keys = string_split<std::string>(path, /*separator*/ '/');
+        bool valid_path = true;
+        for (const std::string & k : keys) {
+            if (valid_path && current.is_object() && current.contains(k)) {
+                current = current[k];
+            } else {
+                valid_path = false;
+            }
+        }
+        if (valid_path) {
+            result[path] = current;
+        }
+    }
+    return result;
+}
+
+
+/**
+ * this handles 2 cases:
+ * - only string, example: "string"
+ * - mixed string and tokens, example: [12, 34, "string", 56, 78]
+ */
+static llama_tokens tokenize_mixed(const llama_vocab * vocab, const json & json_prompt, bool add_special, bool parse_special) {
+    // If `add_bos` is true, we only add BOS, when json_prompt is a string,
+    // or the first element of the json_prompt array is a string.
+    llama_tokens prompt_tokens;
+
+    if (json_prompt.is_array()) {
+        bool first = true;
+        for (const auto & p : json_prompt) {
+            if (p.is_string()) {
+                auto s = p.template get<std::string>();
+
+                llama_tokens p;
+                if (first) {
+                    p = common_tokenize(vocab, s, add_special, parse_special);
+                    first = false;
+                } else {
+                    p = common_tokenize(vocab, s, false, parse_special);
+                }
+
+                prompt_tokens.insert(prompt_tokens.end(), p.begin(), p.end());
+            } else {
+                if (first) {
+                    first = false;
+                }
+
+                prompt_tokens.push_back(p.template get<llama_token>());
+            }
+        }
+    } else {
+        auto s = json_prompt.template get<std::string>();
+        prompt_tokens = common_tokenize(vocab, s, add_special, parse_special);
+    }
+
+    return prompt_tokens;
+}
+
+/**
+ * break the input "prompt" object into multiple prompt if needed, then tokenize them
+ * this supports these cases:
+ * - "prompt": "string"
+ * - "prompt": [12, 34, 56]
+ * - "prompt": [12, 34, "string", 56, 78]
+ * and multiple prompts (multi-tasks):
+ * - "prompt": ["string1", "string2"]
+ * - "prompt": ["string1", [12, 34, 56]]
+ * - "prompt": [[12, 34, 56], [78, 90, 12]]
+ * - "prompt": [[12, 34, "string", 56, 78], [12, 34, 56]]
+ */
+static std::vector<llama_tokens> tokenize_input_prompts(const llama_vocab * vocab, const json & json_prompt, bool add_special, bool parse_special) {
+    std::vector<llama_tokens> result;
+    if (json_prompt.is_string() || json_is_array_of_mixed_numbers_strings(json_prompt)) {
+        // string or mixed
+        result.push_back(tokenize_mixed(vocab, json_prompt, add_special, parse_special));
+    } else if (json_is_array_of_numbers(json_prompt)) {
+        // array of tokens
+        result.push_back(json_prompt.get<llama_tokens>());
+    } else if (json_prompt.is_array()) {
+        // array of prompts
+        result.reserve(json_prompt.size());
+        for (const auto & p : json_prompt) {
+            if (p.is_string() || json_is_array_of_mixed_numbers_strings(p)) {
+                result.push_back(tokenize_mixed(vocab, p, add_special, parse_special));
+            } else if (json_is_array_of_numbers(p)) {
+                // array of tokens
+                result.push_back(p.get<llama_tokens>());
+            } else {
+                throw std::runtime_error("element of \"prompt\" must be a string, an list of tokens, or a list of mixed strings & tokens");
+            }
+        }
+    } else {
+        throw std::runtime_error("\"prompt\" must be a string, an list of tokens, a list of mixed strings & tokens, or a list of prompts");
+    }
+    if (result.empty()) {
+        throw std::runtime_error("\"prompt\" must not be empty");
+    }
+    return result;
+}
+
+
+
+
+//
+// utils for interacting with libmtmd
+// (may need to refactor in near future)
+//
+
+/**
+ * server_tokens is a helper to manage the input tokens and image for the server.
+ * it is made this way to simplify the logic of KV cache management.
+ */
+struct server_tokens {
+    bool has_mtmd = false;
+
+private: // disallow accessing these members directly, risking out-of-sync
+
+    // map a **start** position in tokens to the image chunk
+    std::unordered_map<llama_pos, mtmd::input_chunk_ptr> map_pos_to_image;
+
+    // list of tokens
+    // it can include LLAMA_TOKEN_NULL, which is used to indicate a token that is not a text token
+    // a mtmd_input_chunk can occupy multiple tokens, one llama_token per **position**
+    // important: for models using mrope, an image can contain multiple tokens but will use only one **position**
+    llama_tokens tokens;
+
+    // for ex. with input of 5 text tokens and 2 images:
+    //      [0] [1] [2] [3] [4] [img0] [img0] [img0] [img1] [img1]
+    // pos  0   1   2   3   4   5      6      7      8      9
+    // map_pos_to_image will contain: {5, img0}, {8, img1}
+
+public:
+    server_tokens() = default;
+    ~server_tokens() = default;
+
+    // Prevent copying
+    server_tokens(const server_tokens&) = delete;
+    server_tokens& operator=(const server_tokens&) = delete;
+
+    // Allow moving (usually implicitly generated if members are movable)
+    server_tokens(server_tokens&&) = default;
+    server_tokens& operator=(server_tokens&&) = default;
+
+    // Allow accessing elements using [] operator
+    llama_token operator[](size_t index) { return tokens[index]; }
+    const llama_token& operator[](size_t index) const { return tokens[index]; }
+
+    server_tokens(mtmd::input_chunks & mtmd_chunks, bool has_mtmd) : has_mtmd(has_mtmd) {
+        for (size_t i = 0; i < mtmd_chunks.size(); ++i) {
+            push_back(mtmd_chunks[i]);
+        }
+    }
+
+    server_tokens(llama_tokens & tokens, bool has_mtmd) : has_mtmd(has_mtmd), tokens(tokens) {}
+
+    // for debugging
+    std::string str() const {
+        std::ostringstream oss;
+        oss << "tokens: ";
+        for (const auto & t : tokens) {
+            if (t == LLAMA_TOKEN_NULL) {
+                oss << "<embd> ";
+            } else {
+                oss << t << " ";
+            }
+        }
+        oss << "\n";
+        oss << "image pos: ";
+        for (const auto & it : map_pos_to_image) {
+            oss << it.first << ", ";
+        }
+        return oss.str();
+    }
+
+    const mtmd::input_chunk_ptr & find_chunk(llama_pos pos) const {
+        auto it = map_pos_to_image.find(pos);
+        if (it != map_pos_to_image.end()) {
+            return it->second;
+        } else {
+            throw std::runtime_error("Chunk not found");
+        }
+    }
+
+    void push_back(llama_token tok) {
+        if (tok == LLAMA_TOKEN_NULL) {
+            throw std::runtime_error("Invalid token");
+        }
+        tokens.emplace_back(tok);
+    }
+
+    // will create a copy of the chunk if it contains non-text data
+    void push_back(const mtmd_input_chunk * chunk) {
+        auto type = mtmd_input_chunk_get_type(chunk);
+        if (type == MTMD_INPUT_CHUNK_TYPE_IMAGE) {
+            GGML_ASSERT(has_mtmd);
+            auto img_tokens = mtmd_input_chunk_get_tokens_image(chunk);
+            const int n_pos = mtmd_image_tokens_get_n_pos(img_tokens);
+            llama_pos start_pos = tokens.size();
+            for (int i = 0; i < n_pos; ++i) {
+                tokens.emplace_back(LLAMA_TOKEN_NULL);
+            }
+            mtmd::input_chunk_ptr new_chunk(mtmd_input_chunk_copy(chunk));
+            map_pos_to_image[start_pos] = std::move(new_chunk);
+        } else if (type == MTMD_INPUT_CHUNK_TYPE_TEXT) {
+            size_t n_tokens;
+            auto text_tokens = mtmd_input_chunk_get_tokens_text(chunk, &n_tokens);
+            for (size_t i = 0; i < n_tokens; ++i) {
+                push_back(text_tokens[i]);
+            }
+        } else {
+            GGML_ABORT("Invalid chunk type");
+        }
+    }
+
+    // for compatibility with context shift and prompt truncation
+    void insert(const llama_tokens & inp_tokens) {
+        GGML_ASSERT(!has_mtmd); // only allow this if mtmd is disabled
+        tokens.insert(tokens.end(), inp_tokens.begin(), inp_tokens.end());
+    }
+
+    // for compatibility with speculative decoding, ctx shift, slot save/load
+    const llama_tokens & get_text_tokens() const {
+        GGML_ASSERT(!has_mtmd); // only allow this if mtmd is disabled
+        return tokens;
+    }
+
+    // for compatibility with speculative decoding
+    void set_token(llama_pos pos, llama_token id) {
+        GGML_ASSERT(!has_mtmd); // only allow this if mtmd is disabled
+        tokens[pos] = id;
+    }
+
+    size_t size() const {
+        return tokens.size();
+    }
+
+    bool empty() const {
+        return tokens.empty();
+    }
+
+    void clear() {
+        tokens.clear();
+    }
+
+    void resize(size_t n) {
+        GGML_ASSERT(n <= tokens.size());
+        if (has_mtmd) {
+            // we throw an error if we try to remove a token in the middle of an image
+            // for ex. with input of 5 text tokens and 2 images:
+            //    [0] [1] [2] [3] [4] [img0] [img0] [img0] [img1] [img1]
+            // n  1   2   3   4   5   6      7      8      9      10
+            // allowed to resize      ^                    ^
+            // disallowed to resize          ^      ^             ^
+            if (n > 0) {
+                llama_token last_token = tokens[n - 1];
+                // make sure we never remove tokens in the middle of an image
+                if (last_token == LLAMA_TOKEN_NULL) {
+                    find_chunk(n - 1); // will throw an error if the token is not begin-of-chunk
+                }
+            }
+            // remove all image chunks that are not used anymore
+            for (auto it = map_pos_to_image.begin(); it != map_pos_to_image.end(); ) {
+                llama_pos pos = it->first;
+                if (pos >= (llama_pos)n) {
+                    it = map_pos_to_image.erase(it);
+                } else {
+                    ++it;
+                }
+            }
+        }
+        tokens.resize(n);
+    }
+
+    std::string detokenize(const llama_context * ctx, bool special) const {
+        llama_tokens text_tokens;
+        text_tokens.reserve(tokens.size());
+        for (const auto & t : tokens) {
+            if (t != LLAMA_TOKEN_NULL) {
+                text_tokens.push_back(t);
+            }
+        }
+        return common_detokenize(ctx, text_tokens, special);
+    }
+
+    size_t get_common_prefix(const server_tokens & b) const {
+        size_t max_idx = std::min(tokens.size(), b.tokens.size());
+        for (size_t i = 0; i < max_idx; ++i) {
+            auto & ai =   tokens[i];
+            auto & bi = b.tokens[i];
+
+            if (ai == LLAMA_TOKEN_NULL && bi == LLAMA_TOKEN_NULL) {
+                GGML_ASSERT(has_mtmd);
+                const auto & a_chunk =   find_chunk(i);
+                const auto & b_chunk = b.find_chunk(i);
+                GGML_ASSERT(a_chunk && b_chunk);
+                const auto * a_img = mtmd_input_chunk_get_tokens_image(a_chunk.get());
+                const auto * b_img = mtmd_input_chunk_get_tokens_image(b_chunk.get());
+                std::string ai_id  = mtmd_image_tokens_get_id(a_img);
+                std::string bi_id  = mtmd_image_tokens_get_id(b_img);
+                size_t a_pos       = mtmd_image_tokens_get_n_pos(a_img);
+                size_t b_pos       = mtmd_image_tokens_get_n_pos(b_img);
+                if (ai_id == bi_id && a_pos == b_pos) {
+                    GGML_ASSERT(a_pos > 0 && "Invalid image token"); // should never happen
+                    i += a_pos - 1; // will be +1 by the for loop
+                    continue;
+                } else {
+                    return i;
+                }
+            } else if (ai == bi) {
+                continue;
+            } else {
+                return i;
+            }
+        }
+        return max_idx; // all tokens are equal
+    }
+
+    // make sure all text tokens are within the vocab range
+    bool validate(const struct llama_context * ctx) const {
+        const llama_model * model = llama_get_model(ctx);
+        const llama_vocab * vocab = llama_model_get_vocab(model);
+        const int32_t n_vocab = llama_vocab_n_tokens(vocab);
+
+        for (size_t i = 0; i < tokens.size(); ++i) {
+            auto & t = tokens[i];
+            if (t == LLAMA_TOKEN_NULL) {
+                try {
+                    const auto & chunk = find_chunk(i);
+                    const auto * img_tokens = mtmd_input_chunk_get_tokens_image(chunk.get());
+                    size_t n_pos = mtmd_image_tokens_get_n_pos(img_tokens);
+                    i += n_pos - 1; // will be +1 by the for loop
+                } catch (const std::exception & e) {
+                    return false;
+                }
+            } else if (t < 0 || t >= n_vocab) {
+                return false;
+            }
+        }
+        return true;
+    }
+
+    // encode and decode the image chunk
+    int32_t process_chunk(
+                llama_context * ctx,
+                mtmd_context * mctx,
+                llama_pos n_past,
+                int32_t seq_id,
+                llama_pos & n_pos_out) {
+        auto it = map_pos_to_image.find(n_past);
+        if (it == map_pos_to_image.end()) {
+            throw std::runtime_error("Chunk not found");
+        }
+     //   SRV_INF("%s\n", "processing image...");
+        int32_t n_batch = llama_n_batch(ctx);
+        int64_t t0 = ggml_time_ms();
+        llama_pos new_n_past = n_past;
+        int32_t result = mtmd_helper_eval_chunk_single(mctx, ctx,
+            it->second.get(), // chunk
+            n_past,
+            seq_id,
+            n_batch,
+            true, // logits last
+            &new_n_past);
+        //SRV_INF("image processed in %" PRId64 " ms\n", ggml_time_ms() - t0);
+        if (result != 0) {
+            LOG_ERR("mtmd_helper_eval failed with status %d", result);
+            n_pos_out = n_past;
+            return result;
+        }
+        n_pos_out = new_n_past;
+        return 0;
+    }
+};
+
+// Computes FNV-1a hash of the data
+static std::string fnv_hash(const uint8_t * data, size_t len) {
+    const uint64_t fnv_prime = 0x100000001b3ULL;
+    uint64_t hash = 0xcbf29ce484222325ULL;
+
+    for (size_t i = 0; i < len; ++i) {
+        hash ^= data[i];
+        hash *= fnv_prime;
+    }
+    return std::to_string(hash);
 }

backend/go/image/stablediffusion-ggml/Makefile

@@ -8,12 +8,19 @@ ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
 # keep standard at C11 and C++11
 CXXFLAGS = -I. -I$(INCLUDE_PATH)/../../../../sources/stablediffusion-ggml.cpp/thirdparty -I$(INCLUDE_PATH)/../../../../sources/stablediffusion-ggml.cpp/ggml/include -I$(INCLUDE_PATH)/../../../../sources/stablediffusion-ggml.cpp -O3 -DNDEBUG -std=c++17 -fPIC
 
+GOCMD?=go
+CGO_LDFLAGS?=
+# Avoid parent make file overwriting CGO_LDFLAGS which is needed for hipblas
+CGO_LDFLAGS_SYCL=
+GO_TAGS?=
+LD_FLAGS?=
+
 # Disable Shared libs as we are linking on static gRPC and we can't mix shared and static
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
 
 # If build type is cublas, then we set -DGGML_CUDA=ON to CMAKE_ARGS automatically
 ifeq ($(BUILD_TYPE),cublas)
-	CMAKE_ARGS+=-DGGML_CUDA=ON
+	CMAKE_ARGS+=-DSD_CUDA=ON
 # If build type is openblas then we set -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
 # to CMAKE_ARGS automatically
 else ifeq ($(BUILD_TYPE),openblas)
@@ -23,29 +30,48 @@ else ifeq ($(BUILD_TYPE),clblas)
 	CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
 # If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++
 else ifeq ($(BUILD_TYPE),hipblas)
-	CMAKE_ARGS+=-DGGML_HIP=ON
+	CMAKE_ARGS+=-DSD_HIPBLAS=ON
 # If it's OSX, DO NOT embed the metal library - -DGGML_METAL_EMBED_LIBRARY=ON requires further investigation
 # But if it's OSX without metal, disable it here
 else ifeq ($(OS),Darwin)
 	ifneq ($(BUILD_TYPE),metal)
-		CMAKE_ARGS+=-DGGML_METAL=OFF
+		CMAKE_ARGS+=-DSD_METAL=OFF
 	else
-		CMAKE_ARGS+=-DGGML_METAL=ON
+		CMAKE_ARGS+=-DSD_METAL=ON
 		CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
 		TARGET+=--target ggml-metal
 	endif
 endif
 
-# ifeq ($(BUILD_TYPE),sycl_f16)
+ifeq ($(BUILD_TYPE),sycl_f16)
-# 	CMAKE_ARGS+=-DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON -DSD_SYCL=ON -DGGML_SYCL_F16=ON
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
-# endif
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx \
+		-DSD_SYCL=ON \
+		-DGGML_SYCL_F16=ON
+	CC=icx
+	CXX=icpx
+	CGO_LDFLAGS_SYCL += -fsycl -L${DNNLROOT}/lib -ldnnl ${MKLROOT}/lib/intel64/libmkl_sycl.a -fiopenmp -fopenmp-targets=spir64 -lOpenCL
+	CGO_LDFLAGS_SYCL += $(shell pkg-config --libs mkl-static-lp64-gomp)
+	CGO_CXXFLAGS += -fiopenmp -fopenmp-targets=spir64
+	CGO_CXXFLAGS += $(shell pkg-config --cflags mkl-static-lp64-gomp )
+endif
 
-# ifeq ($(BUILD_TYPE),sycl_f32)
+ifeq ($(BUILD_TYPE),sycl_f32)
-# 	CMAKE_ARGS+=-DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DSD_SYCL=ON
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
-# endif
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx \
+		-DSD_SYCL=ON
+	CC=icx
+	CXX=icpx
+	CGO_LDFLAGS_SYCL += -fsycl -L${DNNLROOT}/lib -ldnnl ${MKLROOT}/lib/intel64/libmkl_sycl.a -fiopenmp -fopenmp-targets=spir64 -lOpenCL
+	CGO_LDFLAGS_SYCL += $(shell pkg-config --libs mkl-static-lp64-gomp)
+	CGO_CXXFLAGS += -fiopenmp -fopenmp-targets=spir64
+	CGO_CXXFLAGS += $(shell pkg-config --cflags mkl-static-lp64-gomp )
+endif
 
 # warnings
-CXXFLAGS += -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function
+# CXXFLAGS += -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function
 
 # Find all .a archives in ARCHIVE_DIR
 # (ggml can have different backends cpu, cuda, etc., each backend generates a .a archive)
@@ -86,11 +112,24 @@ endif
 	$(MAKE) $(COMBINED_LIB)
 
 gosd.o:
+ifneq (,$(findstring sycl,$(BUILD_TYPE)))
+	+bash -c "source $(ONEAPI_VARS); \
+	$(CXX) $(CXXFLAGS) gosd.cpp -o gosd.o -c"
+else
 	$(CXX) $(CXXFLAGS) gosd.cpp -o gosd.o -c
+endif
 
 libsd.a: gosd.o
 	cp $(INCLUDE_PATH)/build/libstable-diffusion.a ./libsd.a
 	$(AR) rcs libsd.a gosd.o
 
+stablediffusion-ggml:
+	CGO_LDFLAGS="$(CGO_LDFLAGS) $(CGO_LDFLAGS_SYCL)" C_INCLUDE_PATH="$(INCLUDE_PATH)" LIBRARY_PATH="$(LIBRARY_PATH)" \
+	CC="$(CC)" CXX="$(CXX)" CGO_CXXFLAGS="$(CGO_CXXFLAGS)" \
+	$(GOCMD) build -ldflags "$(LD_FLAGS)" -tags "$(GO_TAGS)" -o ../../../../backend-assets/grpc/stablediffusion-ggml ./
+ifneq ($(UPX),)
+	$(UPX) ../../../../backend-assets/grpc/stablediffusion-ggml
+endif
+
 clean:
 	rm -rf gosd.o libsd.a build $(COMBINED_LIB)

backend/go/image/stablediffusion-ggml/gosd.cpp

@@ -35,6 +35,8 @@ const char* sample_method_str[] = {
     "ipndm",
     "ipndm_v",
     "lcm",
+    "ddim_trailing",
+    "tcd",
 };
 
 // Names of the sigma schedule overrides, same order as sample_schedule in stable-diffusion.h
@@ -173,6 +175,7 @@ int gen_image(char *text, char *negativeText, int width, int height, int steps,
                             -1, //clip_skip
                             cfg_scale, // sfg_scale
                             3.5f,
+			    0, // eta
                             width,
                             height,
                             sample_method, 

backend/go/image/stablediffusion/main.go

@@ -1,21 +0,0 @@
-package main
-
-// Note: this is started internally by LocalAI and a server is allocated for each model
-
-import (
-	"flag"
-
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
-)
-
-var (
-	addr = flag.String("addr", "localhost:50051", "the address to connect to")
-)
-
-func main() {
-	flag.Parse()
-
-	if err := grpc.StartServer(*addr, &Image{}); err != nil {
-		panic(err)
-	}
-}

backend/go/image/stablediffusion/stablediffusion.go

@@ -1,33 +0,0 @@
-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"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/stablediffusion"
-)
-
-type Image struct {
-	base.SingleThread
-	stablediffusion *stablediffusion.StableDiffusion
-}
-
-func (image *Image) Load(opts *pb.ModelOptions) error {
-	var err error
-	// Note: the Model here is a path to a directory containing the model files
-	image.stablediffusion, err = stablediffusion.New(opts.ModelFile)
-	return err
-}
-
-func (image *Image) GenerateImage(opts *pb.GenerateImageRequest) error {
-	return image.stablediffusion.GenerateImage(
-		int(opts.Height),
-		int(opts.Width),
-		int(opts.Mode),
-		int(opts.Step),
-		int(opts.Seed),
-		opts.PositivePrompt,
-		opts.NegativePrompt,
-		opts.Dst)
-}

backend/go/image/tinydream/main.go

@@ -1,21 +0,0 @@
-package main
-
-// Note: this is started internally by LocalAI and a server is allocated for each model
-
-import (
-	"flag"
-
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
-)
-
-var (
-	addr = flag.String("addr", "localhost:50051", "the address to connect to")
-)
-
-func main() {
-	flag.Parse()
-
-	if err := grpc.StartServer(*addr, &Image{}); err != nil {
-		panic(err)
-	}
-}

backend/go/image/tinydream/tinydream.go

@@ -1,32 +0,0 @@
-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"
-	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
-	"github.com/mudler/LocalAI/pkg/tinydream"
-)
-
-type Image struct {
-	base.SingleThread
-	tinydream *tinydream.TinyDream
-}
-
-func (image *Image) Load(opts *pb.ModelOptions) error {
-	var err error
-	// Note: the Model here is a path to a directory containing the model files
-	image.tinydream, err = tinydream.New(opts.ModelFile)
-	return err
-}
-
-func (image *Image) GenerateImage(opts *pb.GenerateImageRequest) error {
-	return image.tinydream.GenerateImage(
-		int(opts.Height),
-		int(opts.Width),
-		int(opts.Step),
-		int(opts.Seed),
-		opts.PositivePrompt,
-		opts.NegativePrompt,
-		opts.Dst)
-}

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

@@ -1,204 +0,0 @@
-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 (
-	"fmt"
-
-	"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 {
-	base.SingleThread
-
-	llama *llama.LLama
-}
-
-func (llm *LLM) Load(opts *pb.ModelOptions) error {
-	ropeFreqBase := float32(10000)
-	ropeFreqScale := float32(1)
-
-	if opts.RopeFreqBase != 0 {
-		ropeFreqBase = opts.RopeFreqBase
-	}
-	if opts.RopeFreqScale != 0 {
-		ropeFreqScale = opts.RopeFreqScale
-	}
-
-	llamaOpts := []llama.ModelOption{
-		llama.WithRopeFreqBase(ropeFreqBase),
-		llama.WithRopeFreqScale(ropeFreqScale),
-	}
-
-	if opts.NGQA != 0 {
-		llamaOpts = append(llamaOpts, llama.WithGQA(int(opts.NGQA)))
-	}
-
-	if opts.RMSNormEps != 0 {
-		llamaOpts = append(llamaOpts, llama.WithRMSNormEPS(opts.RMSNormEps))
-	}
-
-	if opts.ContextSize != 0 {
-		llamaOpts = append(llamaOpts, llama.SetContext(int(opts.ContextSize)))
-	}
-	if opts.F16Memory {
-		llamaOpts = append(llamaOpts, llama.EnableF16Memory)
-	}
-	if opts.Embeddings {
-		llamaOpts = append(llamaOpts, llama.EnableEmbeddings)
-	}
-	if opts.NGPULayers != 0 {
-		llamaOpts = append(llamaOpts, llama.SetGPULayers(int(opts.NGPULayers)))
-	}
-
-	llamaOpts = append(llamaOpts, llama.SetMMap(opts.MMap))
-	llamaOpts = append(llamaOpts, llama.SetMainGPU(opts.MainGPU))
-	llamaOpts = append(llamaOpts, llama.SetTensorSplit(opts.TensorSplit))
-	if opts.NBatch != 0 {
-		llamaOpts = append(llamaOpts, llama.SetNBatch(int(opts.NBatch)))
-	} else {
-		llamaOpts = append(llamaOpts, llama.SetNBatch(512))
-	}
-
-	if opts.NUMA {
-		llamaOpts = append(llamaOpts, llama.EnableNUMA)
-	}
-
-	if opts.LowVRAM {
-		llamaOpts = append(llamaOpts, llama.EnabelLowVRAM)
-	}
-
-	model, err := llama.New(opts.ModelFile, llamaOpts...)
-	llm.llama = model
-
-	return err
-}
-
-func buildPredictOptions(opts *pb.PredictOptions) []llama.PredictOption {
-	ropeFreqBase := float32(10000)
-	ropeFreqScale := float32(1)
-
-	if opts.RopeFreqBase != 0 {
-		ropeFreqBase = opts.RopeFreqBase
-	}
-	if opts.RopeFreqScale != 0 {
-		ropeFreqScale = opts.RopeFreqScale
-	}
-	predictOptions := []llama.PredictOption{
-		llama.SetTemperature(opts.Temperature),
-		llama.SetTopP(opts.TopP),
-		llama.SetTopK(int(opts.TopK)),
-		llama.SetTokens(int(opts.Tokens)),
-		llama.SetThreads(int(opts.Threads)),
-		llama.WithGrammar(opts.Grammar),
-		llama.SetRopeFreqBase(ropeFreqBase),
-		llama.SetRopeFreqScale(ropeFreqScale),
-		llama.SetNegativePromptScale(opts.NegativePromptScale),
-		llama.SetNegativePrompt(opts.NegativePrompt),
-	}
-
-	if opts.PromptCacheAll {
-		predictOptions = append(predictOptions, llama.EnablePromptCacheAll)
-	}
-
-	if opts.PromptCacheRO {
-		predictOptions = append(predictOptions, llama.EnablePromptCacheRO)
-	}
-
-	// Expected absolute path
-	if opts.PromptCachePath != "" {
-		predictOptions = append(predictOptions, llama.SetPathPromptCache(opts.PromptCachePath))
-	}
-
-	if opts.Mirostat != 0 {
-		predictOptions = append(predictOptions, llama.SetMirostat(int(opts.Mirostat)))
-	}
-
-	if opts.MirostatETA != 0 {
-		predictOptions = append(predictOptions, llama.SetMirostatETA(opts.MirostatETA))
-	}
-
-	if opts.MirostatTAU != 0 {
-		predictOptions = append(predictOptions, llama.SetMirostatTAU(opts.MirostatTAU))
-	}
-
-	if opts.Debug {
-		predictOptions = append(predictOptions, llama.Debug)
-	}
-
-	predictOptions = append(predictOptions, llama.SetStopWords(opts.StopPrompts...))
-
-	if opts.PresencePenalty != 0 {
-		predictOptions = append(predictOptions, llama.SetPenalty(opts.PresencePenalty))
-	}
-
-	if opts.NKeep != 0 {
-		predictOptions = append(predictOptions, llama.SetNKeep(int(opts.NKeep)))
-	}
-
-	if opts.Batch != 0 {
-		predictOptions = append(predictOptions, llama.SetBatch(int(opts.Batch)))
-	}
-
-	if opts.F16KV {
-		predictOptions = append(predictOptions, llama.EnableF16KV)
-	}
-
-	if opts.IgnoreEOS {
-		predictOptions = append(predictOptions, llama.IgnoreEOS)
-	}
-
-	if opts.Seed != 0 {
-		predictOptions = append(predictOptions, llama.SetSeed(int(opts.Seed)))
-	}
-
-	//predictOptions = append(predictOptions, llama.SetLogitBias(c.Seed))
-
-	predictOptions = append(predictOptions, llama.SetFrequencyPenalty(opts.FrequencyPenalty))
-	predictOptions = append(predictOptions, llama.SetMlock(opts.MLock))
-	predictOptions = append(predictOptions, llama.SetMemoryMap(opts.MMap))
-	predictOptions = append(predictOptions, llama.SetPredictionMainGPU(opts.MainGPU))
-	predictOptions = append(predictOptions, llama.SetPredictionTensorSplit(opts.TensorSplit))
-	predictOptions = append(predictOptions, llama.SetTailFreeSamplingZ(opts.TailFreeSamplingZ))
-	predictOptions = append(predictOptions, llama.SetTypicalP(opts.TypicalP))
-	return predictOptions
-}
-
-func (llm *LLM) Predict(opts *pb.PredictOptions) (string, error) {
-	return llm.llama.Predict(opts.Prompt, buildPredictOptions(opts)...)
-}
-
-func (llm *LLM) PredictStream(opts *pb.PredictOptions, results chan string) error {
-	predictOptions := buildPredictOptions(opts)
-
-	predictOptions = append(predictOptions, llama.SetTokenCallback(func(token string) bool {
-		results <- token
-		return true
-	}))
-
-	go func() {
-		_, err := llm.llama.Predict(opts.Prompt, predictOptions...)
-		if err != nil {
-			fmt.Println("err: ", err)
-		}
-		close(results)
-	}()
-
-	return nil
-}
-
-func (llm *LLM) Embeddings(opts *pb.PredictOptions) ([]float32, error) {
-	predictOptions := buildPredictOptions(opts)
-
-	if len(opts.EmbeddingTokens) > 0 {
-		tokens := []int{}
-		for _, t := range opts.EmbeddingTokens {
-			tokens = append(tokens, int(t))
-		}
-		return llm.llama.TokenEmbeddings(tokens, predictOptions...)
-	}
-
-	return llm.llama.Embeddings(opts.Embeddings, predictOptions...)
-}

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

@@ -1,19 +0,0 @@
-package main
-
-import (
-	"flag"
-
-	grpc "github.com/mudler/LocalAI/pkg/grpc"
-)
-
-var (
-	addr = flag.String("addr", "localhost:50051", "the address to connect to")
-)
-
-func main() {
-	flag.Parse()
-
-	if err := grpc.StartServer(*addr, &LLM{}); err != nil {
-		panic(err)
-	}
-}

backend/go/stores/store.go

@@ -311,12 +311,16 @@ func (s *Store) StoresGet(opts *pb.StoresGetOptions) (pb.StoresGetResult, error)
 }
 
 func isNormalized(k []float32) bool {
-	var sum float32
+	var sum float64
+
 	for _, v := range k {
-		sum += v
+		v64 := float64(v)
+		sum += v64*v64
 	}
 
-	return sum == 1.0
+	s := math.Sqrt(sum)
+
+	return s >= 0.99 && s <= 1.01
 }
 
 // TODO: This we could replace with handwritten SIMD code
@@ -328,7 +332,7 @@ func normalizedCosineSimilarity(k1, k2 []float32) float32 {
 		dot += k1[i] * k2[i]
 	}
 
-	assert(dot >= -1 && dot <= 1, fmt.Sprintf("dot = %f", dot))
+	assert(dot >= -1.01 && dot <= 1.01, fmt.Sprintf("dot = %f", dot))
 
 	// 2.0 * (1.0 - dot) would be the Euclidean distance
 	return dot
@@ -418,7 +422,7 @@ func cosineSimilarity(k1, k2 []float32, mag1 float64) float32 {
 
 	sim := float32(dot / (mag1 * math.Sqrt(mag2)))
 
-	assert(sim >= -1 && sim <= 1, fmt.Sprintf("sim = %f", sim))
+	assert(sim >= -1.01 && sim <= 1.01, fmt.Sprintf("sim = %f", sim))
 
 	return sim
 }

backend/go/transcribe/whisper/whisper.go

@@ -74,7 +74,7 @@ func (sd *Whisper) AudioTranscription(opts *pb.TranscriptRequest) (pb.Transcript
 		context.SetTranslate(true)
 	}
 
-	if err := context.Process(data, nil, nil); err != nil {
+	if err := context.Process(data, nil, nil, nil); err != nil {
 		return pb.TranscriptResult{}, err
 	}
 

backend/python/autogptq/README.md

@@ -1,5 +0,0 @@
-# Creating a separate environment for the autogptq project
-
-```
-make autogptq
-```

backend/python/autogptq/backend.py

@@ -1,153 +0,0 @@
-#!/usr/bin/env python3
-from concurrent import futures
-import argparse
-import signal
-import sys
-import os
-import time
-import base64
-
-import grpc
-import backend_pb2
-import backend_pb2_grpc
-
-from auto_gptq import AutoGPTQForCausalLM
-from transformers import AutoTokenizer, AutoModelForCausalLM
-from transformers import TextGenerationPipeline
-
-_ONE_DAY_IN_SECONDS = 60 * 60 * 24
-
-# If MAX_WORKERS are specified in the environment use it, otherwise default to 1
-MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
-
-# Implement the BackendServicer class with the service methods
-class BackendServicer(backend_pb2_grpc.BackendServicer):
-    def Health(self, request, context):
-        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
-    def LoadModel(self, request, context):
-        try:
-            device = "cuda:0"
-            if request.Device != "":
-                device = request.Device
-
-            # support loading local model files
-            model_path = os.path.join(os.environ.get('MODELS_PATH', './'), request.Model)
-            tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True, trust_remote_code=request.TrustRemoteCode)
-
-            # support model `Qwen/Qwen-VL-Chat-Int4`
-            if "qwen-vl" in request.Model.lower():
-                self.model_name = "Qwen-VL-Chat"
-                model = AutoModelForCausalLM.from_pretrained(model_path, 
-                    trust_remote_code=request.TrustRemoteCode,
-                    device_map="auto").eval()
-            else:
-                model = AutoGPTQForCausalLM.from_quantized(model_path,
-                    model_basename=request.ModelBaseName,
-                    use_safetensors=True,
-                    trust_remote_code=request.TrustRemoteCode,
-                    device=device,
-                    use_triton=request.UseTriton,
-                    quantize_config=None)
-            
-            self.model = model
-            self.tokenizer = tokenizer
-        except Exception as err:
-            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
-        return backend_pb2.Result(message="Model loaded successfully", success=True)
-
-    def Predict(self, request, context):
-        penalty = 1.0
-        if request.Penalty != 0.0:
-            penalty = request.Penalty
-        tokens = 512
-        if request.Tokens != 0:
-            tokens = request.Tokens
-        top_p = 0.95
-        if request.TopP != 0.0:
-            top_p = request.TopP
-
-        
-        prompt_images = self.recompile_vl_prompt(request)
-        compiled_prompt = prompt_images[0]
-        print(f"Prompt: {compiled_prompt}", file=sys.stderr)
-
-        # Implement Predict RPC
-        pipeline = TextGenerationPipeline(
-            model=self.model, 
-            tokenizer=self.tokenizer,
-            max_new_tokens=tokens,
-            temperature=request.Temperature,
-            top_p=top_p,
-            repetition_penalty=penalty,
-            )
-        t = pipeline(compiled_prompt)[0]["generated_text"]
-        print(f"generated_text: {t}", file=sys.stderr)
-        
-        if compiled_prompt in t:
-            t = t.replace(compiled_prompt, "")
-        # house keeping. Remove the image files from /tmp folder
-        for img_path in prompt_images[1]:
-            try:
-                os.remove(img_path)
-            except Exception as e:
-                print(f"Error removing image file: {img_path}, {e}", file=sys.stderr)
-
-        return backend_pb2.Result(message=bytes(t, encoding='utf-8'))
-
-    def PredictStream(self, request, context):
-        # Implement PredictStream RPC
-        #for reply in some_data_generator():
-        #    yield reply
-        # Not implemented yet
-        return self.Predict(request, context)
-
-    def recompile_vl_prompt(self, request):
-        prompt = request.Prompt
-        image_paths = []
-
-        if "qwen-vl" in self.model_name.lower():
-            # request.Images is an array which contains base64 encoded images. Iterate the request.Images array, decode and save each image to /tmp folder with a random filename.
-            # Then, save the image file paths to an array "image_paths".
-            # read "request.Prompt", replace "[img-%d]" with the image file paths in the order they appear in "image_paths". Save the new prompt to "prompt".
-            for i, img in enumerate(request.Images):
-                timestamp = str(int(time.time() * 1000))  # Generate timestamp
-                img_path = f"/tmp/vl-{timestamp}.jpg"  # Use timestamp in filename
-                with open(img_path, "wb") as f:
-                    f.write(base64.b64decode(img))
-                image_paths.append(img_path)
-                prompt = prompt.replace(f"[img-{i}]", "<img>" + img_path + "</img>,")
-        else:
-            prompt = request.Prompt
-        return (prompt, image_paths)
-
-def serve(address):
-    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
-    backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
-    server.add_insecure_port(address)
-    server.start()
-    print("Server started. Listening on: " + address, file=sys.stderr)
-
-    # Define the signal handler function
-    def signal_handler(sig, frame):
-        print("Received termination signal. Shutting down...")
-        server.stop(0)
-        sys.exit(0)
-
-    # Set the signal handlers for SIGINT and SIGTERM
-    signal.signal(signal.SIGINT, signal_handler)
-    signal.signal(signal.SIGTERM, signal_handler)
-
-    try:
-        while True:
-            time.sleep(_ONE_DAY_IN_SECONDS)
-    except KeyboardInterrupt:
-        server.stop(0)
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Run the gRPC server.")
-    parser.add_argument(
-        "--addr", default="localhost:50051", help="The address to bind the server to."
-    )
-    args = parser.parse_args()
-
-    serve(args.addr)

backend/python/autogptq/requirements-cublas11.txt

@@ -1,2 +0,0 @@
---extra-index-url https://download.pytorch.org/whl/cu118
-torch==2.4.1+cu118

backend/python/autogptq/requirements-cublas12.txt

@@ -1 +0,0 @@
-torch==2.4.1

backend/python/autogptq/requirements.txt

@@ -1,6 +0,0 @@
-accelerate
-auto-gptq==0.7.1
-grpcio==1.69.0
-protobuf
-certifi
-transformers

backend/python/bark/backend.py

@@ -61,7 +61,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         return backend_pb2.Result(success=True)
 
 def serve(address):
-    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
+    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
+        options=[
+            ('grpc.max_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_send_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_receive_message_length', 50 * 1024 * 1024),  # 50MB
+        ])
     backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
     server.add_insecure_port(address)
     server.start()

backend/python/bark/requirements.txt

@@ -1,4 +1,4 @@
 bark==0.1.5
-grpcio==1.69.0
+grpcio==1.72.0
 protobuf
 certifi

backend/python/common/template/requirements.txt

@@ -1,3 +1,3 @@
-grpcio==1.69.0
+grpcio==1.72.0
 protobuf
 grpcio-tools

backend/python/coqui/backend.py

@@ -86,7 +86,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         return backend_pb2.Result(success=True)
 
 def serve(address):
-    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
+    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
+        options=[
+            ('grpc.max_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_send_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_receive_message_length', 50 * 1024 * 1024),  # 50MB
+        ])
     backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
     server.add_insecure_port(address)
     server.start()

backend/python/coqui/requirements-cpu.txt

@@ -1,4 +1,4 @@
-transformers
+transformers==4.48.3
 accelerate
 torch==2.4.1
 coqui-tts

backend/python/coqui/requirements-cublas11.txt

@@ -1,6 +1,6 @@
 --extra-index-url https://download.pytorch.org/whl/cu118
 torch==2.4.1+cu118
 torchaudio==2.4.1+cu118
-transformers
+transformers==4.48.3
 accelerate
 coqui-tts

backend/python/coqui/requirements-cublas12.txt

@@ -1,5 +1,5 @@
 torch==2.4.1
 torchaudio==2.4.1
-transformers
+transformers==4.48.3
 accelerate
 coqui-tts

backend/python/coqui/requirements-hipblas.txt

@@ -1,6 +1,6 @@
 --extra-index-url https://download.pytorch.org/whl/rocm6.0
 torch==2.4.1+rocm6.0
 torchaudio==2.4.1+rocm6.0
-transformers
+transformers==4.48.3
 accelerate
 coqui-tts

backend/python/coqui/requirements-intel.txt

@@ -5,6 +5,6 @@ torchaudio==2.3.1+cxx11.abi
 oneccl_bind_pt==2.3.100+xpu
 optimum[openvino]
 setuptools
-transformers
+transformers==4.48.3
 accelerate
 coqui-tts

backend/python/coqui/requirements.txt

@@ -1,4 +1,4 @@
-grpcio==1.69.0
+grpcio==1.72.0
 protobuf
 certifi
 packaging==24.1

backend/python/diffusers/backend.py

@@ -19,7 +19,7 @@ import grpc
 
 from diffusers import SanaPipeline, StableDiffusion3Pipeline, StableDiffusionXLPipeline, StableDiffusionDepth2ImgPipeline, DPMSolverMultistepScheduler, StableDiffusionPipeline, DiffusionPipeline, \
     EulerAncestralDiscreteScheduler, FluxPipeline, FluxTransformer2DModel
-from diffusers import StableDiffusionImg2ImgPipeline, AutoPipelineForText2Image, ControlNetModel, StableVideoDiffusionPipeline
+from diffusers import StableDiffusionImg2ImgPipeline, AutoPipelineForText2Image, ControlNetModel, StableVideoDiffusionPipeline, Lumina2Text2ImgPipeline
 from diffusers.pipelines.stable_diffusion import safety_checker
 from diffusers.utils import load_image, export_to_video
 from compel import Compel, ReturnedEmbeddingsType
@@ -159,6 +159,22 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 torchType = torch.float16
                 variant = "fp16"
 
+            options = request.Options
+
+            # empty dict
+            self.options = {}
+
+            # The options are a list of strings in this form optname:optvalue
+            # We are storing all the options in a dict so we can use it later when
+            # generating the images
+            for opt in options:
+                if ":" not in opt:
+                    continue
+                key, value = opt.split(":")
+                self.options[key] = value
+
+            print(f"Options: {self.options}", file=sys.stderr)
+
             local = False
             modelFile = request.Model
 
@@ -275,6 +291,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 
                     if request.LowVRAM:
                         self.pipe.enable_model_cpu_offload()
+            elif request.PipelineType == "Lumina2Text2ImgPipeline":
+                self.pipe = Lumina2Text2ImgPipeline.from_pretrained(
+                    request.Model,
+                    torch_dtype=torch.bfloat16)
+                if request.LowVRAM:
+                    self.pipe.enable_model_cpu_offload()
             elif request.PipelineType == "SanaPipeline":
                 self.pipe = SanaPipeline.from_pretrained(
                     request.Model,
@@ -441,6 +463,9 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         # create a dictionary of parameters by using the keys from EnableParameters and the values from defaults
         kwargs = {key: options.get(key) for key in keys if key in options}
 
+        # populate kwargs from self.options.
+        kwargs.update(self.options)
+
         # Set seed
         if request.seed > 0:
             kwargs["generator"] = torch.Generator(device=self.device).manual_seed(
@@ -501,7 +526,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 
 
 def serve(address):
-    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
+    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
+        options=[
+            ('grpc.max_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_send_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_receive_message_length', 50 * 1024 * 1024),  # 50MB
+        ])
     backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
     server.add_insecure_port(address)
     server.start()

backend/python/diffusers/requirements.txt

@@ -1,5 +1,5 @@
 setuptools
-grpcio==1.69.0
+grpcio==1.72.0
 pillow
 protobuf
 certifi

backend/python/exllama2/backend.py

@@ -105,7 +105,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 
 
 def serve(address):
-    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
+    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
+        options=[
+            ('grpc.max_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_send_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_receive_message_length', 50 * 1024 * 1024),  # 50MB
+        ])
     backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
     server.add_insecure_port(address)
     server.start()

backend/python/exllama2/requirements.txt

@@ -1,4 +1,4 @@
-grpcio==1.69.0
+grpcio==1.72.0
 protobuf
 certifi
 wheel

backend/python/faster-whisper/Makefile

@@ -1,6 +1,9 @@
-.PHONY: autogptq
+.DEFAULT_GOAL := install
-autogptq: protogen
+
+.PHONY: install
+install:
 	bash install.sh
+	$(MAKE) protogen
 
 .PHONY: protogen
 protogen: backend_pb2_grpc.py backend_pb2.py
@@ -10,7 +13,7 @@ protogen-clean:
 	$(RM) backend_pb2_grpc.py backend_pb2.py
 
 backend_pb2_grpc.py backend_pb2.py:
-	python3 -m grpc_tools.protoc -I../.. --python_out=. --grpc_python_out=. backend.proto
+	bash protogen.sh
 
 .PHONY: clean
 clean: protogen-clean

backend/python/faster-whisper/backend.py

@@ -1,88 +1,73 @@
 #!/usr/bin/env python3
 """
-Extra gRPC server for HuggingFace SentenceTransformer models.
+This is an extra gRPC server of LocalAI for Bark TTS
 """
 from concurrent import futures
-
+import time
 import argparse
 import signal
 import sys
 import os
-
-import time
 import backend_pb2
 import backend_pb2_grpc
 
+from faster_whisper import WhisperModel
+
 import grpc
 
-from sentence_transformers import SentenceTransformer
 
 _ONE_DAY_IN_SECONDS = 60 * 60 * 24
 
 # If MAX_WORKERS are specified in the environment use it, otherwise default to 1
 MAX_WORKERS = int(os.environ.get('PYTHON_GRPC_MAX_WORKERS', '1'))
+COQUI_LANGUAGE = os.environ.get('COQUI_LANGUAGE', None)
 
 # Implement the BackendServicer class with the service methods
 class BackendServicer(backend_pb2_grpc.BackendServicer):
     """
-    A gRPC servicer for the backend service.
+    BackendServicer is the class that implements the gRPC service
-
-    This class implements the gRPC methods for the backend service, including Health, LoadModel, and Embedding.
     """
     def Health(self, request, context):
-        """
-        A gRPC method that returns the health status of the backend service.
-
-        Args:
-            request: A HealthRequest object that contains the request parameters.
-            context: A grpc.ServicerContext object that provides information about the RPC.
-
-        Returns:
-            A Reply object that contains the health status of the backend service.
-        """
         return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
-
     def LoadModel(self, request, context):
-        """
+        device = "cpu"
-        A gRPC method that loads a model into memory.
+        # Get device
+        # device = "cuda" if request.CUDA else "cpu"
+        if request.CUDA:
+            device = "cuda"
 
-        Args:
-            request: A LoadModelRequest object that contains the request parameters.
-            context: A grpc.ServicerContext object that provides information about the RPC.
-
-        Returns:
-            A Result object that contains the result of the LoadModel operation.
-        """
-        model_name = request.Model
         try:
-            self.model = SentenceTransformer(model_name, trust_remote_code=request.TrustRemoteCode)
+            print("Preparing models, please wait", file=sys.stderr)
+            self.model = WhisperModel(request.Model, device=device, compute_type="float16")
         except Exception as err:
             return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
-
         # Implement your logic here for the LoadModel service
         # Replace this with your desired response
         return backend_pb2.Result(message="Model loaded successfully", success=True)
 
-    def Embedding(self, request, context):
+    def AudioTranscription(self, request, context):
-        """
+        resultSegments = []
-        A gRPC method that calculates embeddings for a given sentence.
+        text = ""
-
+        try:
-        Args:
+            segments, info = self.model.transcribe(request.dst, beam_size=5, condition_on_previous_text=False)
-            request: An EmbeddingRequest object that contains the request parameters.
+            id = 0
-            context: A grpc.ServicerContext object that provides information about the RPC.
+            for segment in segments:
-
+                print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
-        Returns:
+                resultSegments.append(backend_pb2.TranscriptSegment(id=id, start=segment.start, end=segment.end, text=segment.text))
-            An EmbeddingResult object that contains the calculated embeddings.
+                text += segment.text
-        """
+                id += 1            
-        # Implement your logic here for the Embedding service
+        except Exception as err:
-        # Replace this with your desired response
+            print(f"Unexpected {err=}, {type(err)=}", file=sys.stderr)
-        print("Calculated embeddings for: " + request.Embeddings, file=sys.stderr)
-        sentence_embeddings = self.model.encode(request.Embeddings)
-        return backend_pb2.EmbeddingResult(embeddings=sentence_embeddings)
 
+        return backend_pb2.TranscriptResult(segments=resultSegments, text=text)
 
 def serve(address):
-    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS))
+    server = grpc.server(futures.ThreadPoolExecutor(max_workers=MAX_WORKERS),
+        options=[
+            ('grpc.max_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_send_message_length', 50 * 1024 * 1024),  # 50MB
+            ('grpc.max_receive_message_length', 50 * 1024 * 1024),  # 50MB
+        ])
     backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
     server.add_insecure_port(address)
     server.start()