feat(quantization): add quantization backend

.github/workflows/backend.yml

@@ -131,6 +131,19 @@ jobs:
             dockerfile: "./backend/Dockerfile.python"
             context: "./"
             ubuntu-version: '2404'
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64,linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-cpu-llama-cpp-quantization'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:24.04"
+            skip-drivers: 'true'
+            backend: "llama-cpp-quantization"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./"
+            ubuntu-version: '2404'
           - build-type: ''
             cuda-major-version: ""
             cuda-minor-version: ""
@@ -2412,6 +2425,9 @@ jobs:
             tag-suffix: "-metal-darwin-arm64-local-store"
             build-type: "metal"
             lang: "go"
+          - backend: "llama-cpp-quantization"
+            tag-suffix: "-metal-darwin-arm64-llama-cpp-quantization"
+            build-type: "mps"
     with:
       backend: ${{ matrix.backend }}
       build-type: ${{ matrix.build-type }}

.github/workflows/test-extra.yml

@@ -383,6 +383,33 @@ jobs:
         run: |
           make --jobs=5 --output-sync=target -C backend/python/voxcpm
           make --jobs=5 --output-sync=target -C backend/python/voxcpm test
+  tests-llama-cpp-quantization:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      - name: Clone
+        uses: actions/checkout@v6
+        with:
+          submodules: true
+      - name: Dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential cmake curl git python3-pip
+          # Install UV
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          pip install --user --no-cache-dir grpcio-tools==1.64.1
+      - name: Build llama-quantize from llama.cpp
+        run: |
+          git clone --depth 1 https://github.com/ggml-org/llama.cpp.git /tmp/llama.cpp
+          cmake -B /tmp/llama.cpp/build -S /tmp/llama.cpp -DGGML_NATIVE=OFF
+          cmake --build /tmp/llama.cpp/build --target llama-quantize -j$(nproc)
+          sudo cp /tmp/llama.cpp/build/bin/llama-quantize /usr/local/bin/
+      - name: Install backend
+        run: |
+          make --jobs=5 --output-sync=target -C backend/python/llama-cpp-quantization
+      - name: Test llama-cpp-quantization
+        run: |
+          make --jobs=5 --output-sync=target -C backend/python/llama-cpp-quantization test
   tests-acestep-cpp:
     runs-on: ubuntu-latest
     steps:

Makefile

@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -575,6 +575,7 @@ BACKEND_WHISPERX = whisperx|python|.|false|true
 BACKEND_ACE_STEP = ace-step|python|.|false|true
 BACKEND_MLX_DISTRIBUTED = mlx-distributed|python|./|false|true
 BACKEND_TRL = trl|python|.|false|true
+BACKEND_LLAMA_CPP_QUANTIZATION = llama-cpp-quantization|python|.|false|true
 
 # Helper function to build docker image for a backend
 # Usage: $(call docker-build-backend,BACKEND_NAME,DOCKERFILE_TYPE,BUILD_CONTEXT,PROGRESS_FLAG,NEEDS_BACKEND_ARG)
@@ -633,12 +634,13 @@ $(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_ACESTEP_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_MLX_DISTRIBUTED)))
 $(eval $(call generate-docker-build-target,$(BACKEND_TRL)))
+$(eval $(call generate-docker-build-target,$(BACKEND_LLAMA_CPP_QUANTIZATION)))
 
 # Pattern rule for docker-save targets
 docker-save-%: backend-images
 	docker save local-ai-backend:$* -o backend-images/$*.tar
 
-docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl
+docker-build-backends: docker-build-llama-cpp docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization
 
 ########################################################
 ### Mock Backend for E2E Tests

backend/backend.proto

@@ -46,6 +46,11 @@ service Backend {
   rpc StopFineTune(FineTuneStopRequest) returns (Result) {}
   rpc ListCheckpoints(ListCheckpointsRequest) returns (ListCheckpointsResponse) {}
   rpc ExportModel(ExportModelRequest) returns (Result) {}
+
+  // Quantization RPCs
+  rpc StartQuantization(QuantizationRequest) returns (QuantizationJobResult) {}
+  rpc QuantizationProgress(QuantizationProgressRequest) returns (stream QuantizationProgressUpdate) {}
+  rpc StopQuantization(QuantizationStopRequest) returns (Result) {}
 }
 
 // Define the empty request
@@ -637,3 +642,36 @@ message ExportModelRequest {
   string model = 5;                   // base model name (for merge operations)
   map<string, string> extra_options = 6;
 }
+
+// Quantization messages
+
+message QuantizationRequest {
+  string model = 1;                      // HF model name or local path
+  string quantization_type = 2;          // q4_k_m, q5_k_m, q8_0, f16, etc.
+  string output_dir = 3;                 // where to write output files
+  string job_id = 4;                     // client-assigned job ID
+  map<string, string> extra_options = 5; // hf_token, custom flags, etc.
+}
+
+message QuantizationJobResult {
+  string job_id = 1;
+  bool success = 2;
+  string message = 3;
+}
+
+message QuantizationProgressRequest {
+  string job_id = 1;
+}
+
+message QuantizationProgressUpdate {
+  string job_id = 1;
+  float progress_percent = 2;
+  string status = 3;                     // queued, downloading, converting, quantizing, completed, failed, stopped
+  string message = 4;
+  string output_file = 5;               // set when completed — path to the output GGUF file
+  map<string, float> extra_metrics = 6;  // e.g. file_size_mb, compression_ratio
+}
+
+message QuantizationStopRequest {
+  string job_id = 1;
+}

backend/index.yaml

@@ -118,7 +118,7 @@
   capabilities:
     nvidia: "cuda12-rfdetr"
     intel: "intel-rfdetr"
     #amd: "rocm-rfdetr"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr"
     metal: "metal-rfdetr"
     default: "cpu-rfdetr"
@@ -1522,7 +1522,7 @@
   capabilities:
     nvidia: "cuda12-rfdetr-development"
     intel: "intel-rfdetr-development"
     #amd: "rocm-rfdetr-development"
     nvidia-l4t: "nvidia-l4t-arm64-rfdetr-development"
     metal: "metal-rfdetr-development"
     default: "cpu-rfdetr-development"
@@ -3081,3 +3081,31 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-cublas-cuda13-trl"
   mirrors:
     - localai/localai-backends:master-cublas-cuda13-trl
+## llama.cpp quantization backend
+- &llama-cpp-quantization
+  name: "llama-cpp-quantization"
+  alias: "llama-cpp-quantization"
+  license: mit
+  icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
+  description: |
+    Model quantization backend using llama.cpp. Downloads HuggingFace models, converts them to GGUF format,
+    and quantizes them to various formats (q4_k_m, q5_k_m, q8_0, f16, etc.).
+  urls:
+    - https://github.com/ggml-org/llama.cpp
+  tags:
+    - quantization
+    - GGUF
+    - CPU
+  capabilities:
+    default: "cpu-llama-cpp-quantization"
+    metal: "metal-darwin-arm64-llama-cpp-quantization"
+- !!merge <<: *llama-cpp-quantization
+  name: "cpu-llama-cpp-quantization"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-llama-cpp-quantization"
+  mirrors:
+    - localai/localai-backends:latest-cpu-llama-cpp-quantization
+- !!merge <<: *llama-cpp-quantization
+  name: "metal-darwin-arm64-llama-cpp-quantization"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-llama-cpp-quantization"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-llama-cpp-quantization

backend/python/llama-cpp-quantization/Makefile

@@ -0,0 +1,26 @@
+# Version of llama.cpp to fetch convert_hf_to_gguf.py from
+LLAMA_CPP_CONVERT_VERSION ?= master
+
+.PHONY: llama-cpp-quantization
+llama-cpp-quantization:
+	LLAMA_CPP_CONVERT_VERSION=$(LLAMA_CPP_CONVERT_VERSION) bash install.sh
+
+.PHONY: run
+run: llama-cpp-quantization
+	@echo "Running llama-cpp-quantization..."
+	bash run.sh
+	@echo "llama-cpp-quantization run."
+
+.PHONY: test
+test: llama-cpp-quantization
+	@echo "Testing llama-cpp-quantization..."
+	bash test.sh
+	@echo "llama-cpp-quantization tested."
+
+.PHONY: protogen-clean
+protogen-clean:
+	$(RM) backend_pb2_grpc.py backend_pb2.py
+
+.PHONY: clean
+clean: protogen-clean
+	rm -rf venv __pycache__