chore: ⬆️ Update ggml-org/llama.cpp to be48528b068111304e4a0bb82c028558b5705f05 (#6012)

⬆️ Update ggml-org/llama.cpp

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

.github/workflows/backend.yml

@@ -87,6 +87,18 @@ jobs:
             backend: "diffusers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'l4t'
+            cuda-major-version: "12"
+            cuda-minor-version: "0"
+            platforms: 'linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-l4t-diffusers'
+            runs-on: 'ubuntu-24.04-arm'
+            base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+            skip-drivers: 'true'
+            backend: "diffusers"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           # CUDA 11 additional backends
           - build-type: 'cublas'
             cuda-major-version: "11"
@@ -313,7 +325,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-rocm-hipblas-transformers'
-            runs-on: 'ubuntu-latest'
+            runs-on: 'arc-runner-set'
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             skip-drivers: 'false'
             backend: "transformers"
@@ -325,7 +337,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-rocm-hipblas-diffusers'
-            runs-on: 'ubuntu-latest'
+            runs-on: 'arc-runner-set'
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             skip-drivers: 'false'
             backend: "diffusers"
@@ -338,7 +350,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-rocm-hipblas-kokoro'
-            runs-on: 'ubuntu-latest'
+            runs-on: 'arc-runner-set'
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             skip-drivers: 'false'
             backend: "kokoro"
@@ -374,7 +386,7 @@ jobs:
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-rocm-hipblas-bark'
-            runs-on: 'ubuntu-latest'
+            runs-on: 'arc-runner-set'
             base-image: "rocm/dev-ubuntu-22.04:6.1"
             skip-drivers: 'false'
             backend: "bark"
@@ -920,6 +932,19 @@ jobs:
           #   backend: "rfdetr"
           #   dockerfile: "./backend/Dockerfile.python"
           #   context: "./backend"
+          # kitten-tts
+          - build-type: ''
+            cuda-major-version: ""
+            cuda-minor-version: ""
+            platforms: 'linux/amd64,linux/arm64'
+            tag-latest: 'auto'
+            tag-suffix: '-kitten-tts'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "kitten-tts"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
   llama-cpp-darwin:
     runs-on: macOS-14
     strategy:
@@ -955,6 +980,7 @@ jobs:
           path: build/llama-cpp.tar
   llama-cpp-darwin-publish:
     needs: llama-cpp-darwin
+    if: github.event_name != 'pull_request'
     runs-on: ubuntu-latest
     steps:
       - name: Download llama-cpp.tar
@@ -1043,6 +1069,7 @@ jobs:
           name: llama-cpp-tar-x86
           path: build/llama-cpp.tar
   llama-cpp-darwin-x86-publish:
+    if: github.event_name != 'pull_request'
     needs: llama-cpp-darwin-x86
     runs-on: ubuntu-latest
     steps:
@@ -1096,4 +1123,4 @@ jobs:
         run: |
           for tag in $(echo "${{ steps.quaymeta.outputs.tags }}" | tr ',' '\n'); do
             crane push llama-cpp.tar $tag
-          done
+          done

.github/workflows/image-pr.yml

@@ -51,12 +51,12 @@ jobs:
             grpc-base-image: "ubuntu:22.04"
             runs-on: 'ubuntu-latest'
             makeflags: "--jobs=3 --output-sync=target"
-          - build-type: 'sycl_f16'
+          - build-type: 'sycl'
             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'
+            tag-suffix: 'sycl'
             runs-on: 'ubuntu-latest'
             makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'vulkan'

.github/workflows/image.yml

@@ -109,24 +109,15 @@ jobs:
             skip-drivers: 'false'
             makeflags: "--jobs=4 --output-sync=target"
             aio: "-aio-gpu-vulkan"
-          - build-type: 'sycl_f16'
+          - build-type: 'intel'
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
             grpc-base-image: "ubuntu:22.04"
-            tag-suffix: '-gpu-intel-f16'
+            tag-suffix: '-gpu-intel'
             runs-on: 'ubuntu-latest'
             makeflags: "--jobs=3 --output-sync=target"
-            aio: "-aio-gpu-intel-f16"
-          - build-type: 'sycl_f32'
-            platforms: 'linux/amd64'
-            tag-latest: 'auto'
-            base-image: "quay.io/go-skynet/intel-oneapi-base:latest"
-            grpc-base-image: "ubuntu:22.04"
-            tag-suffix: '-gpu-intel-f32'
-            runs-on: 'ubuntu-latest'
-            makeflags: "--jobs=3 --output-sync=target"
-            aio: "-aio-gpu-intel-f32"
+            aio: "-aio-gpu-intel"
 
   gh-runner:
     uses: ./.github/workflows/image_build.yml

.github/workflows/test.yml

@@ -23,6 +23,20 @@ jobs:
       matrix:
         go-version: ['1.21.x']
     steps:
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: true
+          swap-storage: true
       - name: Release space from worker
         run: |
           echo "Listing top largest packages"

Dockerfile

@@ -9,7 +9,7 @@ ENV DEBIAN_FRONTEND=noninteractive
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
         ca-certificates curl wget espeak-ng libgomp1 \
-        python3 python-is-python3 ffmpeg && \
+        python3 python-is-python3 ffmpeg libopenblas-base libopenblas-dev && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
@@ -100,6 +100,8 @@ RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then
         ldconfig \
     ; fi
 
+RUN expr "${BUILD_TYPE}" = intel && echo "intel" > /run/localai/capability || echo "not intel"
+
 # Cuda
 ENV PATH=/usr/local/cuda/bin:${PATH}
 

Makefile

@@ -5,8 +5,6 @@ BINARY_NAME=local-ai
 
 GORELEASER?=
 
-ONEAPI_VERSION?=2025.2
-
 export BUILD_TYPE?=
 
 GO_TAGS?=
@@ -134,6 +132,9 @@ test: test-models/testmodel.ggml protogen-go
 	$(MAKE) test-tts
 	$(MAKE) test-stablediffusion
 
+backends/diffusers: docker-build-diffusers docker-save-diffusers build
+	./local-ai backends install "ocifile://$(abspath ./backend-images/diffusers.tar)"
+
 backends/llama-cpp: docker-build-llama-cpp docker-save-llama-cpp build
 	./local-ai backends install "ocifile://$(abspath ./backend-images/llama-cpp.tar)"
 
@@ -158,6 +159,12 @@ backends/huggingface: docker-build-huggingface docker-save-huggingface build
 backends/rfdetr: docker-build-rfdetr docker-save-rfdetr build
 	./local-ai backends install "ocifile://$(abspath ./backend-images/rfdetr.tar)"
 
+backends/kitten-tts: docker-build-kitten-tts docker-save-kitten-tts build
+	./local-ai backends install "ocifile://$(abspath ./backend-images/kitten-tts.tar)"
+
+backends/kokoro: docker-build-kokoro docker-save-kokoro build
+	./local-ai backends install "ocifile://$(abspath ./backend-images/kokoro.tar)"
+
 ########################################################
 ## AIO tests
 ########################################################
@@ -340,19 +347,11 @@ docker-aio-all:
 
 docker-image-intel:
 	docker build \
-		--build-arg BASE_IMAGE=intel/oneapi-basekit:${ONEAPI_VERSION}.0-0-devel-ubuntu24.04 \
+		--build-arg BASE_IMAGE=quay.io/go-skynet/intel-oneapi-base:latest \
 		--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
 		--build-arg GO_TAGS="$(GO_TAGS)" \
 		--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
-		--build-arg BUILD_TYPE=sycl_f32 -t $(DOCKER_IMAGE) .
-
-docker-image-intel-xpu:
-	docker build \
-		--build-arg BASE_IMAGE=intel/oneapi-basekit:${ONEAPI_VERSION}.0-0-devel-ubuntu22.04 \
-		--build-arg IMAGE_TYPE=$(IMAGE_TYPE) \
-		--build-arg GO_TAGS="$(GO_TAGS)" \
-		--build-arg MAKEFLAGS="$(DOCKER_MAKEFLAGS)" \
-		--build-arg BUILD_TYPE=sycl_f32 -t $(DOCKER_IMAGE) .
+		--build-arg BUILD_TYPE=intel -t $(DOCKER_IMAGE) .
 
 ########################################################
 ## Backends
@@ -379,6 +378,18 @@ docker-build-huggingface:
 docker-build-rfdetr:
 	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:rfdetr -f backend/Dockerfile.python --build-arg BACKEND=rfdetr ./backend
 
+docker-build-kitten-tts:
+	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:kitten-tts -f backend/Dockerfile.python --build-arg BACKEND=kitten-tts ./backend
+
+docker-save-kitten-tts: backend-images
+	docker save local-ai-backend:kitten-tts -o backend-images/kitten-tts.tar
+
+docker-build-kokoro:
+	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:kokoro -f backend/Dockerfile.python --build-arg BACKEND=kokoro ./backend
+
+docker-save-kokoro: backend-images
+	docker save local-ai-backend:kokoro -o backend-images/kokoro.tar
+
 docker-save-rfdetr: backend-images
 	docker save local-ai-backend:rfdetr -o backend-images/rfdetr.tar
 
@@ -419,10 +430,10 @@ docker-build-transformers:
 	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:transformers -f backend/Dockerfile.python --build-arg BACKEND=transformers .
 
 docker-build-diffusers:
-	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:diffusers -f backend/Dockerfile.python --build-arg BACKEND=diffusers .
+	docker build --progress=plain --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:diffusers -f backend/Dockerfile.python --build-arg BACKEND=diffusers ./backend
 
-docker-build-kokoro:
-	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:kokoro -f backend/Dockerfile.python --build-arg BACKEND=kokoro .
+docker-save-diffusers: backend-images
+	docker save local-ai-backend:diffusers -o backend-images/diffusers.tar
 
 docker-build-whisper:
 	docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_IMAGE) -t local-ai-backend:whisper -f backend/Dockerfile.golang --build-arg BACKEND=whisper  .

README.md

@@ -140,11 +140,7 @@ docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri
 ### Intel GPU Images (oneAPI):
 
 ```bash
-# Intel GPU with FP16 support
-docker run -ti --name local-ai -p 8080:8080 --device=/dev/dri/card1 --device=/dev/dri/renderD128 localai/localai:latest-gpu-intel-f16
-
-# Intel GPU with FP32 support
-docker run -ti --name local-ai -p 8080:8080 --device=/dev/dri/card1 --device=/dev/dri/renderD128 localai/localai:latest-gpu-intel-f32
+docker run -ti --name local-ai -p 8080:8080 --device=/dev/dri/card1 --device=/dev/dri/renderD128 localai/localai:latest-gpu-intel
 ```
 
 ### Vulkan GPU Images:
@@ -166,7 +162,7 @@ docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-ai
 docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-aio-gpu-nvidia-cuda-11
 
 # Intel GPU version
-docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel-f16
+docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel
 
 # AMD GPU version
 docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-hipblas

backend/Dockerfile.golang

@@ -96,17 +96,6 @@ RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ "${SKIP_DRIVERS}" = "false" ]; then
         ldconfig \
     ; fi
 
-# Intel oneAPI requirements
-RUN <<EOT bash
-    if [[ "${BUILD_TYPE}" == sycl* ]] && [ "${SKIP_DRIVERS}" = "false" ]; then
-        apt-get update && \
-        apt-get install -y --no-install-recommends \
-            intel-oneapi-runtime-libs && \
-        apt-get clean && \
-        rm -rf /var/lib/apt/lists/*
-    fi
-EOT
-
 # Install Go
 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:/usr/local/bin

backend/backend.proto

@@ -305,6 +305,9 @@ message GenerateImageRequest {
   // Diffusers
   string EnableParameters = 10;
   int32 CLIPSkip = 11;
+  
+  // Reference images for models that support them (e.g., Flux Kontext)
+  repeated string ref_images = 12;
 }
 
 message GenerateVideoRequest {

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=bf78f5439ee8e82e367674043303ebf8e92b4805
+LLAMA_VERSION?=be48528b068111304e4a0bb82c028558b5705f05
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=
@@ -26,7 +26,7 @@ else ifeq ($(BUILD_TYPE),openblas)
 # If build type is clblas (openCL) we set -DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
 else ifeq ($(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++ 
+# 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)
 	ROCM_HOME ?= /opt/rocm
 	ROCM_PATH ?= /opt/rocm

backend/cpp/llama-cpp/grpc-server.cpp

@@ -313,9 +313,11 @@ static void params_parse(const backend::ModelOptions* request,
         params.pooling_type = LLAMA_POOLING_TYPE_RANK;
     }
 
+    
     if (request->ropescaling() == "none")   { params.rope_scaling_type = LLAMA_ROPE_SCALING_TYPE_NONE; }
     else if (request->ropescaling() == "yarn")   { params.rope_scaling_type = LLAMA_ROPE_SCALING_TYPE_YARN; }
-    else { params.rope_scaling_type = LLAMA_ROPE_SCALING_TYPE_LINEAR; }
+    else if (request->ropescaling() == "linear")   {  params.rope_scaling_type = LLAMA_ROPE_SCALING_TYPE_LINEAR; }
+
     if ( request->yarnextfactor() != 0.0f ) {
         params.yarn_ext_factor = request->yarnextfactor();
     }

backend/go/stablediffusion-ggml/Makefile

@@ -19,10 +19,10 @@ LD_FLAGS?=
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=eed97a5e1d054f9c1e7ac01982ae480411d4157e
+STABLEDIFFUSION_GGML_VERSION?=5900ef6605c6fbf7934239f795c13c97bc993853
 
 # 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 -DGGML_MAX_NAME=128 -DSD_USE_SYSTEM_GGML=OFF
 
 ifeq ($(NATIVE),false)
 	CMAKE_ARGS+=-DGGML_NATIVE=OFF

backend/go/stablediffusion-ggml/gosd.cpp

@@ -1,3 +1,5 @@
+#define GGML_MAX_NAME 128
+
 #include <stdio.h>
 #include <string.h>
 #include <time.h>
@@ -5,6 +7,7 @@
 #include <random>
 #include <string>
 #include <vector>
+#include <filesystem>
 #include "gosd.h"
 
 // #include "preprocessing.hpp"
@@ -85,7 +88,7 @@ void sd_log_cb(enum sd_log_level_t level, const char* log, void* data) {
     fflush(stderr);
 }
 
-int load_model(char *model, char* options[], int threads, int diff) {
+int load_model(char *model, char *model_path, char* options[], int threads, int diff) {
     fprintf (stderr, "Loading model!\n");
 
     sd_set_log_callback(sd_log_cb, NULL);
@@ -103,6 +106,8 @@ int load_model(char *model, char* options[], int threads, int diff) {
     char *vae_path  = "";
     char *scheduler = "";
     char *sampler = "";
+    char *lora_dir = model_path;
+    bool lora_dir_allocated = false;
 
     fprintf(stderr, "parsing options\n");
 
@@ -132,6 +137,20 @@ int load_model(char *model, char* options[], int threads, int diff) {
         if (!strcmp(optname, "sampler")) {
             sampler = optval;
         }
+        if (!strcmp(optname, "lora_dir")) {
+            // Path join with model dir
+            if (model_path && strlen(model_path) > 0) {
+                std::filesystem::path model_path_str(model_path);
+                std::filesystem::path lora_path(optval);
+                std::filesystem::path full_lora_path = model_path_str / lora_path;
+                lora_dir = strdup(full_lora_path.string().c_str());
+                lora_dir_allocated = true;
+                fprintf(stderr, "Lora dir resolved to: %s\n", lora_dir);
+            } else {
+                lora_dir = optval;
+                fprintf(stderr, "No model path provided, using lora dir as-is: %s\n", lora_dir);
+            }
+        }
     }
 
     fprintf(stderr, "parsed options\n");
@@ -176,7 +195,7 @@ int load_model(char *model, char* options[], int threads, int diff) {
     ctx_params.vae_path = vae_path;
     ctx_params.taesd_path = "";
     ctx_params.control_net_path = "";
-    ctx_params.lora_model_dir = "";
+    ctx_params.lora_model_dir = lora_dir;
     ctx_params.embedding_dir = "";
     ctx_params.stacked_id_embed_dir = "";
     ctx_params.vae_decode_only = false;
@@ -189,16 +208,25 @@ int load_model(char *model, char* options[], int threads, int diff) {
 
     if (sd_ctx == NULL) {
         fprintf (stderr, "failed loading model (generic error)\n");
+        // Clean up allocated memory
+        if (lora_dir_allocated && lora_dir) {
+            free(lora_dir);
+        }
         return 1;
     }
     fprintf (stderr, "Created context: OK\n");
 
     sd_c = sd_ctx;
 
+    // Clean up allocated memory
+    if (lora_dir_allocated && lora_dir) {
+        free(lora_dir);
+    }
+
     return 0;
 }
 
-int gen_image(char *text, char *negativeText, int width, int height, int steps, int seed , char *dst, float cfg_scale) {
+int gen_image(char *text, char *negativeText, int width, int height, int steps, int seed , char *dst, float cfg_scale, char *src_image, float strength, char *mask_image, char **ref_images, int ref_images_count) {
 
     sd_image_t* results;
 
@@ -221,15 +249,187 @@ int gen_image(char *text, char *negativeText, int width, int height, int steps,
     p.seed = seed;
     p.input_id_images_path = "";
 
+    // Handle input image for img2img
+    bool has_input_image = (src_image != NULL && strlen(src_image) > 0);
+    bool has_mask_image = (mask_image != NULL && strlen(mask_image) > 0);
+    
+    uint8_t* input_image_buffer = NULL;
+    uint8_t* mask_image_buffer = NULL;
+    std::vector<uint8_t> default_mask_image_vec;
+    
+    if (has_input_image) {
+        fprintf(stderr, "Loading input image: %s\n", src_image);
+        
+        int c = 0;
+        int img_width = 0;
+        int img_height = 0;
+        input_image_buffer = stbi_load(src_image, &img_width, &img_height, &c, 3);
+        if (input_image_buffer == NULL) {
+            fprintf(stderr, "Failed to load input image from '%s'\n", src_image);
+            return 1;
+        }
+        if (c < 3) {
+            fprintf(stderr, "Input image must have at least 3 channels, got %d\n", c);
+            free(input_image_buffer);
+            return 1;
+        }
+        
+        // Resize input image if dimensions don't match
+        if (img_width != width || img_height != height) {
+            fprintf(stderr, "Resizing input image from %dx%d to %dx%d\n", img_width, img_height, width, height);
+            
+            uint8_t* resized_image_buffer = (uint8_t*)malloc(height * width * 3);
+            if (resized_image_buffer == NULL) {
+                fprintf(stderr, "Failed to allocate memory for resized image\n");
+                free(input_image_buffer);
+                return 1;
+            }
+            
+            stbir_resize(input_image_buffer, img_width, img_height, 0,
+                         resized_image_buffer, width, height, 0, STBIR_TYPE_UINT8,
+                         3, STBIR_ALPHA_CHANNEL_NONE, 0,
+                         STBIR_EDGE_CLAMP, STBIR_EDGE_CLAMP,
+                         STBIR_FILTER_BOX, STBIR_FILTER_BOX,
+                         STBIR_COLORSPACE_SRGB, nullptr);
+            
+            free(input_image_buffer);
+            input_image_buffer = resized_image_buffer;
+        }
+        
+        p.init_image = {(uint32_t)width, (uint32_t)height, 3, input_image_buffer};
+        p.strength = strength;
+        fprintf(stderr, "Using img2img with strength: %.2f\n", strength);
+    } else {
+        // No input image, use empty image for text-to-image
+        p.init_image = {(uint32_t)width, (uint32_t)height, 3, NULL};
+        p.strength = 0.0f;
+    }
+    
+    // Handle mask image for inpainting
+    if (has_mask_image) {
+        fprintf(stderr, "Loading mask image: %s\n", mask_image);
+        
+        int c = 0;
+        int mask_width = 0;
+        int mask_height = 0;
+        mask_image_buffer = stbi_load(mask_image, &mask_width, &mask_height, &c, 1);
+        if (mask_image_buffer == NULL) {
+            fprintf(stderr, "Failed to load mask image from '%s'\n", mask_image);
+            if (input_image_buffer) free(input_image_buffer);
+            return 1;
+        }
+        
+        // Resize mask if dimensions don't match
+        if (mask_width != width || mask_height != height) {
+            fprintf(stderr, "Resizing mask image from %dx%d to %dx%d\n", mask_width, mask_height, width, height);
+            
+            uint8_t* resized_mask_buffer = (uint8_t*)malloc(height * width);
+            if (resized_mask_buffer == NULL) {
+                fprintf(stderr, "Failed to allocate memory for resized mask\n");
+                free(mask_image_buffer);
+                if (input_image_buffer) free(input_image_buffer);
+                return 1;
+            }
+            
+            stbir_resize(mask_image_buffer, mask_width, mask_height, 0,
+                         resized_mask_buffer, width, height, 0, STBIR_TYPE_UINT8,
+                         1, STBIR_ALPHA_CHANNEL_NONE, 0,
+                         STBIR_EDGE_CLAMP, STBIR_EDGE_CLAMP,
+                         STBIR_FILTER_BOX, STBIR_FILTER_BOX,
+                         STBIR_COLORSPACE_SRGB, nullptr);
+            
+            free(mask_image_buffer);
+            mask_image_buffer = resized_mask_buffer;
+        }
+        
+        p.mask_image = {(uint32_t)width, (uint32_t)height, 1, mask_image_buffer};
+        fprintf(stderr, "Using inpainting with mask\n");
+    } else {
+        // No mask image, create default full mask
+        default_mask_image_vec.resize(width * height, 255);
+        p.mask_image = {(uint32_t)width, (uint32_t)height, 1, default_mask_image_vec.data()};
+    }
+
+    // Handle reference images
+    std::vector<sd_image_t> ref_images_vec;
+    std::vector<uint8_t*> ref_image_buffers;
+    
+    if (ref_images_count > 0 && ref_images != NULL) {
+        fprintf(stderr, "Loading %d reference images\n", ref_images_count);
+        
+        for (int i = 0; i < ref_images_count; i++) {
+            if (ref_images[i] == NULL || strlen(ref_images[i]) == 0) {
+                continue;
+            }
+            
+            fprintf(stderr, "Loading reference image %d: %s\n", i + 1, ref_images[i]);
+            
+            int c = 0;
+            int ref_width = 0;
+            int ref_height = 0;
+            uint8_t* ref_image_buffer = stbi_load(ref_images[i], &ref_width, &ref_height, &c, 3);
+            if (ref_image_buffer == NULL) {
+                fprintf(stderr, "Failed to load reference image from '%s'\n", ref_images[i]);
+                continue;
+            }
+            if (c < 3) {
+                fprintf(stderr, "Reference image must have at least 3 channels, got %d\n", c);
+                free(ref_image_buffer);
+                continue;
+            }
+            
+            // Resize reference image if dimensions don't match
+            if (ref_width != width || ref_height != height) {
+                fprintf(stderr, "Resizing reference image from %dx%d to %dx%d\n", ref_width, ref_height, width, height);
+                
+                uint8_t* resized_ref_buffer = (uint8_t*)malloc(height * width * 3);
+                if (resized_ref_buffer == NULL) {
+                    fprintf(stderr, "Failed to allocate memory for resized reference image\n");
+                    free(ref_image_buffer);
+                    continue;
+                }
+                
+                stbir_resize(ref_image_buffer, ref_width, ref_height, 0,
+                             resized_ref_buffer, width, height, 0, STBIR_TYPE_UINT8,
+                             3, STBIR_ALPHA_CHANNEL_NONE, 0,
+                             STBIR_EDGE_CLAMP, STBIR_EDGE_CLAMP,
+                             STBIR_FILTER_BOX, STBIR_FILTER_BOX,
+                             STBIR_COLORSPACE_SRGB, nullptr);
+                
+                free(ref_image_buffer);
+                ref_image_buffer = resized_ref_buffer;
+            }
+            
+            ref_image_buffers.push_back(ref_image_buffer);
+            ref_images_vec.push_back({(uint32_t)width, (uint32_t)height, 3, ref_image_buffer});
+        }
+        
+        if (!ref_images_vec.empty()) {
+            p.ref_images = ref_images_vec.data();
+            p.ref_images_count = ref_images_vec.size();
+            fprintf(stderr, "Using %zu reference images\n", ref_images_vec.size());
+        }
+    }
+
     results = generate_image(sd_c, &p);
 
     if (results == NULL) {
         fprintf (stderr, "NO results\n");
+        if (input_image_buffer) free(input_image_buffer);
+        if (mask_image_buffer) free(mask_image_buffer);
+        for (auto buffer : ref_image_buffers) {
+            if (buffer) free(buffer);
+        }
         return 1;
     }
 
     if (results[0].data == NULL) {
         fprintf (stderr, "Results with no data\n");
+        if (input_image_buffer) free(input_image_buffer);
+        if (mask_image_buffer) free(mask_image_buffer);
+        for (auto buffer : ref_image_buffers) {
+            if (buffer) free(buffer);
+        }
         return 1;
     }
 
@@ -245,11 +445,15 @@ int gen_image(char *text, char *negativeText, int width, int height, int steps,
                        results[0].data, 0, NULL);
     fprintf (stderr, "Saved resulting image to '%s'\n", dst);
 
-    // TODO: free results. Why does it crash?
-
+    // Clean up
     free(results[0].data);
     results[0].data = NULL;
     free(results);
+    if (input_image_buffer) free(input_image_buffer);
+    if (mask_image_buffer) free(mask_image_buffer);
+    for (auto buffer : ref_image_buffers) {
+        if (buffer) free(buffer);
+    }
     fprintf (stderr, "gen_image is done", dst);
 
     return 0;

backend/go/stablediffusion-ggml/gosd.go

@@ -29,16 +29,21 @@ func (sd *SDGGML) Load(opts *pb.ModelOptions) error {
 
 	sd.threads = int(opts.Threads)
 
+	modelPath := opts.ModelPath
+
 	modelFile := C.CString(opts.ModelFile)
 	defer C.free(unsafe.Pointer(modelFile))
 
+	modelPathC := C.CString(modelPath)
+	defer C.free(unsafe.Pointer(modelPathC))
+
 	var options **C.char
 	// prepare the options array to pass to C
 
 	size := C.size_t(unsafe.Sizeof((*C.char)(nil)))
 	length := C.size_t(len(opts.Options))
 	options = (**C.char)(C.malloc((length + 1) * size))
-	view := (*[1 << 30]*C.char)(unsafe.Pointer(options))[0:len(opts.Options) + 1:len(opts.Options) + 1]
+	view := (*[1 << 30]*C.char)(unsafe.Pointer(options))[0 : len(opts.Options)+1 : len(opts.Options)+1]
 
 	var diffusionModel int
 
@@ -70,7 +75,7 @@ func (sd *SDGGML) Load(opts *pb.ModelOptions) error {
 
 	sd.cfgScale = opts.CFGScale
 
-	ret := C.load_model(modelFile, options, C.int(opts.Threads), C.int(diffusionModel))
+	ret := C.load_model(modelFile, modelPathC, options, C.int(opts.Threads), C.int(diffusionModel))
 	if ret != 0 {
 		return fmt.Errorf("could not load model")
 	}
@@ -88,7 +93,56 @@ func (sd *SDGGML) GenerateImage(opts *pb.GenerateImageRequest) error {
 	negative := C.CString(opts.NegativePrompt)
 	defer C.free(unsafe.Pointer(negative))
 
-	ret := C.gen_image(t, negative, C.int(opts.Width), C.int(opts.Height), C.int(opts.Step), C.int(opts.Seed), dst, C.float(sd.cfgScale))
+	// Handle source image path
+	var srcImage *C.char
+	if opts.Src != "" {
+		srcImage = C.CString(opts.Src)
+		defer C.free(unsafe.Pointer(srcImage))
+	}
+
+	// Handle mask image path
+	var maskImage *C.char
+	if opts.EnableParameters != "" {
+		// Parse EnableParameters for mask path if provided
+		// This is a simple approach - in a real implementation you might want to parse JSON
+		if strings.Contains(opts.EnableParameters, "mask:") {
+			parts := strings.Split(opts.EnableParameters, "mask:")
+			if len(parts) > 1 {
+				maskPath := strings.TrimSpace(parts[1])
+				if maskPath != "" {
+					maskImage = C.CString(maskPath)
+					defer C.free(unsafe.Pointer(maskImage))
+				}
+			}
+		}
+	}
+
+	// Handle reference images
+	var refImages **C.char
+	var refImagesCount C.int
+	if len(opts.RefImages) > 0 {
+		refImagesCount = C.int(len(opts.RefImages))
+		// Allocate array of C strings
+		size := C.size_t(unsafe.Sizeof((*C.char)(nil)))
+		refImages = (**C.char)(C.malloc((C.size_t(len(opts.RefImages)) + 1) * size))
+		view := (*[1 << 30]*C.char)(unsafe.Pointer(refImages))[0 : len(opts.RefImages)+1 : len(opts.RefImages)+1]
+
+		for i, refImagePath := range opts.RefImages {
+			view[i] = C.CString(refImagePath)
+			defer C.free(unsafe.Pointer(view[i]))
+		}
+		view[len(opts.RefImages)] = nil
+	}
+
+	// Default strength for img2img (0.75 is a good default)
+	strength := C.float(0.75)
+	if opts.Src != "" {
+		// If we have a source image, use img2img mode
+		// You could also parse strength from EnableParameters if needed
+		strength = C.float(0.75)
+	}
+
+	ret := C.gen_image(t, negative, C.int(opts.Width), C.int(opts.Height), C.int(opts.Step), C.int(opts.Seed), dst, C.float(sd.cfgScale), srcImage, strength, maskImage, refImages, refImagesCount)
 	if ret != 0 {
 		return fmt.Errorf("inference failed")
 	}

backend/go/stablediffusion-ggml/gosd.h

@@ -1,8 +1,8 @@
 #ifdef __cplusplus
 extern "C" {
 #endif
-int load_model(char *model, char* options[], int threads, int diffusionModel);
-int gen_image(char *text, char *negativeText, int width, int height, int steps, int seed, char *dst, float cfg_scale);
+int load_model(char *model, char *model_path, char* options[], int threads, int diffusionModel);
+int gen_image(char *text, char *negativeText, int width, int height, int steps, int seed, char *dst, float cfg_scale, char *src_image, float strength, char *mask_image, char **ref_images, int ref_images_count);
 #ifdef __cplusplus
 }
 #endif

backend/go/whisper/Makefile

@@ -6,7 +6,7 @@ CMAKE_ARGS?=
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=e7bf0294ec9099b5fc21f5ba969805dfb2108cea
+WHISPER_CPP_VERSION?=b02242d0adb5c6c4896d59ac86d9ec9fe0d0fe33
 
 export WHISPER_CMAKE_ARGS?=-DBUILD_SHARED_LIBS=OFF
 export WHISPER_DIR=$(abspath ./sources/whisper.cpp)

backend/index.yaml

@@ -168,6 +168,7 @@
     nvidia: "cuda12-diffusers"
     intel: "intel-diffusers"
     amd: "rocm-diffusers"
+    nvidia-l4t: "nvidia-l4t-diffusers"
 - &exllama2
   name: "exllama2"
   urls:
@@ -294,6 +295,7 @@
   license: MIT
   icon: https://private-user-images.githubusercontent.com/660224/448166653-bd8c5f03-e91d-4ee5-b680-57355da204d1.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3NTAxOTE0MDAsIm5iZiI6MTc1MDE5MTEwMCwicGF0aCI6Ii82NjAyMjQvNDQ4MTY2NjUzLWJkOGM1ZjAzLWU5MWQtNGVlNS1iNjgwLTU3MzU1ZGEyMDRkMS5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjUwNjE3JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI1MDYxN1QyMDExNDBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1hMmI1NGY3OGFiZTlhNGFkNTVlYTY4NTIwMWEzODRiZGE4YzdhNGQ5MGNhNzE3MDYyYTA2NDIxYTkyYzhiODkwJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCJ9.mR9kM9xX0TdzPuSpuspCllHYQiq79dFQ2rtuNvjrl6w
   name: "chatterbox"
+  alias: "chatterbox"
   capabilities:
     nvidia: "cuda12-chatterbox"
 - &piper
@@ -356,6 +358,24 @@
     - LLM
     - huggingface
   license: MIT
+- &kitten-tts
+  name: "kitten-tts"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-kitten-tts"
+  mirrors:
+    - localai/localai-backends:latest-kitten-tts
+  urls:
+    - https://github.com/KittenML/KittenTTS
+  description: |
+    Kitten TTS is a text-to-speech model that can generate speech from text.
+  tags:
+    - text-to-speech
+    - TTS
+  license: apache-2.0
+- !!merge <<: *kitten-tts
+  name: "kitten-tts-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-kitten-tts"
+  mirrors:
+    - localai/localai-backends:master-kitten-tts
 - !!merge <<: *huggingface
   name: "huggingface-development"
   uri: "quay.io/go-skynet/local-ai-backends:master-huggingface"
@@ -834,6 +854,17 @@
     nvidia: "cuda12-diffusers-development"
     intel: "intel-diffusers-development"
     amd: "rocm-diffusers-development"
+    nvidia-l4t: "nvidia-l4t-diffusers-development"
+- !!merge <<: *diffusers
+  name: "nvidia-l4t-diffusers"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-l4t-diffusers"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-l4t-diffusers
+- !!merge <<: *diffusers
+  name: "nvidia-l4t-diffusers-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-l4t-diffusers"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-l4t-diffusers
 - !!merge <<: *diffusers
   name: "cuda12-diffusers"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-diffusers"

backend/python/common/libbackend.sh

@@ -57,6 +57,11 @@ function init() {
 # - hipblas
 # - intel
 function getBuildProfile() {
+    if [ "x${BUILD_TYPE}" == "xl4t" ]; then
+        echo "l4t"
+        return 0
+    fi
+
     # First check if we are a cublas build, and if so report the correct build profile
     if [ x"${BUILD_TYPE}" == "xcublas" ]; then
         if [ ! -z ${CUDA_MAJOR_VERSION} ]; then

backend/python/diffusers/backend.py

@@ -65,6 +65,19 @@ from diffusers.schedulers import (
     UniPCMultistepScheduler,
 )
 
+def is_float(s):
+    try:
+        float(s)
+        return True
+    except ValueError:
+        return False
+
+def is_int(s):
+    try:
+        int(s)
+        return True
+    except ValueError:
+        return False
 
 # The scheduler list mapping was taken from here: https://github.com/neggles/animatediff-cli/blob/6f336f5f4b5e38e85d7f06f1744ef42d0a45f2a7/src/animatediff/schedulers.py#L39
 # Credits to https://github.com/neggles
@@ -169,8 +182,24 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 if ":" not in opt:
                     continue
                 key, value = opt.split(":")
+                # if value is a number, convert it to the appropriate type
+                if is_float(value):
+                    value = float(value)
+                elif is_int(value):
+                    value = int(value)
                 self.options[key] = value
 
+            # From options, extract if present "torch_dtype" and set it to the appropriate type
+            if "torch_dtype" in self.options:
+                if self.options["torch_dtype"] == "fp16":
+                    torchType = torch.float16
+                elif self.options["torch_dtype"] == "bf16":
+                    torchType = torch.bfloat16
+                elif self.options["torch_dtype"] == "fp32":
+                    torchType = torch.float32
+                # remove it from options
+                del self.options["torch_dtype"]
+
             print(f"Options: {self.options}", file=sys.stderr)
 
             local = False

backend/python/diffusers/requirements-cpu.txt

@@ -1,9 +1,9 @@
-diffusers
+git+https://github.com/huggingface/diffusers
 opencv-python
 transformers
 accelerate
 compel
 peft
 sentencepiece
-torch==2.4.1
+torch==2.7.1
 optimum-quanto

backend/python/diffusers/requirements-cublas11.txt

@@ -1,6 +1,6 @@
 --extra-index-url https://download.pytorch.org/whl/cu118
-torch==2.4.1+cu118
-diffusers
+torch==2.7.1+cu118
+git+https://github.com/huggingface/diffusers
 opencv-python
 transformers
 accelerate

backend/python/diffusers/requirements-cublas12.txt

@@ -1,5 +1,5 @@
-torch==2.4.1
-diffusers
+torch==2.7.1
+git+https://github.com/huggingface/diffusers
 opencv-python
 transformers
 accelerate

backend/python/diffusers/requirements-hipblas.txt

@@ -1,7 +1,7 @@
---extra-index-url https://download.pytorch.org/whl/rocm6.0
-torch==2.3.1+rocm6.0
-torchvision==0.18.1+rocm6.0
-diffusers
+--extra-index-url https://download.pytorch.org/whl/rocm6.3
+torch==2.7.1+rocm6.3
+torchvision==0.22.1+rocm6.3
+git+https://github.com/huggingface/diffusers
 opencv-python
 transformers
 accelerate

backend/python/diffusers/requirements-intel.txt

@@ -1,11 +1,11 @@
 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 intel-extension-for-pytorch==2.3.110+xpu
-torch==2.3.1+cxx11.abi
-torchvision==0.18.1+cxx11.abi
-oneccl_bind_pt==2.3.100+xpu
+torch==2.5.1+cxx11.abi
+torchvision==0.20.1+cxx11.abi
+oneccl_bind_pt==2.8.0+xpu
 optimum[openvino]
 setuptools
-diffusers
+git+https://github.com/huggingface/diffusers
 opencv-python
 transformers
 accelerate

backend/python/diffusers/requirements-l4t.txt

@@ -0,0 +1,10 @@
+--extra-index-url https://pypi.jetson-ai-lab.io/jp6/cu126/
+torch
+diffusers
+transformers
+accelerate
+compel
+peft
+optimum-quanto
+numpy<2
+sentencepiece

backend/python/kitten-tts/Makefile

@@ -0,0 +1,29 @@
+.PHONY: kitten-tts
+kitten-tts: protogen
+	bash install.sh
+
+.PHONY: run
+run: protogen
+	@echo "Running kitten-tts..."
+	bash run.sh
+	@echo "kitten-tts run."
+
+.PHONY: test
+test: protogen
+	@echo "Testing kitten-tts..."
+	bash test.sh
+	@echo "kitten-tts tested."
+
+.PHONY: protogen
+protogen: backend_pb2_grpc.py backend_pb2.py
+
+.PHONY: protogen-clean
+protogen-clean:
+	$(RM) backend_pb2_grpc.py backend_pb2.py
+
+backend_pb2_grpc.py backend_pb2.py:
+	python3 -m grpc_tools.protoc -I../.. -I./ --python_out=. --grpc_python_out=. backend.proto
+
+.PHONY: clean
+clean: protogen-clean
+	rm -rf venv __pycache__

backend/python/kitten-tts/backend.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python3
+"""
+This is an extra gRPC server of LocalAI for Kitten TTS
+"""
+from concurrent import futures
+import time
+import argparse
+import signal
+import sys
+import os
+import backend_pb2
+import backend_pb2_grpc
+
+import torch
+from kittentts import KittenTTS
+import soundfile as sf
+
+import grpc
+
+
+_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'))
+KITTEN_LANGUAGE = os.environ.get('KITTEN_LANGUAGE', None)
+
+# Implement the BackendServicer class with the service methods
+class BackendServicer(backend_pb2_grpc.BackendServicer):
+    """
+    BackendServicer is the class that implements the gRPC service
+    """
+    def Health(self, request, context):
+        return backend_pb2.Reply(message=bytes("OK", 'utf-8'))
+    def LoadModel(self, request, context):
+
+        # Get device
+        # device = "cuda" if request.CUDA else "cpu"
+        if torch.cuda.is_available():
+            print("CUDA is available", file=sys.stderr)
+            device = "cuda"
+        else:
+            print("CUDA is not available", file=sys.stderr)
+            device = "cpu"
+
+        if not torch.cuda.is_available() and request.CUDA:
+            return backend_pb2.Result(success=False, message="CUDA is not available")
+
+        self.AudioPath = None
+        # List available KittenTTS models
+        print("Available KittenTTS voices: expr-voice-2-m, expr-voice-2-f, expr-voice-3-m, expr-voice-3-f, expr-voice-4-m, expr-voice-4-f, expr-voice-5-m, expr-voice-5-f")
+        if os.path.isabs(request.AudioPath):
+            self.AudioPath = request.AudioPath
+        elif request.AudioPath and request.ModelFile != "" and not os.path.isabs(request.AudioPath):
+            # get base path of modelFile
+            modelFileBase = os.path.dirname(request.ModelFile)
+            # modify LoraAdapter to be relative to modelFileBase
+            self.AudioPath = os.path.join(modelFileBase, request.AudioPath)
+
+        try:
+            print("Preparing KittenTTS model, please wait", file=sys.stderr)
+            # Use the model name from request.Model, defaulting to "KittenML/kitten-tts-nano-0.1" if not specified
+            model_name = request.Model if request.Model else "KittenML/kitten-tts-nano-0.1"
+            self.tts = KittenTTS(model_name)
+        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 TTS(self, request, context):
+        try:
+            # KittenTTS doesn't use language parameter like TTS, so we ignore it
+            # For multi-speaker models, use voice parameter
+            voice = request.voice if request.voice else "expr-voice-2-f"
+            
+            # Generate audio using KittenTTS
+            audio = self.tts.generate(request.text, voice=voice)
+            
+            # Save the audio using soundfile
+            sf.write(request.dst, audio, 24000)
+            
+        except Exception as err:
+            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+        return backend_pb2.Result(success=True)
+
+def serve(address):
+    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()
+    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/kitten-tts/install.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+set -e
+
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+# This is here because the Intel pip index is broken and returns 200 status codes for every package name, it just doesn't return any package links.
+# This makes uv think that the package exists in the Intel pip index, and by default it stops looking at other pip indexes once it finds a match.
+# We need uv to continue falling through to the pypi default index to find optimum[openvino] in the pypi index
+# the --upgrade actually allows us to *downgrade* torch to the version provided in the Intel pip index
+if [ "x${BUILD_PROFILE}" == "xintel" ]; then
+    EXTRA_PIP_INSTALL_FLAGS+=" --upgrade --index-strategy=unsafe-first-match"
+fi
+
+installRequirements

backend/python/kitten-tts/requirements.txt

@@ -0,0 +1,5 @@
+grpcio==1.71.0
+protobuf
+certifi
+packaging==24.1
+https://github.com/KittenML/KittenTTS/releases/download/0.1/kittentts-0.1.0-py3-none-any.whl

backend/python/kitten-tts/run.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+backend_dir=$(dirname $0)
+if [ -d $backend_dir/common ]; then
+    source $backend_dir/common/libbackend.sh
+else
+    source $backend_dir/../common/libbackend.sh
+fi
+
+startBackend $@

backend/python/kitten-tts/test.py

@@ -0,0 +1,82 @@
+"""
+A test script to test the gRPC service
+"""
+import unittest
+import subprocess
+import time
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+
+
+class TestBackendServicer(unittest.TestCase):
+    """
+    TestBackendServicer is the class that tests the gRPC service
+    """
+    def setUp(self):
+        """
+        This method sets up the gRPC service by starting the server
+        """
+        self.service = subprocess.Popen(["python3", "backend.py", "--addr", "localhost:50051"])
+        time.sleep(30)
+
+    def tearDown(self) -> None:
+        """
+        This method tears down the gRPC service by terminating the server
+        """
+        self.service.terminate()
+        self.service.wait()
+
+    def test_server_startup(self):
+        """
+        This method tests if the server starts up successfully
+        """
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.Health(backend_pb2.HealthMessage())
+                self.assertEqual(response.message, b'OK')
+        except Exception as err:
+            print(err)
+            self.fail("Server failed to start")
+        finally:
+            self.tearDown()
+
+    def test_load_model(self):
+        """
+        This method tests if the model is loaded successfully
+        """
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.LoadModel(backend_pb2.ModelOptions(Model="tts_models/en/vctk/vits"))
+                print(response)
+                self.assertTrue(response.success)
+                self.assertEqual(response.message, "Model loaded successfully")
+        except Exception as err:
+            print(err)
+            self.fail("LoadModel service failed")
+        finally:
+            self.tearDown()
+
+    def test_tts(self):
+        """
+        This method tests if the embeddings are generated successfully
+        """
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.LoadModel(backend_pb2.ModelOptions(Model="tts_models/en/vctk/vits"))
+                self.assertTrue(response.success)
+                tts_request = backend_pb2.TTSRequest(text="80s TV news production music hit for tonight's biggest story")
+                tts_response = stub.TTS(tts_request)
+                self.assertIsNotNone(tts_response)
+        except Exception as err:
+            print(err)
+            self.fail("TTS service failed")
+        finally:
+            self.tearDown()

backend/python/kitten-tts/test.sh

@@ -8,4 +8,4 @@ else
     source $backend_dir/../common/libbackend.sh
 fi
 
-python3 -m grpc_tools.protoc -I../.. -I./ --python_out=. --grpc_python_out=. backend.proto
+runUnittests

backend/python/kokoro/Makefile

@@ -1,9 +1,18 @@
-.DEFAULT_GOAL := install
-
-.PHONY: install
-install:
+.PHONY: kokoro
+kokoro: protogen
 	bash install.sh
-	$(MAKE) protogen
+
+.PHONY: run
+run: protogen
+	@echo "Running kokoro..."
+	bash run.sh
+	@echo "kokoro run."
+
+.PHONY: test
+test: protogen
+	@echo "Testing kokoro..."
+	bash test.sh
+	@echo "kokoro tested."
 
 .PHONY: protogen
 protogen: backend_pb2_grpc.py backend_pb2.py
@@ -13,7 +22,7 @@ protogen-clean:
 	$(RM) backend_pb2_grpc.py backend_pb2.py
 
 backend_pb2_grpc.py backend_pb2.py:
-	bash protogen.sh
+	python3 -m grpc_tools.protoc -I../.. -I./ --python_out=. --grpc_python_out=. backend.proto
 
 .PHONY: clean
 clean: protogen-clean

backend/python/kokoro/README.md

@@ -0,0 +1,23 @@
+# Kokoro TTS Backend for LocalAI
+
+This is a gRPC server backend for LocalAI that uses the Kokoro TTS pipeline.
+
+## Creating a separate environment for kokoro project
+
+```bash
+make kokoro
+```
+
+## Testing the gRPC server
+
+```bash
+make test
+```
+
+## Features
+
+- Lightweight TTS model with 82 million parameters
+- Apache-licensed weights
+- Fast and cost-efficient
+- Multi-language support
+- Multiple voice options

backend/python/kokoro/backend.py

@@ -1,101 +1,92 @@
 #!/usr/bin/env python3
 """
-Extra gRPC server for Kokoro models.
+This is an extra gRPC server of LocalAI for Kokoro TTS
 """
 from concurrent import futures
-
+import time
 import argparse
 import signal
 import sys
 import os
-import time
 import backend_pb2
 import backend_pb2_grpc
+
+import torch
+from kokoro import KPipeline
 import soundfile as sf
+
 import grpc
 
-from models import build_model
-from kokoro import generate
-import torch
 
-SAMPLE_RATE = 22050
 _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'))
+KOKORO_LANG_CODE = os.environ.get('KOKORO_LANG_CODE', 'a')
 
 # Implement the BackendServicer class with the service methods
 class BackendServicer(backend_pb2_grpc.BackendServicer):
     """
-    A gRPC servicer for the backend service.
-
-    This class implements the gRPC methods for the backend service, including Health, LoadModel, and Embedding.
+    BackendServicer is the class that implements the gRPC service
     """
     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):
-        """
-        A gRPC method that loads a model into memory.
+        # Get device
+        if torch.cuda.is_available():
+            print("CUDA is available", file=sys.stderr)
+            device = "cuda"
+        else:
+            print("CUDA is not available", file=sys.stderr)
+            device = "cpu"
 
-        Args:
-            request: A LoadModelRequest object that contains the request parameters.
-            context: A grpc.ServicerContext object that provides information about the RPC.
+        if not torch.cuda.is_available() and request.CUDA:
+            return backend_pb2.Result(success=False, message="CUDA is not available")
 
-        Returns:
-            A Result object that contains the result of the LoadModel operation.
-        """
-        model_name = request.Model
         try:
-            device = "cuda:0" if torch.cuda.is_available() else "cpu"
-            self.MODEL = build_model(request.ModelFile, device)
+            print("Preparing Kokoro TTS pipeline, please wait", file=sys.stderr)
+            # empty dict
+            self.options = {}
             options = request.Options
-            # Find the voice from the options, options are a list of strings in this form optname:optvalue:
-            VOICE_NAME = None
+            # 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 opt.startswith("voice:"):
-                    VOICE_NAME = opt.split(":")[1]
-                    break
-            if VOICE_NAME is None:
-                return backend_pb2.Result(success=False, message=f"No voice specified in options")
-            MODELPATH = request.ModelPath
-            # If voice name contains a plus, split it and load the two models and combine them
-            if "+" in VOICE_NAME:
-                voice1, voice2 = VOICE_NAME.split("+")
-                voice1 = torch.load(f'{MODELPATH}/{voice1}.pt', weights_only=True).to(device)
-                voice2 = torch.load(f'{MODELPATH}/{voice2}.pt', weights_only=True).to(device)
-                self.VOICEPACK = torch.mean(torch.stack([voice1, voice2]), dim=0)
-            else:
-                self.VOICEPACK = torch.load(f'{MODELPATH}/{VOICE_NAME}.pt', weights_only=True).to(device)
+                if ":" not in opt:
+                    continue
+                key, value = opt.split(":")
+                self.options[key] = value
 
-            self.VOICE_NAME = VOICE_NAME
-
-            print(f'Loaded voice: {VOICE_NAME}')
+            # Initialize Kokoro pipeline with language code
+            lang_code = self.options.get("lang_code", KOKORO_LANG_CODE)
+            self.pipeline = KPipeline(lang_code=lang_code)
+            print(f"Kokoro TTS pipeline loaded with language code: {lang_code}", file=sys.stderr)
         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)
+        
+        return backend_pb2.Result(message="Kokoro TTS pipeline loaded successfully", success=True)
 
     def TTS(self, request, context):
-        model_name = request.model
-        if model_name == "":
-            return backend_pb2.Result(success=False, message="request.model is required")
         try:
-            audio, out_ps = generate(self.MODEL, request.text, self.VOICEPACK, lang=self.VOICE_NAME)
-            print(out_ps)
-            sf.write(request.dst, audio, SAMPLE_RATE)
+            # Get voice from request, default to 'af_heart' if not specified
+            voice = request.voice if request.voice else 'af_heart'
+            
+            # Generate audio using Kokoro pipeline
+            generator = self.pipeline(request.text, voice=voice)
+            
+            # Get the first (and typically only) audio segment
+            for i, (gs, ps, audio) in enumerate(generator):
+                # Save audio to the destination file
+                sf.write(request.dst, audio, 24000)
+                print(f"Generated audio segment {i}: gs={gs}, ps={ps}", file=sys.stderr)
+                # For now, we only process the first segment
+                # If you need to handle multiple segments, you might want to modify this
+                break
+                
         except Exception as err:
             return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+        
         return backend_pb2.Result(success=True)
 
 def serve(address):
@@ -108,11 +99,11 @@ def serve(address):
     backend_pb2_grpc.add_BackendServicer_to_server(BackendServicer(), server)
     server.add_insecure_port(address)
     server.start()
-    print("[Kokoro] Server started. Listening on: " + address, file=sys.stderr)
+    print("Server started. Listening on: " + address, file=sys.stderr)
 
     # Define the signal handler function
     def signal_handler(sig, frame):
-        print("[Kokoro] Received termination signal. Shutting down...")
+        print("Received termination signal. Shutting down...")
         server.stop(0)
         sys.exit(0)
 
@@ -132,5 +123,5 @@ if __name__ == "__main__":
         "--addr", default="localhost:50051", help="The address to bind the server to."
     )
     args = parser.parse_args()
-    print(f"[Kokoro] startup: {args}", file=sys.stderr)
+
     serve(args.addr)

backend/python/kokoro/istftnet.py

@@ -1,524 +0,0 @@
-# https://huggingface.co/hexgrad/Kokoro-82M/blob/main/istftnet.py
-# https://github.com/yl4579/StyleTTS2/blob/main/Modules/istftnet.py
-from scipy.signal import get_window
-from torch.nn import Conv1d, ConvTranspose1d
-from torch.nn.utils import weight_norm, remove_weight_norm
-import numpy as np
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-# https://github.com/yl4579/StyleTTS2/blob/main/Modules/utils.py
-def init_weights(m, mean=0.0, std=0.01):
-    classname = m.__class__.__name__
-    if classname.find("Conv") != -1:
-        m.weight.data.normal_(mean, std)
-
-def get_padding(kernel_size, dilation=1):
-    return int((kernel_size*dilation - dilation)/2)
-
-LRELU_SLOPE = 0.1
-
-class AdaIN1d(nn.Module):
-    def __init__(self, style_dim, num_features):
-        super().__init__()
-        self.norm = nn.InstanceNorm1d(num_features, affine=False)
-        self.fc = nn.Linear(style_dim, num_features*2)
-
-    def forward(self, x, s):
-        h = self.fc(s)
-        h = h.view(h.size(0), h.size(1), 1)
-        gamma, beta = torch.chunk(h, chunks=2, dim=1)
-        return (1 + gamma) * self.norm(x) + beta
-
-class AdaINResBlock1(torch.nn.Module):
-    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5), style_dim=64):
-        super(AdaINResBlock1, self).__init__()
-        self.convs1 = nn.ModuleList([
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[0],
-                               padding=get_padding(kernel_size, dilation[0]))),
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[1],
-                               padding=get_padding(kernel_size, dilation[1]))),
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[2],
-                               padding=get_padding(kernel_size, dilation[2])))
-        ])
-        self.convs1.apply(init_weights)
-
-        self.convs2 = nn.ModuleList([
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
-                               padding=get_padding(kernel_size, 1))),
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
-                               padding=get_padding(kernel_size, 1))),
-            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
-                               padding=get_padding(kernel_size, 1)))
-        ])
-        self.convs2.apply(init_weights)
-        
-        self.adain1 = nn.ModuleList([
-            AdaIN1d(style_dim, channels),
-            AdaIN1d(style_dim, channels),
-            AdaIN1d(style_dim, channels),
-        ])
-        
-        self.adain2 = nn.ModuleList([
-            AdaIN1d(style_dim, channels),
-            AdaIN1d(style_dim, channels),
-            AdaIN1d(style_dim, channels),
-        ])
-        
-        self.alpha1 = nn.ParameterList([nn.Parameter(torch.ones(1, channels, 1)) for i in range(len(self.convs1))])
-        self.alpha2 = nn.ParameterList([nn.Parameter(torch.ones(1, channels, 1)) for i in range(len(self.convs2))])
-
-
-    def forward(self, x, s):
-        for c1, c2, n1, n2, a1, a2 in zip(self.convs1, self.convs2, self.adain1, self.adain2, self.alpha1, self.alpha2):
-            xt = n1(x, s)
-            xt = xt + (1 / a1) * (torch.sin(a1 * xt) ** 2)  # Snake1D
-            xt = c1(xt)
-            xt = n2(xt, s)
-            xt = xt + (1 / a2) * (torch.sin(a2 * xt) ** 2)  # Snake1D
-            xt = c2(xt)
-            x = xt + x
-        return x
-
-    def remove_weight_norm(self):
-        for l in self.convs1:
-            remove_weight_norm(l)
-        for l in self.convs2:
-            remove_weight_norm(l)
-            
-class TorchSTFT(torch.nn.Module):
-    def __init__(self, filter_length=800, hop_length=200, win_length=800, window='hann'):
-        super().__init__()
-        self.filter_length = filter_length
-        self.hop_length = hop_length
-        self.win_length = win_length
-        self.window = torch.from_numpy(get_window(window, win_length, fftbins=True).astype(np.float32))
-
-    def transform(self, input_data):
-        forward_transform = torch.stft(
-            input_data,
-            self.filter_length, self.hop_length, self.win_length, window=self.window.to(input_data.device),
-            return_complex=True)
-
-        return torch.abs(forward_transform), torch.angle(forward_transform)
-
-    def inverse(self, magnitude, phase):
-        inverse_transform = torch.istft(
-            magnitude * torch.exp(phase * 1j),
-            self.filter_length, self.hop_length, self.win_length, window=self.window.to(magnitude.device))
-
-        return inverse_transform.unsqueeze(-2)  # unsqueeze to stay consistent with conv_transpose1d implementation
-
-    def forward(self, input_data):
-        self.magnitude, self.phase = self.transform(input_data)
-        reconstruction = self.inverse(self.magnitude, self.phase)
-        return reconstruction
-    
-class SineGen(torch.nn.Module):
-    """ Definition of sine generator
-    SineGen(samp_rate, harmonic_num = 0,
-            sine_amp = 0.1, noise_std = 0.003,
-            voiced_threshold = 0,
-            flag_for_pulse=False)
-    samp_rate: sampling rate in Hz
-    harmonic_num: number of harmonic overtones (default 0)
-    sine_amp: amplitude of sine-wavefrom (default 0.1)
-    noise_std: std of Gaussian noise (default 0.003)
-    voiced_thoreshold: F0 threshold for U/V classification (default 0)
-    flag_for_pulse: this SinGen is used inside PulseGen (default False)
-    Note: when flag_for_pulse is True, the first time step of a voiced
-        segment is always sin(np.pi) or cos(0)
-    """
-
-    def __init__(self, samp_rate, upsample_scale, harmonic_num=0,
-                 sine_amp=0.1, noise_std=0.003,
-                 voiced_threshold=0,
-                 flag_for_pulse=False):
-        super(SineGen, self).__init__()
-        self.sine_amp = sine_amp
-        self.noise_std = noise_std
-        self.harmonic_num = harmonic_num
-        self.dim = self.harmonic_num + 1
-        self.sampling_rate = samp_rate
-        self.voiced_threshold = voiced_threshold
-        self.flag_for_pulse = flag_for_pulse
-        self.upsample_scale = upsample_scale
-
-    def _f02uv(self, f0):
-        # generate uv signal
-        uv = (f0 > self.voiced_threshold).type(torch.float32)
-        return uv
-
-    def _f02sine(self, f0_values):
-        """ f0_values: (batchsize, length, dim)
-            where dim indicates fundamental tone and overtones
-        """
-        # convert to F0 in rad. The integer part n can be ignored
-        # because 2 * np.pi * n doesn't affect phase
-        rad_values = (f0_values / self.sampling_rate) % 1
-
-        # initial phase noise (no noise for fundamental component)
-        rand_ini = torch.rand(f0_values.shape[0], f0_values.shape[2], \
-                              device=f0_values.device)
-        rand_ini[:, 0] = 0
-        rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini
-
-        # instantanouse phase sine[t] = sin(2*pi \sum_i=1 ^{t} rad)
-        if not self.flag_for_pulse:
-#             # for normal case
-
-#             # To prevent torch.cumsum numerical overflow,
-#             # it is necessary to add -1 whenever \sum_k=1^n rad_value_k > 1.
-#             # Buffer tmp_over_one_idx indicates the time step to add -1.
-#             # This will not change F0 of sine because (x-1) * 2*pi = x * 2*pi
-#             tmp_over_one = torch.cumsum(rad_values, 1) % 1
-#             tmp_over_one_idx = (padDiff(tmp_over_one)) < 0
-#             cumsum_shift = torch.zeros_like(rad_values)
-#             cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0
-
-#             phase = torch.cumsum(rad_values, dim=1) * 2 * np.pi
-            rad_values = torch.nn.functional.interpolate(rad_values.transpose(1, 2), 
-                                                         scale_factor=1/self.upsample_scale, 
-                                                         mode="linear").transpose(1, 2)
-    
-#             tmp_over_one = torch.cumsum(rad_values, 1) % 1
-#             tmp_over_one_idx = (padDiff(tmp_over_one)) < 0
-#             cumsum_shift = torch.zeros_like(rad_values)
-#             cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0
-    
-            phase = torch.cumsum(rad_values, dim=1) * 2 * np.pi
-            phase = torch.nn.functional.interpolate(phase.transpose(1, 2) * self.upsample_scale, 
-                                                    scale_factor=self.upsample_scale, mode="linear").transpose(1, 2)
-            sines = torch.sin(phase)
-            
-        else:
-            # If necessary, make sure that the first time step of every
-            # voiced segments is sin(pi) or cos(0)
-            # This is used for pulse-train generation
-
-            # identify the last time step in unvoiced segments
-            uv = self._f02uv(f0_values)
-            uv_1 = torch.roll(uv, shifts=-1, dims=1)
-            uv_1[:, -1, :] = 1
-            u_loc = (uv < 1) * (uv_1 > 0)
-
-            # get the instantanouse phase
-            tmp_cumsum = torch.cumsum(rad_values, dim=1)
-            # different batch needs to be processed differently
-            for idx in range(f0_values.shape[0]):
-                temp_sum = tmp_cumsum[idx, u_loc[idx, :, 0], :]
-                temp_sum[1:, :] = temp_sum[1:, :] - temp_sum[0:-1, :]
-                # stores the accumulation of i.phase within
-                # each voiced segments
-                tmp_cumsum[idx, :, :] = 0
-                tmp_cumsum[idx, u_loc[idx, :, 0], :] = temp_sum
-
-            # rad_values - tmp_cumsum: remove the accumulation of i.phase
-            # within the previous voiced segment.
-            i_phase = torch.cumsum(rad_values - tmp_cumsum, dim=1)
-
-            # get the sines
-            sines = torch.cos(i_phase * 2 * np.pi)
-        return sines
-
-    def forward(self, f0):
-        """ sine_tensor, uv = forward(f0)
-        input F0: tensor(batchsize=1, length, dim=1)
-                  f0 for unvoiced steps should be 0
-        output sine_tensor: tensor(batchsize=1, length, dim)
-        output uv: tensor(batchsize=1, length, 1)
-        """
-        f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim,
-                             device=f0.device)
-        # fundamental component
-        fn = torch.multiply(f0, torch.FloatTensor([[range(1, self.harmonic_num + 2)]]).to(f0.device))
-
-        # generate sine waveforms
-        sine_waves = self._f02sine(fn) * self.sine_amp
-
-        # generate uv signal
-        # uv = torch.ones(f0.shape)
-        # uv = uv * (f0 > self.voiced_threshold)
-        uv = self._f02uv(f0)
-
-        # noise: for unvoiced should be similar to sine_amp
-        #        std = self.sine_amp/3 -> max value ~ self.sine_amp
-        # .       for voiced regions is self.noise_std
-        noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3
-        noise = noise_amp * torch.randn_like(sine_waves)
-
-        # first: set the unvoiced part to 0 by uv
-        # then: additive noise
-        sine_waves = sine_waves * uv + noise
-        return sine_waves, uv, noise
-
-
-class SourceModuleHnNSF(torch.nn.Module):
-    """ SourceModule for hn-nsf
-    SourceModule(sampling_rate, harmonic_num=0, sine_amp=0.1,
-                 add_noise_std=0.003, voiced_threshod=0)
-    sampling_rate: sampling_rate in Hz
-    harmonic_num: number of harmonic above F0 (default: 0)
-    sine_amp: amplitude of sine source signal (default: 0.1)
-    add_noise_std: std of additive Gaussian noise (default: 0.003)
-        note that amplitude of noise in unvoiced is decided
-        by sine_amp
-    voiced_threshold: threhold to set U/V given F0 (default: 0)
-    Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
-    F0_sampled (batchsize, length, 1)
-    Sine_source (batchsize, length, 1)
-    noise_source (batchsize, length 1)
-    uv (batchsize, length, 1)
-    """
-
-    def __init__(self, sampling_rate, upsample_scale, harmonic_num=0, sine_amp=0.1,
-                 add_noise_std=0.003, voiced_threshod=0):
-        super(SourceModuleHnNSF, self).__init__()
-
-        self.sine_amp = sine_amp
-        self.noise_std = add_noise_std
-
-        # to produce sine waveforms
-        self.l_sin_gen = SineGen(sampling_rate, upsample_scale, harmonic_num,
-                                 sine_amp, add_noise_std, voiced_threshod)
-
-        # to merge source harmonics into a single excitation
-        self.l_linear = torch.nn.Linear(harmonic_num + 1, 1)
-        self.l_tanh = torch.nn.Tanh()
-
-    def forward(self, x):
-        """
-        Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
-        F0_sampled (batchsize, length, 1)
-        Sine_source (batchsize, length, 1)
-        noise_source (batchsize, length 1)
-        """
-        # source for harmonic branch
-        with torch.no_grad():
-            sine_wavs, uv, _ = self.l_sin_gen(x)
-        sine_merge = self.l_tanh(self.l_linear(sine_wavs))
-
-        # source for noise branch, in the same shape as uv
-        noise = torch.randn_like(uv) * self.sine_amp / 3
-        return sine_merge, noise, uv
-def padDiff(x):
-    return F.pad(F.pad(x, (0,0,-1,1), 'constant', 0) - x, (0,0,0,-1), 'constant', 0)
-
-    
-class Generator(torch.nn.Module):
-    def __init__(self, style_dim, resblock_kernel_sizes, upsample_rates, upsample_initial_channel, resblock_dilation_sizes, upsample_kernel_sizes, gen_istft_n_fft, gen_istft_hop_size):
-        super(Generator, self).__init__()
-
-        self.num_kernels = len(resblock_kernel_sizes)
-        self.num_upsamples = len(upsample_rates)
-        resblock = AdaINResBlock1
-
-        self.m_source = SourceModuleHnNSF(
-                    sampling_rate=24000,
-                    upsample_scale=np.prod(upsample_rates) * gen_istft_hop_size,
-                    harmonic_num=8, voiced_threshod=10)
-        self.f0_upsamp = torch.nn.Upsample(scale_factor=np.prod(upsample_rates) * gen_istft_hop_size)
-        self.noise_convs = nn.ModuleList()
-        self.noise_res = nn.ModuleList()
-        
-        self.ups = nn.ModuleList()
-        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
-            self.ups.append(weight_norm(
-                ConvTranspose1d(upsample_initial_channel//(2**i), upsample_initial_channel//(2**(i+1)),
-                                k, u, padding=(k-u)//2)))
-
-        self.resblocks = nn.ModuleList()
-        for i in range(len(self.ups)):
-            ch = upsample_initial_channel//(2**(i+1))
-            for j, (k, d) in enumerate(zip(resblock_kernel_sizes,resblock_dilation_sizes)):
-                self.resblocks.append(resblock(ch, k, d, style_dim))
-                
-            c_cur = upsample_initial_channel // (2 ** (i + 1))
-            
-            if i + 1 < len(upsample_rates):  #
-                stride_f0 = np.prod(upsample_rates[i + 1:])
-                self.noise_convs.append(Conv1d(
-                    gen_istft_n_fft + 2, c_cur, kernel_size=stride_f0 * 2, stride=stride_f0, padding=(stride_f0+1) // 2))
-                self.noise_res.append(resblock(c_cur, 7, [1,3,5], style_dim))
-            else:
-                self.noise_convs.append(Conv1d(gen_istft_n_fft + 2, c_cur, kernel_size=1))
-                self.noise_res.append(resblock(c_cur, 11, [1,3,5], style_dim))
-                
-                
-        self.post_n_fft = gen_istft_n_fft
-        self.conv_post = weight_norm(Conv1d(ch, self.post_n_fft + 2, 7, 1, padding=3))
-        self.ups.apply(init_weights)
-        self.conv_post.apply(init_weights)
-        self.reflection_pad = torch.nn.ReflectionPad1d((1, 0))
-        self.stft = TorchSTFT(filter_length=gen_istft_n_fft, hop_length=gen_istft_hop_size, win_length=gen_istft_n_fft)
-        
-        
-    def forward(self, x, s, f0):
-        with torch.no_grad():
-            f0 = self.f0_upsamp(f0[:, None]).transpose(1, 2)  # bs,n,t
-
-            har_source, noi_source, uv = self.m_source(f0)
-            har_source = har_source.transpose(1, 2).squeeze(1)
-            har_spec, har_phase = self.stft.transform(har_source)
-            har = torch.cat([har_spec, har_phase], dim=1)
-        
-        for i in range(self.num_upsamples):
-            x = F.leaky_relu(x, LRELU_SLOPE)
-            x_source = self.noise_convs[i](har)
-            x_source = self.noise_res[i](x_source, s)
-
-            x = self.ups[i](x)
-            if i == self.num_upsamples - 1:
-                x = self.reflection_pad(x)
-
-            x = x + x_source
-            xs = None
-            for j in range(self.num_kernels):
-                if xs is None:
-                    xs = self.resblocks[i*self.num_kernels+j](x, s)
-                else:
-                    xs += self.resblocks[i*self.num_kernels+j](x, s)
-            x = xs / self.num_kernels
-        x = F.leaky_relu(x)
-        x = self.conv_post(x)
-        spec = torch.exp(x[:,:self.post_n_fft // 2 + 1, :])
-        phase = torch.sin(x[:, self.post_n_fft // 2 + 1:, :])
-        return self.stft.inverse(spec, phase)
-    
-    def fw_phase(self, x, s):
-        for i in range(self.num_upsamples):
-            x = F.leaky_relu(x, LRELU_SLOPE)
-            x = self.ups[i](x)
-            xs = None
-            for j in range(self.num_kernels):
-                if xs is None:
-                    xs = self.resblocks[i*self.num_kernels+j](x, s)
-                else:
-                    xs += self.resblocks[i*self.num_kernels+j](x, s)
-            x = xs / self.num_kernels
-        x = F.leaky_relu(x)
-        x = self.reflection_pad(x)
-        x = self.conv_post(x)
-        spec = torch.exp(x[:,:self.post_n_fft // 2 + 1, :])
-        phase = torch.sin(x[:, self.post_n_fft // 2 + 1:, :])
-        return spec, phase
-
-    def remove_weight_norm(self):
-        print('Removing weight norm...')
-        for l in self.ups:
-            remove_weight_norm(l)
-        for l in self.resblocks:
-            l.remove_weight_norm()
-        remove_weight_norm(self.conv_pre)
-        remove_weight_norm(self.conv_post)
-
-        
-class AdainResBlk1d(nn.Module):
-    def __init__(self, dim_in, dim_out, style_dim=64, actv=nn.LeakyReLU(0.2),
-                 upsample='none', dropout_p=0.0):
-        super().__init__()
-        self.actv = actv
-        self.upsample_type = upsample
-        self.upsample = UpSample1d(upsample)
-        self.learned_sc = dim_in != dim_out
-        self._build_weights(dim_in, dim_out, style_dim)
-        self.dropout = nn.Dropout(dropout_p)
-        
-        if upsample == 'none':
-            self.pool = nn.Identity()
-        else:
-            self.pool = weight_norm(nn.ConvTranspose1d(dim_in, dim_in, kernel_size=3, stride=2, groups=dim_in, padding=1, output_padding=1))
-        
-        
-    def _build_weights(self, dim_in, dim_out, style_dim):
-        self.conv1 = weight_norm(nn.Conv1d(dim_in, dim_out, 3, 1, 1))
-        self.conv2 = weight_norm(nn.Conv1d(dim_out, dim_out, 3, 1, 1))
-        self.norm1 = AdaIN1d(style_dim, dim_in)
-        self.norm2 = AdaIN1d(style_dim, dim_out)
-        if self.learned_sc:
-            self.conv1x1 = weight_norm(nn.Conv1d(dim_in, dim_out, 1, 1, 0, bias=False))
-
-    def _shortcut(self, x):
-        x = self.upsample(x)
-        if self.learned_sc:
-            x = self.conv1x1(x)
-        return x
-
-    def _residual(self, x, s):
-        x = self.norm1(x, s)
-        x = self.actv(x)
-        x = self.pool(x)
-        x = self.conv1(self.dropout(x))
-        x = self.norm2(x, s)
-        x = self.actv(x)
-        x = self.conv2(self.dropout(x))
-        return x
-
-    def forward(self, x, s):
-        out = self._residual(x, s)
-        out = (out + self._shortcut(x)) / np.sqrt(2)
-        return out
-    
-class UpSample1d(nn.Module):
-    def __init__(self, layer_type):
-        super().__init__()
-        self.layer_type = layer_type
-
-    def forward(self, x):
-        if self.layer_type == 'none':
-            return x
-        else:
-            return F.interpolate(x, scale_factor=2, mode='nearest')
-
-class Decoder(nn.Module):
-    def __init__(self, dim_in=512, F0_channel=512, style_dim=64, dim_out=80, 
-                resblock_kernel_sizes = [3,7,11],
-                upsample_rates = [10, 6],
-                upsample_initial_channel=512,
-                resblock_dilation_sizes=[[1,3,5], [1,3,5], [1,3,5]],
-                upsample_kernel_sizes=[20, 12], 
-                gen_istft_n_fft=20, gen_istft_hop_size=5):
-        super().__init__()
-        
-        self.decode = nn.ModuleList()
-        
-        self.encode = AdainResBlk1d(dim_in + 2, 1024, style_dim)
-        
-        self.decode.append(AdainResBlk1d(1024 + 2 + 64, 1024, style_dim))
-        self.decode.append(AdainResBlk1d(1024 + 2 + 64, 1024, style_dim))
-        self.decode.append(AdainResBlk1d(1024 + 2 + 64, 1024, style_dim))
-        self.decode.append(AdainResBlk1d(1024 + 2 + 64, 512, style_dim, upsample=True))
-
-        self.F0_conv = weight_norm(nn.Conv1d(1, 1, kernel_size=3, stride=2, groups=1, padding=1))
-        
-        self.N_conv = weight_norm(nn.Conv1d(1, 1, kernel_size=3, stride=2, groups=1, padding=1))
-        
-        self.asr_res = nn.Sequential(
-            weight_norm(nn.Conv1d(512, 64, kernel_size=1)),
-        )
-        
-        
-        self.generator = Generator(style_dim, resblock_kernel_sizes, upsample_rates, 
-                                   upsample_initial_channel, resblock_dilation_sizes, 
-                                   upsample_kernel_sizes, gen_istft_n_fft, gen_istft_hop_size)
-        
-    def forward(self, asr, F0_curve, N, s):
-        F0 = self.F0_conv(F0_curve.unsqueeze(1))
-        N = self.N_conv(N.unsqueeze(1))
-        
-        x = torch.cat([asr, F0, N], axis=1)
-        x = self.encode(x, s)
-        
-        asr_res = self.asr_res(asr)
-        
-        res = True
-        for block in self.decode:
-            if res:
-                x = torch.cat([x, asr_res, F0, N], axis=1)
-            x = block(x, s)
-            if block.upsample_type != "none":
-                res = False
-                
-        x = self.generator(x, s, F0_curve)
-        return x

backend/python/kokoro/kokoro.py

@@ -1,166 +0,0 @@
-# https://huggingface.co/hexgrad/Kokoro-82M/blob/main/kokoro.py
-import phonemizer
-import re
-import torch
-import numpy as np
-
-def split_num(num):
-    num = num.group()
-    if '.' in num:
-        return num
-    elif ':' in num:
-        h, m = [int(n) for n in num.split(':')]
-        if m == 0:
-            return f"{h} o'clock"
-        elif m < 10:
-            return f'{h} oh {m}'
-        return f'{h} {m}'
-    year = int(num[:4])
-    if year < 1100 or year % 1000 < 10:
-        return num
-    left, right = num[:2], int(num[2:4])
-    s = 's' if num.endswith('s') else ''
-    if 100 <= year % 1000 <= 999:
-        if right == 0:
-            return f'{left} hundred{s}'
-        elif right < 10:
-            return f'{left} oh {right}{s}'
-    return f'{left} {right}{s}'
-
-def flip_money(m):
-    m = m.group()
-    bill = 'dollar' if m[0] == '$' else 'pound'
-    if m[-1].isalpha():
-        return f'{m[1:]} {bill}s'
-    elif '.' not in m:
-        s = '' if m[1:] == '1' else 's'
-        return f'{m[1:]} {bill}{s}'
-    b, c = m[1:].split('.')
-    s = '' if b == '1' else 's'
-    c = int(c.ljust(2, '0'))
-    coins = f"cent{'' if c == 1 else 's'}" if m[0] == '$' else ('penny' if c == 1 else 'pence')
-    return f'{b} {bill}{s} and {c} {coins}'
-
-def point_num(num):
-    a, b = num.group().split('.')
-    return ' point '.join([a, ' '.join(b)])
-
-def normalize_text(text):
-    text = text.replace(chr(8216), "'").replace(chr(8217), "'")
-    text = text.replace('«', chr(8220)).replace('»', chr(8221))
-    text = text.replace(chr(8220), '"').replace(chr(8221), '"')
-    text = text.replace('(', '«').replace(')', '»')
-    for a, b in zip('、。！，：；？', ',.!,:;?'):
-        text = text.replace(a, b+' ')
-    text = re.sub(r'[^\S \n]', ' ', text)
-    text = re.sub(r'  +', ' ', text)
-    text = re.sub(r'(?<=\n) +(?=\n)', '', text)
-    text = re.sub(r'\bD[Rr]\.(?= [A-Z])', 'Doctor', text)
-    text = re.sub(r'\b(?:Mr\.|MR\.(?= [A-Z]))', 'Mister', text)
-    text = re.sub(r'\b(?:Ms\.|MS\.(?= [A-Z]))', 'Miss', text)
-    text = re.sub(r'\b(?:Mrs\.|MRS\.(?= [A-Z]))', 'Mrs', text)
-    text = re.sub(r'\betc\.(?! [A-Z])', 'etc', text)
-    text = re.sub(r'(?i)\b(y)eah?\b', r"\1e'a", text)
-    text = re.sub(r'\d*\.\d+|\b\d{4}s?\b|(?<!:)\b(?:[1-9]|1[0-2]):[0-5]\d\b(?!:)', split_num, text)
-    text = re.sub(r'(?<=\d),(?=\d)', '', text)
-    text = re.sub(r'(?i)[$£]\d+(?:\.\d+)?(?: hundred| thousand| (?:[bm]|tr)illion)*\b|[$£]\d+\.\d\d?\b', flip_money, text)
-    text = re.sub(r'\d*\.\d+', point_num, text)
-    text = re.sub(r'(?<=\d)-(?=\d)', ' to ', text)
-    text = re.sub(r'(?<=\d)S', ' S', text)
-    text = re.sub(r"(?<=[BCDFGHJ-NP-TV-Z])'?s\b", "'S", text)
-    text = re.sub(r"(?<=X')S\b", 's', text)
-    text = re.sub(r'(?:[A-Za-z]\.){2,} [a-z]', lambda m: m.group().replace('.', '-'), text)
-    text = re.sub(r'(?i)(?<=[A-Z])\.(?=[A-Z])', '-', text)
-    return text.strip()
-
-def get_vocab():
-    _pad = "$"
-    _punctuation = ';:,.!?¡¿—…"«»“” '
-    _letters = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz'
-    _letters_ipa = "ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑→↗↘'̩'ᵻ"
-    symbols = [_pad] + list(_punctuation) + list(_letters) + list(_letters_ipa)
-    dicts = {}
-    for i in range(len((symbols))):
-        dicts[symbols[i]] = i
-    return dicts
-
-VOCAB = get_vocab()
-def tokenize(ps):
-    return [i for i in map(VOCAB.get, ps) if i is not None]
-
-phonemizers = dict(
-    a=phonemizer.backend.EspeakBackend(language='en-us', preserve_punctuation=True, with_stress=True),
-    b=phonemizer.backend.EspeakBackend(language='en-gb', preserve_punctuation=True, with_stress=True),
-)
-def phonemize(text, lang, norm=True):
-    if norm:
-        text = normalize_text(text)
-    ps = phonemizers[lang].phonemize([text])
-    ps = ps[0] if ps else ''
-    # https://en.wiktionary.org/wiki/kokoro#English
-    ps = ps.replace('kəkˈoːɹoʊ', 'kˈoʊkəɹoʊ').replace('kəkˈɔːɹəʊ', 'kˈəʊkəɹəʊ')
-    ps = ps.replace('ʲ', 'j').replace('r', 'ɹ').replace('x', 'k').replace('ɬ', 'l')
-    ps = re.sub(r'(?<=[a-zɹː])(?=hˈʌndɹɪd)', ' ', ps)
-    ps = re.sub(r' z(?=[;:,.!?¡¿—…"«»“” ]|$)', 'z', ps)
-    if lang == 'a':
-        ps = re.sub(r'(?<=nˈaɪn)ti(?!ː)', 'di', ps)
-    ps = ''.join(filter(lambda p: p in VOCAB, ps))
-    return ps.strip()
-
-def length_to_mask(lengths):
-    mask = torch.arange(lengths.max()).unsqueeze(0).expand(lengths.shape[0], -1).type_as(lengths)
-    mask = torch.gt(mask+1, lengths.unsqueeze(1))
-    return mask
-
-@torch.no_grad()
-def forward(model, tokens, ref_s, speed):
-    device = ref_s.device
-    tokens = torch.LongTensor([[0, *tokens, 0]]).to(device)
-    input_lengths = torch.LongTensor([tokens.shape[-1]]).to(device)
-    text_mask = length_to_mask(input_lengths).to(device)
-    bert_dur = model.bert(tokens, attention_mask=(~text_mask).int())
-    d_en = model.bert_encoder(bert_dur).transpose(-1, -2)
-    s = ref_s[:, 128:]
-    d = model.predictor.text_encoder(d_en, s, input_lengths, text_mask)
-    x, _ = model.predictor.lstm(d)
-    duration = model.predictor.duration_proj(x)
-    duration = torch.sigmoid(duration).sum(axis=-1) / speed
-    pred_dur = torch.round(duration).clamp(min=1).long()
-    pred_aln_trg = torch.zeros(input_lengths, pred_dur.sum().item())
-    c_frame = 0
-    for i in range(pred_aln_trg.size(0)):
-        pred_aln_trg[i, c_frame:c_frame + pred_dur[0,i].item()] = 1
-        c_frame += pred_dur[0,i].item()
-    en = d.transpose(-1, -2) @ pred_aln_trg.unsqueeze(0).to(device)
-    F0_pred, N_pred = model.predictor.F0Ntrain(en, s)
-    t_en = model.text_encoder(tokens, input_lengths, text_mask)
-    asr = t_en @ pred_aln_trg.unsqueeze(0).to(device)
-    return model.decoder(asr, F0_pred, N_pred, ref_s[:, :128]).squeeze().cpu().numpy()
-
-def generate(model, text, voicepack, lang='a', speed=1, ps=None):
-    ps = ps or phonemize(text, lang)
-    tokens = tokenize(ps)
-    if not tokens:
-        return None
-    elif len(tokens) > 510:
-        tokens = tokens[:510]
-        print('Truncated to 510 tokens')
-    ref_s = voicepack[len(tokens)]
-    out = forward(model, tokens, ref_s, speed)
-    ps = ''.join(next(k for k, v in VOCAB.items() if i == v) for i in tokens)
-    return out, ps
-
-def generate_full(model, text, voicepack, lang='a', speed=1, ps=None):
-    ps = ps or phonemize(text, lang)
-    tokens = tokenize(ps)
-    if not tokens:
-        return None
-    outs = []
-    loop_count = len(tokens)//510 + (1 if len(tokens) % 510 != 0 else 0)
-    for i in range(loop_count):
-        ref_s = voicepack[len(tokens[i*510:(i+1)*510])]
-        out = forward(model, tokens[i*510:(i+1)*510], ref_s, speed)
-        outs.append(out)
-    outs = np.concatenate(outs)
-    ps = ''.join(next(k for k, v in VOCAB.items() if i == v) for i in tokens)
-    return outs, ps

backend/python/kokoro/models.py

@@ -1,373 +0,0 @@
-# https://github.com/yl4579/StyleTTS2/blob/main/models.py
-# https://huggingface.co/hexgrad/Kokoro-82M/blob/main/models.py
-from istftnet import AdaIN1d, Decoder
-from munch import Munch
-from pathlib import Path
-from plbert import load_plbert
-from torch.nn.utils import weight_norm, spectral_norm
-import json
-import numpy as np
-import os
-import os.path as osp
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-class LinearNorm(torch.nn.Module):
-    def __init__(self, in_dim, out_dim, bias=True, w_init_gain='linear'):
-        super(LinearNorm, self).__init__()
-        self.linear_layer = torch.nn.Linear(in_dim, out_dim, bias=bias)
-
-        torch.nn.init.xavier_uniform_(
-            self.linear_layer.weight,
-            gain=torch.nn.init.calculate_gain(w_init_gain))
-
-    def forward(self, x):
-        return self.linear_layer(x)
-
-class LayerNorm(nn.Module):
-    def __init__(self, channels, eps=1e-5):
-        super().__init__()
-        self.channels = channels
-        self.eps = eps
-
-        self.gamma = nn.Parameter(torch.ones(channels))
-        self.beta = nn.Parameter(torch.zeros(channels))
-
-    def forward(self, x):
-        x = x.transpose(1, -1)
-        x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps)
-        return x.transpose(1, -1)
-    
-class TextEncoder(nn.Module):
-    def __init__(self, channels, kernel_size, depth, n_symbols, actv=nn.LeakyReLU(0.2)):
-        super().__init__()
-        self.embedding = nn.Embedding(n_symbols, channels)
-
-        padding = (kernel_size - 1) // 2
-        self.cnn = nn.ModuleList()
-        for _ in range(depth):
-            self.cnn.append(nn.Sequential(
-                weight_norm(nn.Conv1d(channels, channels, kernel_size=kernel_size, padding=padding)),
-                LayerNorm(channels),
-                actv,
-                nn.Dropout(0.2),
-            ))
-        # self.cnn = nn.Sequential(*self.cnn)
-
-        self.lstm = nn.LSTM(channels, channels//2, 1, batch_first=True, bidirectional=True)
-
-    def forward(self, x, input_lengths, m):
-        x = self.embedding(x)  # [B, T, emb]
-        x = x.transpose(1, 2)  # [B, emb, T]
-        m = m.to(input_lengths.device).unsqueeze(1)
-        x.masked_fill_(m, 0.0)
-        
-        for c in self.cnn:
-            x = c(x)
-            x.masked_fill_(m, 0.0)
-            
-        x = x.transpose(1, 2)  # [B, T, chn]
-
-        input_lengths = input_lengths.cpu().numpy()
-        x = nn.utils.rnn.pack_padded_sequence(
-            x, input_lengths, batch_first=True, enforce_sorted=False)
-
-        self.lstm.flatten_parameters()
-        x, _ = self.lstm(x)
-        x, _ = nn.utils.rnn.pad_packed_sequence(
-            x, batch_first=True)
-                
-        x = x.transpose(-1, -2)
-        x_pad = torch.zeros([x.shape[0], x.shape[1], m.shape[-1]])
-
-        x_pad[:, :, :x.shape[-1]] = x
-        x = x_pad.to(x.device)
-        
-        x.masked_fill_(m, 0.0)
-        
-        return x
-
-    def inference(self, x):
-        x = self.embedding(x)
-        x = x.transpose(1, 2)
-        x = self.cnn(x)
-        x = x.transpose(1, 2)
-        self.lstm.flatten_parameters()
-        x, _ = self.lstm(x)
-        return x
-    
-    def length_to_mask(self, lengths):
-        mask = torch.arange(lengths.max()).unsqueeze(0).expand(lengths.shape[0], -1).type_as(lengths)
-        mask = torch.gt(mask+1, lengths.unsqueeze(1))
-        return mask
-
-
-class UpSample1d(nn.Module):
-    def __init__(self, layer_type):
-        super().__init__()
-        self.layer_type = layer_type
-
-    def forward(self, x):
-        if self.layer_type == 'none':
-            return x
-        else:
-            return F.interpolate(x, scale_factor=2, mode='nearest')
-
-class AdainResBlk1d(nn.Module):
-    def __init__(self, dim_in, dim_out, style_dim=64, actv=nn.LeakyReLU(0.2),
-                 upsample='none', dropout_p=0.0):
-        super().__init__()
-        self.actv = actv
-        self.upsample_type = upsample
-        self.upsample = UpSample1d(upsample)
-        self.learned_sc = dim_in != dim_out
-        self._build_weights(dim_in, dim_out, style_dim)
-        self.dropout = nn.Dropout(dropout_p)
-        
-        if upsample == 'none':
-            self.pool = nn.Identity()
-        else:
-            self.pool = weight_norm(nn.ConvTranspose1d(dim_in, dim_in, kernel_size=3, stride=2, groups=dim_in, padding=1, output_padding=1))
-        
-        
-    def _build_weights(self, dim_in, dim_out, style_dim):
-        self.conv1 = weight_norm(nn.Conv1d(dim_in, dim_out, 3, 1, 1))
-        self.conv2 = weight_norm(nn.Conv1d(dim_out, dim_out, 3, 1, 1))
-        self.norm1 = AdaIN1d(style_dim, dim_in)
-        self.norm2 = AdaIN1d(style_dim, dim_out)
-        if self.learned_sc:
-            self.conv1x1 = weight_norm(nn.Conv1d(dim_in, dim_out, 1, 1, 0, bias=False))
-
-    def _shortcut(self, x):
-        x = self.upsample(x)
-        if self.learned_sc:
-            x = self.conv1x1(x)
-        return x
-
-    def _residual(self, x, s):
-        x = self.norm1(x, s)
-        x = self.actv(x)
-        x = self.pool(x)
-        x = self.conv1(self.dropout(x))
-        x = self.norm2(x, s)
-        x = self.actv(x)
-        x = self.conv2(self.dropout(x))
-        return x
-
-    def forward(self, x, s):
-        out = self._residual(x, s)
-        out = (out + self._shortcut(x)) / np.sqrt(2)
-        return out
-    
-class AdaLayerNorm(nn.Module):
-    def __init__(self, style_dim, channels, eps=1e-5):
-        super().__init__()
-        self.channels = channels
-        self.eps = eps
-
-        self.fc = nn.Linear(style_dim, channels*2)
-
-    def forward(self, x, s):
-        x = x.transpose(-1, -2)
-        x = x.transpose(1, -1)
-                
-        h = self.fc(s)
-        h = h.view(h.size(0), h.size(1), 1)
-        gamma, beta = torch.chunk(h, chunks=2, dim=1)
-        gamma, beta = gamma.transpose(1, -1), beta.transpose(1, -1)
-        
-        
-        x = F.layer_norm(x, (self.channels,), eps=self.eps)
-        x = (1 + gamma) * x + beta
-        return x.transpose(1, -1).transpose(-1, -2)
-
-class ProsodyPredictor(nn.Module):
-
-    def __init__(self, style_dim, d_hid, nlayers, max_dur=50, dropout=0.1):
-        super().__init__() 
-        
-        self.text_encoder = DurationEncoder(sty_dim=style_dim, 
-                                            d_model=d_hid,
-                                            nlayers=nlayers, 
-                                            dropout=dropout)
-
-        self.lstm = nn.LSTM(d_hid + style_dim, d_hid // 2, 1, batch_first=True, bidirectional=True)
-        self.duration_proj = LinearNorm(d_hid, max_dur)
-        
-        self.shared = nn.LSTM(d_hid + style_dim, d_hid // 2, 1, batch_first=True, bidirectional=True)
-        self.F0 = nn.ModuleList()
-        self.F0.append(AdainResBlk1d(d_hid, d_hid, style_dim, dropout_p=dropout))
-        self.F0.append(AdainResBlk1d(d_hid, d_hid // 2, style_dim, upsample=True, dropout_p=dropout))
-        self.F0.append(AdainResBlk1d(d_hid // 2, d_hid // 2, style_dim, dropout_p=dropout))
-
-        self.N = nn.ModuleList()
-        self.N.append(AdainResBlk1d(d_hid, d_hid, style_dim, dropout_p=dropout))
-        self.N.append(AdainResBlk1d(d_hid, d_hid // 2, style_dim, upsample=True, dropout_p=dropout))
-        self.N.append(AdainResBlk1d(d_hid // 2, d_hid // 2, style_dim, dropout_p=dropout))
-        
-        self.F0_proj = nn.Conv1d(d_hid // 2, 1, 1, 1, 0)
-        self.N_proj = nn.Conv1d(d_hid // 2, 1, 1, 1, 0)
-
-
-    def forward(self, texts, style, text_lengths, alignment, m):
-        d = self.text_encoder(texts, style, text_lengths, m)
-        
-        batch_size = d.shape[0]
-        text_size = d.shape[1]
-        
-        # predict duration
-        input_lengths = text_lengths.cpu().numpy()
-        x = nn.utils.rnn.pack_padded_sequence(
-            d, input_lengths, batch_first=True, enforce_sorted=False)
-        
-        m = m.to(text_lengths.device).unsqueeze(1)
-        
-        self.lstm.flatten_parameters()
-        x, _ = self.lstm(x)
-        x, _ = nn.utils.rnn.pad_packed_sequence(
-            x, batch_first=True)
-        
-        x_pad = torch.zeros([x.shape[0], m.shape[-1], x.shape[-1]])
-
-        x_pad[:, :x.shape[1], :] = x
-        x = x_pad.to(x.device)
-                
-        duration = self.duration_proj(nn.functional.dropout(x, 0.5, training=self.training))
-        
-        en = (d.transpose(-1, -2) @ alignment)
-
-        return duration.squeeze(-1), en
-    
-    def F0Ntrain(self, x, s):
-        x, _ = self.shared(x.transpose(-1, -2))
-        
-        F0 = x.transpose(-1, -2)
-        for block in self.F0:
-            F0 = block(F0, s)
-        F0 = self.F0_proj(F0)
-
-        N = x.transpose(-1, -2)
-        for block in self.N:
-            N = block(N, s)
-        N = self.N_proj(N)
-        
-        return F0.squeeze(1), N.squeeze(1)
-    
-    def length_to_mask(self, lengths):
-        mask = torch.arange(lengths.max()).unsqueeze(0).expand(lengths.shape[0], -1).type_as(lengths)
-        mask = torch.gt(mask+1, lengths.unsqueeze(1))
-        return mask
-
-class DurationEncoder(nn.Module):
-
-    def __init__(self, sty_dim, d_model, nlayers, dropout=0.1):
-        super().__init__()
-        self.lstms = nn.ModuleList()
-        for _ in range(nlayers):
-            self.lstms.append(nn.LSTM(d_model + sty_dim, 
-                                 d_model // 2, 
-                                 num_layers=1, 
-                                 batch_first=True, 
-                                 bidirectional=True, 
-                                 dropout=dropout))
-            self.lstms.append(AdaLayerNorm(sty_dim, d_model))
-        
-        
-        self.dropout = dropout
-        self.d_model = d_model
-        self.sty_dim = sty_dim
-
-    def forward(self, x, style, text_lengths, m):
-        masks = m.to(text_lengths.device)
-        
-        x = x.permute(2, 0, 1)
-        s = style.expand(x.shape[0], x.shape[1], -1)
-        x = torch.cat([x, s], axis=-1)
-        x.masked_fill_(masks.unsqueeze(-1).transpose(0, 1), 0.0)
-                
-        x = x.transpose(0, 1)
-        input_lengths = text_lengths.cpu().numpy()
-        x = x.transpose(-1, -2)
-        
-        for block in self.lstms:
-            if isinstance(block, AdaLayerNorm):
-                x = block(x.transpose(-1, -2), style).transpose(-1, -2)
-                x = torch.cat([x, s.permute(1, -1, 0)], axis=1)
-                x.masked_fill_(masks.unsqueeze(-1).transpose(-1, -2), 0.0)
-            else:
-                x = x.transpose(-1, -2)
-                x = nn.utils.rnn.pack_padded_sequence(
-                    x, input_lengths, batch_first=True, enforce_sorted=False)
-                block.flatten_parameters()
-                x, _ = block(x)
-                x, _ = nn.utils.rnn.pad_packed_sequence(
-                    x, batch_first=True)
-                x = F.dropout(x, p=self.dropout, training=self.training)
-                x = x.transpose(-1, -2)
-                
-                x_pad = torch.zeros([x.shape[0], x.shape[1], m.shape[-1]])
-
-                x_pad[:, :, :x.shape[-1]] = x
-                x = x_pad.to(x.device)
-        
-        return x.transpose(-1, -2)
-    
-    def inference(self, x, style):
-        x = self.embedding(x.transpose(-1, -2)) * np.sqrt(self.d_model)
-        style = style.expand(x.shape[0], x.shape[1], -1)
-        x = torch.cat([x, style], axis=-1)
-        src = self.pos_encoder(x)
-        output = self.transformer_encoder(src).transpose(0, 1)
-        return output
-    
-    def length_to_mask(self, lengths):
-        mask = torch.arange(lengths.max()).unsqueeze(0).expand(lengths.shape[0], -1).type_as(lengths)
-        mask = torch.gt(mask+1, lengths.unsqueeze(1))
-        return mask
-
-# https://github.com/yl4579/StyleTTS2/blob/main/utils.py
-def recursive_munch(d):
-    if isinstance(d, dict):
-        return Munch((k, recursive_munch(v)) for k, v in d.items())
-    elif isinstance(d, list):
-        return [recursive_munch(v) for v in d]
-    else:
-        return d
-
-def build_model(path, device):
-    config = Path(__file__).parent / 'config.json'
-    assert config.exists(), f'Config path incorrect: config.json not found at {config}'
-    with open(config, 'r') as r:
-        args = recursive_munch(json.load(r))
-    assert args.decoder.type == 'istftnet', f'Unknown decoder type: {args.decoder.type}'
-    decoder = Decoder(dim_in=args.hidden_dim, style_dim=args.style_dim, dim_out=args.n_mels,
-            resblock_kernel_sizes = args.decoder.resblock_kernel_sizes,
-            upsample_rates = args.decoder.upsample_rates,
-            upsample_initial_channel=args.decoder.upsample_initial_channel,
-            resblock_dilation_sizes=args.decoder.resblock_dilation_sizes,
-            upsample_kernel_sizes=args.decoder.upsample_kernel_sizes,
-            gen_istft_n_fft=args.decoder.gen_istft_n_fft, gen_istft_hop_size=args.decoder.gen_istft_hop_size)
-    text_encoder = TextEncoder(channels=args.hidden_dim, kernel_size=5, depth=args.n_layer, n_symbols=args.n_token)
-    predictor = ProsodyPredictor(style_dim=args.style_dim, d_hid=args.hidden_dim, nlayers=args.n_layer, max_dur=args.max_dur, dropout=args.dropout)
-    bert = load_plbert()
-    bert_encoder = nn.Linear(bert.config.hidden_size, args.hidden_dim)
-    for parent in [bert, bert_encoder, predictor, decoder, text_encoder]:
-        for child in parent.children():
-            if isinstance(child, nn.RNNBase):
-                child.flatten_parameters()
-    model = Munch(
-        bert=bert.to(device).eval(),
-        bert_encoder=bert_encoder.to(device).eval(),
-        predictor=predictor.to(device).eval(),
-        decoder=decoder.to(device).eval(),
-        text_encoder=text_encoder.to(device).eval(),
-    )
-    for key, state_dict in torch.load(path, map_location='cpu', weights_only=True)['net'].items():
-        assert key in model, key
-        try:
-            model[key].load_state_dict(state_dict)
-        except:
-            state_dict = {k[7:]: v for k, v in state_dict.items()}
-            model[key].load_state_dict(state_dict, strict=False)
-    return model

backend/python/kokoro/plbert.py

@@ -1,16 +0,0 @@
-# https://huggingface.co/hexgrad/Kokoro-82M/blob/main/plbert.py
-# https://github.com/yl4579/StyleTTS2/blob/main/Utils/PLBERT/util.py
-from transformers import AlbertConfig, AlbertModel
-
-class CustomAlbert(AlbertModel):
-    def forward(self, *args, **kwargs):
-        # Call the original forward method
-        outputs = super().forward(*args, **kwargs)
-        # Only return the last_hidden_state
-        return outputs.last_hidden_state
-
-def load_plbert():
-    plbert_config = {'vocab_size': 178, 'hidden_size': 768, 'num_attention_heads': 12, 'intermediate_size': 2048, 'max_position_embeddings': 512, 'num_hidden_layers': 12, 'dropout': 0.1}
-    albert_base_configuration = AlbertConfig(**plbert_config)
-    bert = CustomAlbert(albert_base_configuration)
-    return bert

backend/python/kokoro/requirements-cpu.txt

@@ -1,2 +1,6 @@
-torch==2.4.1
-transformers
+--extra-index-url https://download.pytorch.org/whl/cpu
+transformers
+accelerate
+torch
+kokoro
+soundfile

backend/python/kokoro/requirements-cublas11.txt

@@ -1,3 +1,7 @@
 --extra-index-url https://download.pytorch.org/whl/cu118
-torch==2.4.1+cu118
-transformers
+torch==2.7.1+cu118
+torchaudio==2.7.1+cu118
+transformers
+accelerate
+kokoro
+soundfile

backend/python/kokoro/requirements-cublas12.txt

@@ -1,2 +1,6 @@
-torch==2.4.1
-transformers
+torch==2.7.1
+torchaudio==2.7.1
+transformers
+accelerate
+kokoro
+soundfile

backend/python/kokoro/requirements-hipblas.txt

@@ -1,3 +1,7 @@
---extra-index-url https://download.pytorch.org/whl/rocm6.0
-torch==2.4.1+rocm6.0
-transformers
+--extra-index-url https://download.pytorch.org/whl/rocm6.3
+torch==2.7.1+rocm6.3
+torchaudio==2.7.1+rocm6.3
+transformers
+accelerate
+kokoro
+soundfile

backend/python/kokoro/requirements-intel.txt

@@ -1,5 +1,11 @@
 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
-intel-extension-for-pytorch==2.3.110+xpu
-torch==2.3.1+cxx11.abi
-oneccl_bind_pt==2.3.100+xpu
-transformers
+intel-extension-for-pytorch==2.8.10+xpu
+torch==2.5.1+cxx11.abi
+oneccl_bind_pt==2.8.0+xpu
+torchaudio==2.5.1+cxx11.abi
+optimum[openvino]
+setuptools
+transformers==4.48.3
+accelerate
+kokoro
+soundfile

backend/python/kokoro/requirements.txt

@@ -1,7 +1,6 @@
 grpcio==1.71.0
 protobuf
-phonemizer
-scipy
-munch
-setuptools
-soundfile
+certifi
+packaging==24.1
+pip
+chardet

backend/python/kokoro/test.py

@@ -0,0 +1,87 @@
+"""
+A test script to test the gRPC service
+"""
+import unittest
+import subprocess
+import time
+import backend_pb2
+import backend_pb2_grpc
+
+import grpc
+
+
+class TestBackendServicer(unittest.TestCase):
+    """
+    TestBackendServicer is the class that tests the gRPC service
+    """
+    def setUp(self):
+        """
+        This method sets up the gRPC service by starting the server
+        """
+        self.service = subprocess.Popen(["python3", "backend.py", "--addr", "localhost:50051"])
+        time.sleep(30)
+
+    def tearDown(self) -> None:
+        """
+        This method tears down the gRPC service by terminating the server
+        """
+        self.service.terminate()
+        self.service.wait()
+
+    def test_server_startup(self):
+        """
+        This method tests if the server starts up successfully
+        """
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.Health(backend_pb2.HealthMessage())
+                self.assertEqual(response.message, b'OK')
+        except Exception as err:
+            print(err)
+            self.fail("Server failed to start")
+        finally:
+            self.tearDown()
+
+    def test_load_model(self):
+        """
+        This method tests if the Kokoro pipeline is loaded successfully
+        """
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.LoadModel(backend_pb2.ModelOptions(language="a"))
+                print(response)
+                self.assertTrue(response.success)
+                self.assertEqual(response.message, "Kokoro TTS pipeline loaded successfully")
+        except Exception as err:
+            print(err)
+            self.fail("LoadModel service failed")
+        finally:
+            self.tearDown()
+
+    def test_tts(self):
+        """
+        This method tests if the TTS generation works successfully
+        """
+        try:
+            self.setUp()
+            with grpc.insecure_channel("localhost:50051") as channel:
+                stub = backend_pb2_grpc.BackendStub(channel)
+                response = stub.LoadModel(backend_pb2.ModelOptions(language="a"))
+                self.assertTrue(response.success)
+                tts_request = backend_pb2.TTSRequest(
+                    text="Kokoro is an open-weight TTS model with 82 million parameters.",
+                    voice="af_heart",
+                    dst="test_output.wav"
+                )
+                tts_response = stub.TTS(tts_request)
+                self.assertIsNotNone(tts_response)
+                self.assertTrue(tts_response.success)
+        except Exception as err:
+            print(err)
+            self.fail("TTS service failed")
+        finally:
+            self.tearDown()

backend/python/transformers/backend.py

@@ -22,7 +22,7 @@ import torch.cuda
 
 XPU=os.environ.get("XPU", "0") == "1"
 from transformers import AutoTokenizer, AutoModel, set_seed, TextIteratorStreamer, StoppingCriteriaList, StopStringCriteria, MambaConfig, MambaForCausalLM
-from transformers import AutoProcessor, MusicgenForConditionalGeneration
+from transformers import AutoProcessor, MusicgenForConditionalGeneration, DiaForConditionalGeneration
 from scipy.io import wavfile
 import outetts
 from sentence_transformers import SentenceTransformer
@@ -90,6 +90,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         self.CUDA = torch.cuda.is_available()
         self.OV=False
         self.OuteTTS=False
+        self.DiaTTS=False
         self.SentenceTransformer = False
 
         device_map="cpu"
@@ -97,6 +98,30 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         quantization = None
         autoTokenizer = True
 
+        # Parse options from request.Options
+        self.options = {}
+        options = request.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
+        # Example options: ["max_new_tokens:3072", "guidance_scale:3.0", "temperature:1.8", "top_p:0.90", "top_k:45"]
+        for opt in options:
+            if ":" not in opt:
+                continue
+            key, value = opt.split(":", 1)
+            # if value is a number, convert it to the appropriate type
+            try:
+                if "." in value:
+                    value = float(value)
+                else:
+                    value = int(value)
+            except ValueError:
+                # Keep as string if conversion fails
+                pass
+            self.options[key] = value
+
+        print(f"Parsed options: {self.options}", file=sys.stderr)
+
         if self.CUDA:
             from transformers import BitsAndBytesConfig, AutoModelForCausalLM
             if request.MainGPU:
@@ -202,6 +227,16 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 autoTokenizer = False
                 self.processor = AutoProcessor.from_pretrained(model_name)
                 self.model = MusicgenForConditionalGeneration.from_pretrained(model_name)
+            elif request.Type == "DiaForConditionalGeneration":
+                autoTokenizer = False
+                print("DiaForConditionalGeneration", file=sys.stderr)
+                self.processor = AutoProcessor.from_pretrained(model_name)
+                self.model = DiaForConditionalGeneration.from_pretrained(model_name)
+                if self.CUDA:
+                    self.model = self.model.to("cuda")
+                    self.processor = self.processor.to("cuda")
+                print("DiaForConditionalGeneration loaded", file=sys.stderr)
+                self.DiaTTS = True
             elif request.Type == "OuteTTS":
                 autoTokenizer = False
                 options = request.Options
@@ -262,7 +297,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             elif hasattr(self.model, 'config') and hasattr(self.model.config, 'max_position_embeddings'):
                 self.max_tokens = self.model.config.max_position_embeddings
             else:
-                self.max_tokens = 512
+                self.max_tokens = self.options.get("max_new_tokens", 512)
  
             if autoTokenizer:
                 self.tokenizer = AutoTokenizer.from_pretrained(model_name, use_safetensors=True)
@@ -485,16 +520,15 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                     return_tensors="pt",
                 )
             
-            tokens = 256
             if request.HasField('duration'):
                 tokens = int(request.duration * 51.2) # 256 tokens = 5 seconds, therefore 51.2 tokens is one second
-            guidance = 3.0
+            guidance = self.options.get("guidance_scale", 3.0)
             if request.HasField('temperature'):
                 guidance = request.temperature
-            dosample = True
+            dosample = self.options.get("do_sample", True)
             if request.HasField('sample'):
                 dosample = request.sample
-            audio_values = self.model.generate(**inputs, do_sample=dosample, guidance_scale=guidance, max_new_tokens=tokens)
+            audio_values = self.model.generate(**inputs, do_sample=dosample, guidance_scale=guidance, max_new_tokens=self.max_tokens)
             print("[transformers-musicgen] SoundGeneration generated!", file=sys.stderr)
             sampling_rate = self.model.config.audio_encoder.sampling_rate
             wavfile.write(request.dst, rate=sampling_rate, data=audio_values[0, 0].numpy())
@@ -506,13 +540,59 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
             return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
         return backend_pb2.Result(success=True)
 
-    def OuteTTS(self, request, context):
+
+    def CallDiaTTS(self, request, context):
+        """
+        Generates dialogue audio using the Dia model.
+        
+        Args:
+            request: A TTSRequest containing text dialogue and generation parameters
+            context: The gRPC context
+            
+        Returns:
+            A Result object indicating success or failure
+        """
+        try:
+            print("[DiaTTS] generating dialogue audio", file=sys.stderr)
+            
+            # Prepare text input - expect dialogue format like [S1] ... [S2] ...
+            text = [request.text]
+            
+            # Process the input
+            inputs = self.processor(text=text, padding=True, return_tensors="pt")
+            
+            # Generate audio with parameters from options or defaults
+            generation_params = {
+                **inputs,
+                "max_new_tokens": self.max_tokens,
+                "guidance_scale": self.options.get("guidance_scale", 3.0),
+                "temperature": self.options.get("temperature", 1.8),
+                "top_p": self.options.get("top_p", 0.90),
+                "top_k": self.options.get("top_k", 45)
+            }
+            
+            outputs = self.model.generate(**generation_params)
+            
+            # Decode and save audio
+            outputs = self.processor.batch_decode(outputs)
+            self.processor.save_audio(outputs, request.dst)
+            
+            print("[DiaTTS] Generated dialogue audio", file=sys.stderr)
+            print("[DiaTTS] Audio saved to", request.dst, file=sys.stderr)
+            print("[DiaTTS] Dialogue generation done", file=sys.stderr)
+            
+        except Exception as err:
+            return backend_pb2.Result(success=False, message=f"Unexpected {err=}, {type(err)=}")
+        return backend_pb2.Result(success=True)
+
+
+    def CallOuteTTS(self, request, context):
         try:
             print("[OuteTTS] generating TTS", file=sys.stderr)
             gen_cfg = outetts.GenerationConfig(
                 text="Speech synthesis is the artificial production of human speech.",
-                temperature=0.1,
-                repetition_penalty=1.1,
+                temperature=self.options.get("temperature", 0.1),
+                repetition_penalty=self.options.get("repetition_penalty", 1.1),
                 max_length=self.max_tokens,
                 speaker=self.speaker,
                 # voice_characteristics="upbeat enthusiasm, friendliness, clarity, professionalism, and trustworthiness"
@@ -528,7 +608,11 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
 # The TTS endpoint is older, and provides fewer features, but exists for compatibility reasons
     def TTS(self, request, context):
         if self.OuteTTS:
-            return self.OuteTTS(request, context)
+            return self.CallOuteTTS(request, context)
+        
+        if self.DiaTTS:
+            print("DiaTTS", file=sys.stderr)
+            return self.CallDiaTTS(request, context)
 
         model_name = request.model
         try:

backend/python/transformers/requirements-cpu.txt

@@ -1,9 +1,9 @@
-torch==2.4.1
+torch==2.7.1
 llvmlite==0.43.0
 numba==0.60.0
 accelerate
 transformers
 bitsandbytes
 outetts
-sentence-transformers==3.4.1
+sentence-transformers==5.0.0
 protobuf==6.31.0

backend/python/transformers/requirements-cublas11.txt

@@ -1,10 +1,10 @@
 --extra-index-url https://download.pytorch.org/whl/cu118
-torch==2.4.1+cu118
+torch==2.7.1+cu118
 llvmlite==0.43.0
 numba==0.60.0
 accelerate
 transformers
 bitsandbytes
 outetts
-sentence-transformers==4.1.0
+sentence-transformers==5.0.0
 protobuf==6.31.0

backend/python/transformers/requirements-cublas12.txt

@@ -1,9 +1,9 @@
-torch==2.4.1
+torch==2.7.1
 accelerate
 llvmlite==0.43.0
 numba==0.60.0
 transformers
 bitsandbytes
 outetts
-sentence-transformers==4.1.0
+sentence-transformers==5.0.0
 protobuf==6.31.0

backend/python/transformers/requirements-hipblas.txt

@@ -1,5 +1,5 @@
---extra-index-url https://download.pytorch.org/whl/rocm6.0
-torch==2.4.1+rocm6.0
+--extra-index-url https://download.pytorch.org/whl/rocm6.3
+torch==2.7.1+rocm6.3
 accelerate
 transformers
 llvmlite==0.43.0
@@ -7,5 +7,5 @@ numba==0.60.0
 bitsandbytes
 outetts
 bitsandbytes
-sentence-transformers==4.1.0
+sentence-transformers==5.0.0
 protobuf==6.31.0

backend/python/transformers/requirements-intel.txt

@@ -1,7 +1,7 @@
 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 intel-extension-for-pytorch==2.3.110+xpu
-torch==2.3.1+cxx11.abi
-oneccl_bind_pt==2.3.100+xpu
+torch==2.5.1+cxx11.abi
+oneccl_bind_pt==2.8.0+xpu
 optimum[openvino]
 llvmlite==0.43.0
 numba==0.60.0
@@ -9,5 +9,5 @@ transformers
 intel-extension-for-transformers
 bitsandbytes
 outetts
-sentence-transformers==4.1.0
+sentence-transformers==5.0.0
 protobuf==6.31.0

core/application/startup.go

@@ -59,8 +59,10 @@ func New(opts ...config.AppOption) (*Application, error) {
 		log.Error().Err(err).Msg("error installing models")
 	}
 
-	if err := coreStartup.InstallExternalBackends(options.BackendGalleries, options.BackendsPath, nil, options.ExternalBackends...); err != nil {
-		log.Error().Err(err).Msg("error installing external backends")
+	for _, backend := range options.ExternalBackends {
+		if err := coreStartup.InstallExternalBackends(options.BackendGalleries, options.BackendsPath, nil, backend, "", ""); err != nil {
+			log.Error().Err(err).Msg("error installing external backend")
+		}
 	}
 
 	configLoaderOpts := options.ToConfigLoaderOptions()

core/backend/image.go

@@ -7,7 +7,7 @@ import (
 	model "github.com/mudler/LocalAI/pkg/model"
 )
 
-func ImageGeneration(height, width, mode, step, seed int, positive_prompt, negative_prompt, src, dst string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig) (func() error, error) {
+func ImageGeneration(height, width, mode, step, seed int, positive_prompt, negative_prompt, src, dst string, loader *model.ModelLoader, backendConfig config.BackendConfig, appConfig *config.ApplicationConfig, refImages []string) (func() error, error) {
 
 	opts := ModelOptions(backendConfig, appConfig)
 	inferenceModel, err := loader.Load(
@@ -33,6 +33,7 @@ func ImageGeneration(height, width, mode, step, seed int, positive_prompt, negat
 				Dst:              dst,
 				Src:              src,
 				EnableParameters: backendConfig.Diffusers.EnableParameters,
+				RefImages:        refImages,
 			})
 		return err
 	}

core/cli/backends.go

@@ -23,7 +23,9 @@ type BackendsList struct {
 }
 
 type BackendsInstall struct {
-	BackendArgs []string `arg:"" optional:"" name:"backends" help:"Backend configuration URLs to load"`
+	BackendArgs string `arg:"" optional:"" name:"backend" help:"Backend configuration URL to load"`
+	Name        string `arg:"" optional:"" name:"name" help:"Name of the backend"`
+	Alias       string `arg:"" optional:"" name:"alias" help:"Alias of the backend"`
 
 	BackendsCMDFlags `embed:""`
 }
@@ -66,27 +68,25 @@ func (bi *BackendsInstall) Run(ctx *cliContext.Context) error {
 		log.Error().Err(err).Msg("unable to load galleries")
 	}
 
-	for _, backendName := range bi.BackendArgs {
-
-		progressBar := progressbar.NewOptions(
-			1000,
-			progressbar.OptionSetDescription(fmt.Sprintf("downloading backend %s", backendName)),
-			progressbar.OptionShowBytes(false),
-			progressbar.OptionClearOnFinish(),
-		)
-		progressCallback := func(fileName string, current string, total string, percentage float64) {
-			v := int(percentage * 10)
-			err := progressBar.Set(v)
-			if err != nil {
-				log.Error().Err(err).Str("filename", fileName).Int("value", v).Msg("error while updating progress bar")
-			}
-		}
-
-		err := startup.InstallExternalBackends(galleries, bi.BackendsPath, progressCallback, backendName)
+	progressBar := progressbar.NewOptions(
+		1000,
+		progressbar.OptionSetDescription(fmt.Sprintf("downloading backend %s", bi.BackendArgs)),
+		progressbar.OptionShowBytes(false),
+		progressbar.OptionClearOnFinish(),
+	)
+	progressCallback := func(fileName string, current string, total string, percentage float64) {
+		v := int(percentage * 10)
+		err := progressBar.Set(v)
 		if err != nil {
-			return err
+			log.Error().Err(err).Str("filename", fileName).Int("value", v).Msg("error while updating progress bar")
 		}
 	}
+
+	err := startup.InstallExternalBackends(galleries, bi.BackendsPath, progressCallback, bi.BackendArgs, bi.Name, bi.Alias)
+	if err != nil {
+		return err
+	}
+
 	return nil
 }
 

core/gallery/backends.go

@@ -11,6 +11,7 @@ import (
 	"github.com/mudler/LocalAI/pkg/downloader"
 	"github.com/mudler/LocalAI/pkg/model"
 	"github.com/mudler/LocalAI/pkg/system"
+	cp "github.com/otiai10/copy"
 	"github.com/rs/zerolog/log"
 )
 
@@ -145,18 +146,27 @@ func InstallBackend(basePath string, config *GalleryBackend, downloadStatus func
 	}
 
 	uri := downloader.URI(config.URI)
-	if err := uri.DownloadFile(backendPath, "", 1, 1, downloadStatus); err != nil {
-		success := false
-		// Try to download from mirrors
-		for _, mirror := range config.Mirrors {
-			if err := downloader.URI(mirror).DownloadFile(backendPath, "", 1, 1, downloadStatus); err == nil {
-				success = true
-				break
-			}
+	// Check if it is a directory
+	if uri.LooksLikeDir() {
+		// It is a directory, we just copy it over in the backend folder
+		if err := cp.Copy(config.URI, backendPath); err != nil {
+			return fmt.Errorf("failed copying: %w", err)
 		}
+	} else {
+		uri := downloader.URI(config.URI)
+		if err := uri.DownloadFile(backendPath, "", 1, 1, downloadStatus); err != nil {
+			success := false
+			// Try to download from mirrors
+			for _, mirror := range config.Mirrors {
+				if err := downloader.URI(mirror).DownloadFile(backendPath, "", 1, 1, downloadStatus); err == nil {
+					success = true
+					break
+				}
+			}
 
-		if !success {
-			return fmt.Errorf("failed to download backend %q: %v", config.URI, err)
+			if !success {
+				return fmt.Errorf("failed to download backend %q: %v", config.URI, err)
+			}
 		}
 	}
 
@@ -240,16 +250,22 @@ func ListSystemBackends(basePath string) (map[string]string, error) {
 	for _, backend := range backends {
 		if backend.IsDir() {
 			runFile := filepath.Join(basePath, backend.Name(), runFile)
-			// Skip if metadata file don't exist
+
+			var metadata *BackendMetadata
+
+			// If metadata file does not exist, we just use the directory name
+			// and we do not fill the other metadata (such as potential backend Aliases)
 			metadataFilePath := filepath.Join(basePath, backend.Name(), metadataFile)
 			if _, err := os.Stat(metadataFilePath); os.IsNotExist(err) {
-				continue
-			}
-
-			// Check for alias in metadata
-			metadata, err := readBackendMetadata(filepath.Join(basePath, backend.Name()))
-			if err != nil {
-				return nil, err
+				metadata = &BackendMetadata{
+					Name: backend.Name(),
+				}
+			} else {
+				// Check for alias in metadata
+				metadata, err = readBackendMetadata(filepath.Join(basePath, backend.Name()))
+				if err != nil {
+					return nil, err
+				}
 			}
 
 			if metadata == nil {

core/http/endpoints/localai/backend.go

@@ -34,7 +34,7 @@ func CreateBackendEndpointService(galleries []config.Gallery, backendPath string
 
 // GetOpStatusEndpoint returns the job status
 // @Summary Returns the job status
-// @Success 200 {object} services.BackendOpStatus "Response"
+// @Success 200 {object} services.GalleryOpStatus "Response"
 // @Router /backends/jobs/{uuid} [get]
 func (mgs *BackendEndpointService) GetOpStatusEndpoint() func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
@@ -48,7 +48,7 @@ func (mgs *BackendEndpointService) GetOpStatusEndpoint() func(c *fiber.Ctx) erro
 
 // GetAllStatusEndpoint returns all the jobs status progress
 // @Summary Returns all the jobs status progress
-// @Success 200 {object} map[string]services.BackendOpStatus "Response"
+// @Success 200 {object} map[string]services.GalleryOpStatus "Response"
 // @Router /backends/jobs [get]
 func (mgs *BackendEndpointService) GetAllStatusEndpoint() func(c *fiber.Ctx) error {
 	return func(c *fiber.Ctx) error {
@@ -58,7 +58,7 @@ func (mgs *BackendEndpointService) GetAllStatusEndpoint() func(c *fiber.Ctx) err
 
 // ApplyBackendEndpoint installs a new backend to a LocalAI instance
 // @Summary Install backends to LocalAI.
-// @Param request body BackendModel true "query params"
+// @Param request body GalleryBackend true "query params"
 // @Success 200 {object} schema.BackendResponse "Response"
 // @Router /backends/apply [post]
 func (mgs *BackendEndpointService) ApplyBackendEndpoint() func(c *fiber.Ctx) error {

core/http/endpoints/openai/chat.go

@@ -305,7 +305,7 @@ func ChatEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, evaluat
 		// If we are using the tokenizer template, we don't need to process the messages
 		// unless we are processing functions
 		if !config.TemplateConfig.UseTokenizerTemplate || shouldUseFn {
-			predInput = evaluator.TemplateMessages(input.Messages, config, funcs, shouldUseFn)
+			predInput = evaluator.TemplateMessages(*input, input.Messages, config, funcs, shouldUseFn)
 
 			log.Debug().Msgf("Prompt (after templating): %s", predInput)
 			if config.Grammar != "" {

core/http/endpoints/openai/completion.go

@@ -109,8 +109,10 @@ func CompletionEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, e
 			predInput := config.PromptStrings[0]
 
 			templatedInput, err := evaluator.EvaluateTemplateForPrompt(templates.CompletionPromptTemplate, *config, templates.PromptTemplateData{
-				Input:        predInput,
-				SystemPrompt: config.SystemPrompt,
+				Input:           predInput,
+				SystemPrompt:    config.SystemPrompt,
+				ReasoningEffort: input.ReasoningEffort,
+				Metadata:        input.Metadata,
 			})
 			if err == nil {
 				predInput = templatedInput
@@ -160,8 +162,10 @@ func CompletionEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, e
 
 		for k, i := range config.PromptStrings {
 			templatedInput, err := evaluator.EvaluateTemplateForPrompt(templates.CompletionPromptTemplate, *config, templates.PromptTemplateData{
-				SystemPrompt: config.SystemPrompt,
-				Input:        i,
+				SystemPrompt:    config.SystemPrompt,
+				Input:           i,
+				ReasoningEffort: input.ReasoningEffort,
+				Metadata:        input.Metadata,
 			})
 			if err == nil {
 				i = templatedInput

core/http/endpoints/openai/edit.go

@@ -47,9 +47,11 @@ func EditEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, evaluat
 
 		for _, i := range config.InputStrings {
 			templatedInput, err := evaluator.EvaluateTemplateForPrompt(templates.EditPromptTemplate, *config, templates.PromptTemplateData{
-				Input:        i,
-				Instruction:  input.Instruction,
-				SystemPrompt: config.SystemPrompt,
+				Input:           i,
+				Instruction:     input.Instruction,
+				SystemPrompt:    config.SystemPrompt,
+				ReasoningEffort: input.ReasoningEffort,
+				Metadata:        input.Metadata,
 			})
 			if err == nil {
 				i = templatedInput

core/http/endpoints/openai/image.go

@@ -79,49 +79,37 @@ func ImageEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appCon
 			return fiber.ErrBadRequest
 		}
 
+		// Process input images (for img2img/inpainting)
 		src := ""
 		if input.File != "" {
+			src = processImageFile(input.File, appConfig.GeneratedContentDir)
+			if src != "" {
+				defer os.RemoveAll(src)
+			}
+		}
 
-			fileData := []byte{}
-			var err error
-			// check if input.File is an URL, if so download it and save it
-			// to a temporary file
-			if strings.HasPrefix(input.File, "http://") || strings.HasPrefix(input.File, "https://") {
-				out, err := downloadFile(input.File)
-				if err != nil {
-					return fmt.Errorf("failed downloading file:%w", err)
-				}
-				defer os.RemoveAll(out)
-
-				fileData, err = os.ReadFile(out)
-				if err != nil {
-					return fmt.Errorf("failed reading file:%w", err)
-				}
-
-			} else {
-				// base 64 decode the file and write it somewhere
-				// that we will cleanup
-				fileData, err = base64.StdEncoding.DecodeString(input.File)
-				if err != nil {
-					return err
+		// Process multiple input images
+		var inputImages []string
+		if len(input.Files) > 0 {
+			for _, file := range input.Files {
+				processedFile := processImageFile(file, appConfig.GeneratedContentDir)
+				if processedFile != "" {
+					inputImages = append(inputImages, processedFile)
+					defer os.RemoveAll(processedFile)
 				}
 			}
+		}
 
-			// Create a temporary file
-			outputFile, err := os.CreateTemp(appConfig.GeneratedContentDir, "b64")
-			if err != nil {
-				return err
+		// Process reference images
+		var refImages []string
+		if len(input.RefImages) > 0 {
+			for _, file := range input.RefImages {
+				processedFile := processImageFile(file, appConfig.GeneratedContentDir)
+				if processedFile != "" {
+					refImages = append(refImages, processedFile)
+					defer os.RemoveAll(processedFile)
+				}
 			}
-			// write the base64 result
-			writer := bufio.NewWriter(outputFile)
-			_, err = writer.Write(fileData)
-			if err != nil {
-				outputFile.Close()
-				return err
-			}
-			outputFile.Close()
-			src = outputFile.Name()
-			defer os.RemoveAll(src)
 		}
 
 		log.Debug().Msgf("Parameter Config: %+v", config)
@@ -202,7 +190,13 @@ func ImageEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appCon
 
 				baseURL := c.BaseURL()
 
-				fn, err := backend.ImageGeneration(height, width, mode, step, *config.Seed, positive_prompt, negative_prompt, src, output, ml, *config, appConfig)
+				// Use the first input image as src if available, otherwise use the original src
+				inputSrc := src
+				if len(inputImages) > 0 {
+					inputSrc = inputImages[0]
+				}
+
+				fn, err := backend.ImageGeneration(height, width, mode, step, *config.Seed, positive_prompt, negative_prompt, inputSrc, output, ml, *config, appConfig, refImages)
 				if err != nil {
 					return err
 				}
@@ -243,3 +237,51 @@ func ImageEndpoint(cl *config.BackendConfigLoader, ml *model.ModelLoader, appCon
 		return c.JSON(resp)
 	}
 }
+
+// processImageFile handles a single image file (URL or base64) and returns the path to the temporary file
+func processImageFile(file string, generatedContentDir string) string {
+	fileData := []byte{}
+	var err error
+
+	// check if file is an URL, if so download it and save it to a temporary file
+	if strings.HasPrefix(file, "http://") || strings.HasPrefix(file, "https://") {
+		out, err := downloadFile(file)
+		if err != nil {
+			log.Error().Err(err).Msgf("Failed downloading file: %s", file)
+			return ""
+		}
+		defer os.RemoveAll(out)
+
+		fileData, err = os.ReadFile(out)
+		if err != nil {
+			log.Error().Err(err).Msgf("Failed reading downloaded file: %s", out)
+			return ""
+		}
+	} else {
+		// base 64 decode the file and write it somewhere that we will cleanup
+		fileData, err = base64.StdEncoding.DecodeString(file)
+		if err != nil {
+			log.Error().Err(err).Msgf("Failed decoding base64 file")
+			return ""
+		}
+	}
+
+	// Create a temporary file
+	outputFile, err := os.CreateTemp(generatedContentDir, "b64")
+	if err != nil {
+		log.Error().Err(err).Msg("Failed creating temporary file")
+		return ""
+	}
+
+	// write the base64 result
+	writer := bufio.NewWriter(outputFile)
+	_, err = writer.Write(fileData)
+	if err != nil {
+		outputFile.Close()
+		log.Error().Err(err).Msg("Failed writing to temporary file")
+		return ""
+	}
+	outputFile.Close()
+
+	return outputFile.Name()
+}

core/http/static/image.js

@@ -11,6 +11,7 @@ async function promptDallE(input) {
   document.getElementById("input").disabled = true;
 
   const model = document.getElementById("image-model").value;
+  const size = document.getElementById("image-size").value;
   const response = await fetch("v1/images/generations", {
     method: "POST",
     headers: {
@@ -21,7 +22,7 @@ async function promptDallE(input) {
       steps: 10,
       prompt: input,
       n: 1,
-      size: "512x512",
+      size: size,
     }),
   });
   const json = await response.json();
@@ -48,4 +49,13 @@ async function promptDallE(input) {
 
 document.getElementById("input").focus();
 document.getElementById("genimage").addEventListener("submit", genImage);
+
+// Handle Enter key press in the prompt input
+document.getElementById("input").addEventListener("keypress", function(event) {
+    if (event.key === "Enter") {
+        event.preventDefault();
+        genImage(event);
+    }
+});
+
 document.getElementById("loader").style.display = "none";

core/http/views/text2image.html

@@ -91,6 +91,30 @@
                             </svg>
                         </span>
                     </div>
+                    
+                    <!-- Size Selection -->
+                    <div class="mt-4">
+                        <label for="image-size" class="block text-sm font-medium text-gray-300 mb-2">
+                            <i class="fas fa-expand-arrows-alt mr-2"></i>Image Size:
+                        </label>
+                        <input
+                            type="text"
+                            id="image-size"
+                            value="256x256"
+                            placeholder="e.g., 256x256, 512x512, 1024x1024"
+                            class="bg-gray-900 text-white border border-gray-700 focus:border-blue-500 focus:ring focus:ring-blue-500 focus:ring-opacity-50 rounded-lg shadow-sm p-2.5 w-full max-w-xs transition-colors duration-200"
+                        />
+                    </div>
+                    
+                    <!-- Submit Button -->
+                    <div class="mt-6">
+                        <button
+                            type="submit"
+                            class="w-full bg-gradient-to-r from-blue-600 to-indigo-600 hover:from-blue-700 hover:to-indigo-700 text-white font-semibold py-3 px-6 rounded-lg transition duration-300 ease-in-out transform hover:scale-105 hover:shadow-lg focus:outline-none focus:ring-2 focus:ring-blue-500 focus:ring-opacity-50"
+                        >
+                            <i class="fas fa-magic mr-2"></i>Generate Image
+                        </button>
+                    </div>
                 </form>
                 
                 <!-- Image Results Container -->

core/schema/openai.go

@@ -141,6 +141,10 @@ type OpenAIRequest struct {
 
 	// whisper
 	File string `json:"file" validate:"required"`
+	// Multiple input images for img2img or inpainting
+	Files []string `json:"files,omitempty"`
+	// Reference images for models that support them (e.g., Flux Kontext)
+	RefImages []string `json:"ref_images,omitempty"`
 	//whisper/image
 	ResponseFormat interface{} `json:"response_format,omitempty"`
 	// image
@@ -179,6 +183,10 @@ type OpenAIRequest struct {
 	Backend string `json:"backend" yaml:"backend"`
 
 	ModelBaseName string `json:"model_base_name" yaml:"model_base_name"`
+
+	ReasoningEffort string `json:"reasoning_effort" yaml:"reasoning_effort"`
+
+	Metadata map[string]string `json:"metadata" yaml:"metadata"`
 }
 
 type ModelsDataResponse struct {

core/startup/backend_preload.go

@@ -1,7 +1,6 @@
 package startup
 
 import (
-	"errors"
 	"fmt"
 	"path/filepath"
 	"strings"
@@ -13,38 +12,68 @@ import (
 	"github.com/rs/zerolog/log"
 )
 
-func InstallExternalBackends(galleries []config.Gallery, backendPath string, downloadStatus func(string, string, string, float64), backends ...string) error {
-	var errs error
+func InstallExternalBackends(galleries []config.Gallery, backendPath string, downloadStatus func(string, string, string, float64), backend, name, alias string) error {
 	systemState, err := system.GetSystemState()
 	if err != nil {
 		return fmt.Errorf("failed to get system state: %w", err)
 	}
-	for _, backend := range backends {
-		uri := downloader.URI(backend)
-		switch {
-		case uri.LooksLikeOCI():
-			name, err := uri.FilenameFromUrl()
-			if err != nil {
-				return fmt.Errorf("failed to get filename from URL: %w", err)
-			}
-			// strip extension if any
-			name = strings.TrimSuffix(name, filepath.Ext(name))
+	uri := downloader.URI(backend)
+	switch {
+	case uri.LooksLikeDir():
+		if name == "" { // infer it from the path
+			name = filepath.Base(backend)
+		}
+		log.Info().Str("backend", backend).Str("name", name).Msg("Installing backend from path")
+		if err := gallery.InstallBackend(backendPath, &gallery.GalleryBackend{
+			Metadata: gallery.Metadata{
+				Name: name,
+			},
+			Alias: alias,
+			URI:   backend,
+		}, downloadStatus); err != nil {
+			return fmt.Errorf("error installing backend %s: %w", backend, err)
+		}
+	case uri.LooksLikeOCI() && !uri.LooksLikeOCIFile():
+		if name == "" {
+			return fmt.Errorf("specifying a name is required for OCI images")
+		}
+		log.Info().Str("backend", backend).Str("name", name).Msg("Installing backend from OCI image")
+		if err := gallery.InstallBackend(backendPath, &gallery.GalleryBackend{
+			Metadata: gallery.Metadata{
+				Name: name,
+			},
+			Alias: alias,
+			URI:   backend,
+		}, downloadStatus); err != nil {
+			return fmt.Errorf("error installing backend %s: %w", backend, err)
+		}
+	case uri.LooksLikeOCIFile():
+		name, err := uri.FilenameFromUrl()
+		if err != nil {
+			return fmt.Errorf("failed to get filename from URL: %w", err)
+		}
+		// strip extension if any
+		name = strings.TrimSuffix(name, filepath.Ext(name))
 
-			log.Info().Str("backend", backend).Str("name", name).Msg("Installing backend from OCI image")
-			if err := gallery.InstallBackend(backendPath, &gallery.GalleryBackend{
-				Metadata: gallery.Metadata{
-					Name: name,
-				},
-				URI: backend,
-			}, downloadStatus); err != nil {
-				errs = errors.Join(err, fmt.Errorf("error installing backend %s", backend))
-			}
-		default:
-			err := gallery.InstallBackendFromGallery(galleries, systemState, backend, backendPath, downloadStatus, true)
-			if err != nil {
-				errs = errors.Join(err, fmt.Errorf("error installing backend %s", backend))
-			}
+		log.Info().Str("backend", backend).Str("name", name).Msg("Installing backend from OCI image")
+		if err := gallery.InstallBackend(backendPath, &gallery.GalleryBackend{
+			Metadata: gallery.Metadata{
+				Name: name,
+			},
+			Alias: alias,
+			URI:   backend,
+		}, downloadStatus); err != nil {
+			return fmt.Errorf("error installing backend %s: %w", backend, err)
+		}
+	default:
+		if name != "" || alias != "" {
+			return fmt.Errorf("specifying a name or alias is not supported for this backend")
+		}
+		err := gallery.InstallBackendFromGallery(galleries, systemState, backend, backendPath, downloadStatus, true)
+		if err != nil {
+			return fmt.Errorf("error installing backend %s: %w", backend, err)
 		}
 	}
-	return errs
+
+	return nil
 }

core/templates/evaluator.go

@@ -21,6 +21,8 @@ type PromptTemplateData struct {
 	Instruction          string
 	Functions            []functions.Function
 	MessageIndex         int
+	ReasoningEffort      string
+	Metadata             map[string]string
 }
 
 type ChatMessageTemplateData struct {
@@ -133,7 +135,7 @@ func (e *Evaluator) evaluateJinjaTemplateForPrompt(templateType TemplateType, te
 	return e.cache.evaluateJinjaTemplate(templateType, templateName, conversation)
 }
 
-func (e *Evaluator) TemplateMessages(messages []schema.Message, config *config.BackendConfig, funcs []functions.Function, shouldUseFn bool) string {
+func (e *Evaluator) TemplateMessages(input schema.OpenAIRequest, messages []schema.Message, config *config.BackendConfig, funcs []functions.Function, shouldUseFn bool) string {
 
 	if config.TemplateConfig.JinjaTemplate {
 		var messageData []ChatMessageTemplateData
@@ -283,6 +285,8 @@ func (e *Evaluator) TemplateMessages(messages []schema.Message, config *config.B
 		SuppressSystemPrompt: suppressConfigSystemPrompt,
 		Input:                predInput,
 		Functions:            funcs,
+		ReasoningEffort:      input.ReasoningEffort,
+		Metadata:             input.Metadata,
 	})
 	if err == nil {
 		predInput = templatedInput

core/templates/evaluator_test.go

@@ -219,7 +219,7 @@ var _ = Describe("Templates", func() {
 		for key := range chatMLTestMatch {
 			foo := chatMLTestMatch[key]
 			It("renders correctly `"+key+"`", func() {
-				templated := evaluator.TemplateMessages(foo["messages"].([]schema.Message), foo["config"].(*config.BackendConfig), foo["functions"].([]functions.Function), foo["shouldUseFn"].(bool))
+				templated := evaluator.TemplateMessages(schema.OpenAIRequest{}, foo["messages"].([]schema.Message), foo["config"].(*config.BackendConfig), foo["functions"].([]functions.Function), foo["shouldUseFn"].(bool))
 				Expect(templated).To(Equal(foo["expected"]), templated)
 			})
 		}
@@ -232,7 +232,7 @@ var _ = Describe("Templates", func() {
 		for key := range llama3TestMatch {
 			foo := llama3TestMatch[key]
 			It("renders correctly `"+key+"`", func() {
-				templated := evaluator.TemplateMessages(foo["messages"].([]schema.Message), foo["config"].(*config.BackendConfig), foo["functions"].([]functions.Function), foo["shouldUseFn"].(bool))
+				templated := evaluator.TemplateMessages(schema.OpenAIRequest{}, foo["messages"].([]schema.Message), foo["config"].(*config.BackendConfig), foo["functions"].([]functions.Function), foo["shouldUseFn"].(bool))
 				Expect(templated).To(Equal(foo["expected"]), templated)
 			})
 		}
@@ -245,7 +245,7 @@ var _ = Describe("Templates", func() {
 		for key := range jinjaTest {
 			foo := jinjaTest[key]
 			It("renders correctly `"+key+"`", func() {
-				templated := evaluator.TemplateMessages(foo["messages"].([]schema.Message), foo["config"].(*config.BackendConfig), foo["functions"].([]functions.Function), foo["shouldUseFn"].(bool))
+				templated := evaluator.TemplateMessages(schema.OpenAIRequest{}, foo["messages"].([]schema.Message), foo["config"].(*config.BackendConfig), foo["functions"].([]functions.Function), foo["shouldUseFn"].(bool))
 				Expect(templated).To(Equal(foo["expected"]), templated)
 			})
 		}

docs/content/docs/advanced/advanced-usage.md

@@ -95,7 +95,7 @@ Specifying a `config-file` via CLI allows to declare models in a single file as
    chat: chat
 ```
 
-See also [chatbot-ui](https://github.com/go-skynet/LocalAI/tree/master/examples/chatbot-ui) as an example on how to use config files.
+See also [chatbot-ui](https://github.com/mudler/LocalAI-examples/tree/main/chatbot-ui) as an example on how to use config files.
 
 It is possible to specify a full URL or a short-hand URL to a YAML model configuration file and use it on start with local-ai, for example to use phi-2:
 
@@ -341,7 +341,7 @@ Below is an instruction that describes a task, paired with an input that provide
 
 Instead of installing models manually, you can use the LocalAI API endpoints and a model definition to install programmatically via API models in runtime.
 
-A curated collection of model files is in the [model-gallery](https://github.com/go-skynet/model-gallery) (work in progress!). The files of the model gallery are different from the model files used to configure LocalAI models. The model gallery files contains information about the model setup, and the files necessary to run the model locally.
+A curated collection of model files is in the [model-gallery](https://github.com/mudler/LocalAI/tree/master/gallery). The files of the model gallery are different from the model files used to configure LocalAI models. The model gallery files contains information about the model setup, and the files necessary to run the model locally.
 
 To install for example `lunademo`, you can send a POST call to the `/models/apply` endpoint with the model definition url (`url`) and the name of the model should have in LocalAI (`name`, optional):
 
@@ -445,15 +445,17 @@ make -C backend/python/vllm
 When LocalAI runs in a container,
 there are additional environment variables available that modify the behavior of LocalAI on startup:
 
+{{< table "table-responsive" >}}
 | Environment variable       | Default | Description                                                                                                |
 |----------------------------|---------|------------------------------------------------------------------------------------------------------------|
 | `REBUILD`                  | `false` | Rebuild LocalAI on startup                                                                                 |
-| `BUILD_TYPE`               |         | Build type. Available: `cublas`, `openblas`, `clblas`                                                      |
+| `BUILD_TYPE`               |         | Build type. Available: `cublas`, `openblas`, `clblas`, `intel` (intel core), `sycl_f16`, `sycl_f32` (intel backends)                                                      |
 | `GO_TAGS`                  |         | Go tags. Available: `stablediffusion`                                                                      |
 | `HUGGINGFACEHUB_API_TOKEN` |         | Special token for interacting with HuggingFace Inference API, required only when using the `langchain-huggingface` backend |
 | `EXTRA_BACKENDS`          |         | A space separated list of backends to prepare. For example `EXTRA_BACKENDS="backend/python/diffusers backend/python/transformers"` prepares the python environment on start |
 | `DISABLE_AUTODETECT`       | `false` | Disable autodetect of CPU flagset on start                                                                     |
 | `LLAMACPP_GRPC_SERVERS`   |         | A list of llama.cpp workers to distribute the workload. For example `LLAMACPP_GRPC_SERVERS="address1:port,address2:port"` |
+{{< /table >}}
 
 Here is how to configure these variables:
 
@@ -471,12 +473,15 @@ You can control LocalAI with command line arguments, to specify a binding addres
 In the help text below, BASEPATH is the location that local-ai is being executed from
 
 #### Global Flags
+{{< table "table-responsive" >}}
 | Parameter | Default | Description | Environment Variable |
 |-----------|---------|-------------|----------------------|
 |  -h, --help |  | Show context-sensitive help. |
 | --log-level | info | Set the level of logs to output [error,warn,info,debug] | $LOCALAI_LOG_LEVEL |
+{{< /table >}}
 
 #### Storage Flags
+{{< table "table-responsive" >}}
 | Parameter | Default | Description | Environment Variable |
 |-----------|---------|-------------|----------------------|
 | --models-path | BASEPATH/models | Path containing models used for inferencing  | $LOCALAI_MODELS_PATH |
@@ -487,8 +492,10 @@ In the help text below, BASEPATH is the location that local-ai is being executed
 | --localai-config-dir | BASEPATH/configuration | Directory for dynamic loading of certain configuration files (currently api_keys.json and external_backends.json) | $LOCALAI_CONFIG_DIR |
 | --localai-config-dir-poll-interval |  | Typically the config path picks up changes automatically, but if your system has broken fsnotify events, set this to a time duration to poll the LocalAI Config Dir (example: 1m) | $LOCALAI_CONFIG_DIR_POLL_INTERVAL |
 | --models-config-file | STRING | YAML file containing a list of model backend configs | $LOCALAI_MODELS_CONFIG_FILE |
+{{< /table >}}
 
 #### Models Flags
+{{< table "table-responsive" >}}
 | Parameter | Default | Description | Environment Variable |
 |-----------|---------|-------------|----------------------|
 | --galleries | STRING | JSON list of galleries | $LOCALAI_GALLERIES |
@@ -497,15 +504,19 @@ In the help text below, BASEPATH is the location that local-ai is being executed
 | --preload-models | STRING | A List of models to apply in JSON at start |$LOCALAI_PRELOAD_MODELS |
 | --models | MODELS,... | A List of model configuration URLs to load | $LOCALAI_MODELS |
 | --preload-models-config | STRING | A List of models to apply at startup. Path to a YAML config file | $LOCALAI_PRELOAD_MODELS_CONFIG |
+{{< /table >}}
 
 #### Performance Flags
+{{< table "table-responsive" >}}
 | Parameter | Default | Description | Environment Variable |
 |-----------|---------|-------------|----------------------|
 | --f16 |  | Enable GPU acceleration | $LOCALAI_F16 |
 | -t, --threads | 4 | Number of threads used for parallel computation. Usage of the number of physical cores in the system is suggested | $LOCALAI_THREADS |
 | --context-size | 512 | Default context size for models | $LOCALAI_CONTEXT_SIZE |
+{{< /table >}}
 
 #### API Flags
+{{< table "table-responsive" >}}
 | Parameter | Default | Description | Environment Variable |
 |-----------|---------|-------------|----------------------|
 | --address | ":8080" | Bind address for the API server | $LOCALAI_ADDRESS |
@@ -516,8 +527,10 @@ In the help text below, BASEPATH is the location that local-ai is being executed
 | --disable-welcome |  | Disable welcome pages | $LOCALAI_DISABLE_WELCOME |
 | --disable-webui | false | Disables the web user interface. When set to true, the server will only expose API endpoints without serving the web interface | $LOCALAI_DISABLE_WEBUI |
 | --machine-tag |  | If not empty - put that string to Machine-Tag header in each response. Useful to track response from different machines using multiple P2P federated nodes | $LOCALAI_MACHINE_TAG |
+{{< /table >}}
 
 #### Backend Flags
+{{< table "table-responsive" >}}
 | Parameter | Default | Description | Environment Variable |
 |-----------|---------|-------------|----------------------|
 | --parallel-requests |  | Enable backends to handle multiple requests in parallel if they support it (e.g.: llama.cpp or vllm) | $LOCALAI_PARALLEL_REQUESTS |
@@ -528,6 +541,7 @@ In the help text below, BASEPATH is the location that local-ai is being executed
 | --watchdog-idle-timeout | 15m | Threshold beyond which an idle backend should be stopped | $LOCALAI_WATCHDOG_IDLE_TIMEOUT, $WATCHDOG_IDLE_TIMEOUT |
 | --enable-watchdog-busy |  | Enable watchdog for stopping backends that are busy longer than the watchdog-busy-timeout | $LOCALAI_WATCHDOG_BUSY |
 | --watchdog-busy-timeout | 5m | Threshold beyond which a busy backend should be stopped | $LOCALAI_WATCHDOG_BUSY_TIMEOUT |
+{{< /table >}}
 
 ### .env files
 

docs/content/docs/faq.md

@@ -46,7 +46,7 @@ There is the availability of localai-webui and chatbot-ui in the examples sectio
 
 ### Does it work with AutoGPT? 
 
-Yes, see the [examples](https://github.com/go-skynet/LocalAI/tree/master/examples/)!
+Yes, see the [examples](https://github.com/mudler/LocalAI-examples)!
 
 ### How can I troubleshoot when something is wrong?
 

docs/content/docs/features/GPU-acceleration.md

@@ -267,7 +267,7 @@ If building from source, you need to install [Intel oneAPI Base Toolkit](https:/
 
 ### Container images
 
-To use SYCL, use the images with the `gpu-intel-f16` or `gpu-intel-f32` tag, for example `{{< version >}}-gpu-intel-f32-core`, `{{< version >}}-gpu-intel-f16`, ...
+To use SYCL, use the images with `gpu-intel` in the tag, for example `{{< version >}}-gpu-intel`, ...
 
 The image list is on [quay](https://quay.io/repository/go-skynet/local-ai?tab=tags).
 
@@ -276,7 +276,7 @@ The image list is on [quay](https://quay.io/repository/go-skynet/local-ai?tab=ta
 To run LocalAI with Docker and sycl starting `phi-2`, you can use the following command as an example:
 
 ```bash
-docker run -e DEBUG=true --privileged -ti -v $PWD/models:/models -p 8080:8080  -v /dev/dri:/dev/dri --rm quay.io/go-skynet/local-ai:master-gpu-intel-f32 phi-2
+docker run -e DEBUG=true --privileged -ti -v $PWD/models:/models -p 8080:8080  -v /dev/dri:/dev/dri --rm quay.io/go-skynet/local-ai:master-gpu-intel phi-2
 ```
 
 ### Notes
@@ -284,7 +284,7 @@ docker run -e DEBUG=true --privileged -ti -v $PWD/models:/models -p 8080:8080  -
 In addition to the commands to run LocalAI normally, you need to specify `--device /dev/dri` to docker, for example:
 
 ```bash
-docker run --rm -ti --device /dev/dri -p 8080:8080 -e DEBUG=true -e MODELS_PATH=/models -e THREADS=1 -v $PWD/models:/models quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel-f16
+docker run --rm -ti --device /dev/dri -p 8080:8080 -e DEBUG=true -e MODELS_PATH=/models -e THREADS=1 -v $PWD/models:/models quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel
 ```
 
 Note also that sycl does have a known issue to hang with `mmap: true`. You have to disable it in the model configuration if explicitly enabled.

docs/content/docs/features/distributed_inferencing.md

@@ -129,6 +129,7 @@ The server logs should indicate that new workers are being discovered.
 
 There are options that can be tweaked or parameters that can be set using environment variables
 
+{{< table "table-responsive" >}}
 | Environment Variable | Description |
 |----------------------|-------------|
 | **LOCALAI_P2P** | Set to "true" to enable p2p |
@@ -142,6 +143,7 @@ There are options that can be tweaked or parameters that can be set using enviro
 | **LOCALAI_P2P_TOKEN** | Set the token for the p2p network |
 | **LOCALAI_P2P_LOGLEVEL** | Set the loglevel for the LocalAI p2p stack (default: info) |
 | **LOCALAI_P2P_LIB_LOGLEVEL** | Set the loglevel for the underlying libp2p stack (default: fatal) |
+{{< /table >}}
 
 
 ## Architecture

docs/content/docs/features/embeddings.md

@@ -75,4 +75,4 @@ curl http://localhost:8080/embeddings -X POST -H "Content-Type: application/json
 
 ## 💡 Examples
 
-- Example that uses LLamaIndex and LocalAI as embedding: [here](https://github.com/go-skynet/LocalAI/tree/master/examples/query_data/).
+- Example that uses LLamaIndex and LocalAI as embedding: [here](https://github.com/mudler/LocalAI-examples/tree/main/query_data).

docs/content/docs/features/openai-functions.md

@@ -263,4 +263,4 @@ Grammars and function tools can be used as well in conjunction with vision APIs:
 
 ## 💡 Examples
 
-A full e2e example with `docker-compose` is available [here](https://github.com/go-skynet/LocalAI/tree/master/examples/functions).
+A full e2e example with `docker-compose` is available [here](https://github.com/mudler/LocalAI-examples/tree/main/functions).

docs/content/docs/getting-started/build.md

@@ -197,4 +197,4 @@ docker build --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg BASE_IMAGE=$(BASE_
 Note:
 
 - BUILD_TYPE can be either: `cublas`, `hipblas`, `sycl_f16`, `sycl_f32`, `metal`.
-- BASE_IMAGE is tested on `ubuntu:22.04` (and defaults to it)
+- BASE_IMAGE is tested on `ubuntu:22.04` (and defaults to it) and `quay.io/go-skynet/intel-oneapi-base:latest` for intel/sycl

docs/content/docs/getting-started/container-images.md

@@ -41,6 +41,7 @@ All-In-One images are images that come pre-configured with a set of models and b
 
 In the AIO images there are models configured with the names of OpenAI models, however, they are really backed by Open Source models. You can find the table below
 
+{{< table "table-responsive" >}}
 | Category | Model name | Real model (CPU) | Real model (GPU) |
 | ---- | ---- | ---- | ---- |
 | Text Generation | `gpt-4` | `phi-2` | `hermes-2-pro-mistral` |
@@ -49,6 +50,7 @@ In the AIO images there are models configured with the names of OpenAI models, h
 | Speech to Text | `whisper-1` | `whisper` with `whisper-base` model | <= same |
 | Text to Speech | `tts-1` | `en-us-amy-low.onnx` from `rhasspy/piper` | <= same |
 | Embeddings | `text-embedding-ada-002` | `all-MiniLM-L6-v2` in Q4 | `all-MiniLM-L6-v2` |
+{{< /table >}}
 
 ### Usage
 
@@ -131,8 +133,7 @@ docker run -p 8080:8080 --name local-ai -ti -v localai-models:/models localai/lo
 | Latest images for Nvidia GPU (CUDA11) | `quay.io/go-skynet/local-ai:latest-aio-gpu-nvidia-cuda-11` | `localai/localai:latest-aio-gpu-nvidia-cuda-11`                      |
 | Latest images for Nvidia GPU (CUDA12) | `quay.io/go-skynet/local-ai:latest-aio-gpu-nvidia-cuda-12` | `localai/localai:latest-aio-gpu-nvidia-cuda-12`                      |
 | Latest images for AMD GPU | `quay.io/go-skynet/local-ai:latest-aio-gpu-hipblas` | `localai/localai:latest-aio-gpu-hipblas`                      |
-| Latest images for Intel GPU (sycl f16) | `quay.io/go-skynet/local-ai:latest-aio-gpu-intel-f16` | `localai/localai:latest-aio-gpu-intel-f16`                      |
-| Latest images for Intel GPU (sycl f32) | `quay.io/go-skynet/local-ai:latest-aio-gpu-intel-f32` | `localai/localai:latest-aio-gpu-intel-f32`                      |
+| Latest images for Intel GPU | `quay.io/go-skynet/local-ai:latest-aio-gpu-intel` | `localai/localai:latest-aio-gpu-intel`                      |
 
 ### Available environment variables
 
@@ -179,23 +180,13 @@ Standard container images do not have pre-installed models.
 
 {{% /tab %}}
 
-{{% tab tabName="Intel GPU (sycl f16)" %}}
+{{% tab tabName="Intel GPU" %}}
 
 | Description | Quay | Docker Hub                                                  |
 | --- | --- |-------------------------------------------------------------|
-| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-intel-f16` | `localai/localai:master-gpu-intel-f16`                      |
-| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-intel-f16` | `localai/localai:latest-gpu-intel-f16`                      |
-| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel-f16` | `localai/localai:{{< version >}}-gpu-intel-f16`             |
-
-{{% /tab %}}
-
-{{% tab tabName="Intel GPU (sycl f32)" %}}
-
-| Description | Quay | Docker Hub                                                  |
-| --- | --- |-------------------------------------------------------------|
-| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-intel-f32` | `localai/localai:master-gpu-intel-f32`                      |
-| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-intel-f32` | `localai/localai:latest-gpu-intel-f32`                      |
-| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel-f32` | `localai/localai:{{< version >}}-gpu-intel-f32`             |
+| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-gpu-intel` | `localai/localai:master-gpu-intel`                      |
+| Latest tag | `quay.io/go-skynet/local-ai:latest-gpu-intel` | `localai/localai:latest-gpu-intel`                      |
+| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-gpu-intel` | `localai/localai:{{< version >}}-gpu-intel`             |
 
 {{% /tab %}}
 

docs/content/docs/getting-started/models.md

@@ -207,4 +207,4 @@ For instructions on building LocalAI from source, see the [Build Section]({{% re
 {{% /tab %}}
 {{< /tabs >}}
 
-For more model configurations, visit the [Examples Section](https://github.com/mudler/LocalAI/tree/master/examples/configurations).
+For more model configurations, visit the [Examples Section](https://github.com/mudler/LocalAI-examples/tree/main/configurations).

docs/content/docs/getting-started/quickstart.md

@@ -59,11 +59,7 @@ docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri
 #### Intel GPU Images (oneAPI):
 
 ```bash
-# Intel GPU with FP16 support
-docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-intel-f16
-
-# Intel GPU with FP32 support
-docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-intel-f32
+docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-gpu-intel
 ```
 
 #### Vulkan GPU Images:
@@ -85,7 +81,7 @@ docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-ai
 docker run -ti --name local-ai -p 8080:8080 --gpus all localai/localai:latest-aio-gpu-nvidia-cuda-11
 
 # Intel GPU version
-docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel-f16
+docker run -ti --name local-ai -p 8080:8080 localai/localai:latest-aio-gpu-intel
 
 # AMD GPU version
 docker run -ti --name local-ai -p 8080:8080 --device=/dev/kfd --device=/dev/dri --group-add=video localai/localai:latest-aio-gpu-hipblas

docs/content/docs/reference/compatibility-table.md

@@ -14,6 +14,7 @@ LocalAI will attempt to automatically load models which are not explicitly confi
 
 {{% /alert %}}
 
+{{< table "table-responsive" >}}
 | Backend and Bindings                                                             | Compatible models     | Completion/Chat endpoint | Capability | Embeddings support                | Token stream support | Acceleration |
 |----------------------------------------------------------------------------------|-----------------------|--------------------------|---------------------------|-----------------------------------|----------------------|--------------|
 | [llama.cpp]({{%relref "docs/features/text-generation#llama.cpp" %}})        | LLama, Mamba, RWKV, Falcon, Starcoder, GPT-2, [and many others](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#description) | yes                      | GPT and Functions                        | yes | yes                  | CUDA, openCL, cuBLAS, Metal |
@@ -34,6 +35,7 @@ LocalAI will attempt to automatically load models which are not explicitly confi
 | [bark-cpp](https://github.com/PABannier/bark.cpp)        | bark               | no                       | Audio-Only                 | no                                | no                   | yes |
 | [stablediffusion-cpp](https://github.com/leejet/stable-diffusion.cpp)         | stablediffusion-1, stablediffusion-2, stablediffusion-3, flux, PhotoMaker               | no                       | Image                 | no                                | no                   | N/A |
 | [silero-vad](https://github.com/snakers4/silero-vad) with [Golang bindings](https://github.com/streamer45/silero-vad-go) | Silero VAD    | no                       | Voice Activity Detection    | no                               | no                   | CPU |
+{{< /table >}}
 
 Note: any backend name listed above can be used in the `backend` field of the model configuration file (See [the advanced section]({{%relref "docs/advanced" %}})).
 

docs/content/docs/whats-new.md

@@ -99,8 +99,8 @@ Thanks to the community efforts now we have a new [how-to website](https://io.mi
 
 #### 💡 More examples!
 
-- Open source autopilot? See the new addition by {{< github "gruberdev" >}} in our [examples](https://github.com/go-skynet/LocalAI/tree/master/examples/continue) on how to use Continue with LocalAI!
-- Want to try LocalAI with Insomnia? Check out the new [Insomnia example](https://github.com/go-skynet/LocalAI/tree/master/examples/insomnia) by {{< github "dave-gray101" >}}!
+- Open source autopilot? See the new addition by {{< github "gruberdev" >}} in our [examples](https://github.com/mudler/LocalAI-examples/tree/main/continue) on how to use Continue with LocalAI!
+- Want to try LocalAI with Insomnia? Check out the new [Insomnia example](https://github.com/mudler/LocalAI-examples/tree/main/insomnia) by {{< github "dave-gray101" >}}!
 
 #### LocalAGI in discord!
 
@@ -258,7 +258,7 @@ And here when it actually picks to reply to the user instead of using functions!
 
 Note: functions are supported only with `llama.cpp`-compatible models.
 
-A full example is available here: https://github.com/go-skynet/LocalAI/tree/master/examples/functions
+A full example is available here: https://github.com/mudler/LocalAI-examples/tree/main/functions
 
 ### gRPC backends
 
@@ -377,9 +377,9 @@ We now support a vast variety of models, while being backward compatible with pr
 
 ### Examples
 
-- 💡 [AutoGPT](https://github.com/go-skynet/LocalAI/tree/master/examples/autoGPT) example ( [mudler](https://github.com/mudler) )
-- 💡 [PrivateGPT](https://github.com/go-skynet/LocalAI/tree/master/examples/privateGPT) example ( [mudler](https://github.com/mudler) )
-- 💡 [Flowise](https://github.com/go-skynet/LocalAI/tree/master/examples/flowise) example ( [mudler](https://github.com/mudler) )
+- 💡 [AutoGPT](https://github.com/mudler/LocalAI-examples/tree/main/autoGPT) example ( [mudler](https://github.com/mudler) )
+- 💡 [PrivateGPT](https://github.com/mudler/LocalAI-examples/tree/main/privateGPT) example ( [mudler](https://github.com/mudler) )
+- 💡 [Flowise](https://github.com/mudler/LocalAI-examples/tree/main/flowise) example ( [mudler](https://github.com/mudler) )
 
 Two new projects offer now direct integration with LocalAI!
 
@@ -449,7 +449,7 @@ Now LocalAI can generate images too:
 
 - 14-05-2023: __v1.11.1__ released! `rwkv` backend patch release
 - 13-05-2023: __v1.11.0__ released! 🔥 Updated `llama.cpp` bindings: This update includes a breaking change in the model files ( https://github.com/ggerganov/llama.cpp/pull/1405 ) - old models should still work with the `gpt4all-llama` backend.
-- 12-05-2023: __v1.10.0__ released! 🔥🔥 Updated `gpt4all` bindings. Added support for GPTNeox (experimental), RedPajama (experimental), Starcoder (experimental), Replit (experimental), MosaicML MPT. Also now `embeddings` endpoint supports tokens arrays. See the [langchain-chroma](https://github.com/go-skynet/LocalAI/tree/master/examples/langchain-chroma) example! Note - this update does NOT include https://github.com/ggerganov/llama.cpp/pull/1405 which makes models incompatible.
+- 12-05-2023: __v1.10.0__ released! 🔥🔥 Updated `gpt4all` bindings. Added support for GPTNeox (experimental), RedPajama (experimental), Starcoder (experimental), Replit (experimental), MosaicML MPT. Also now `embeddings` endpoint supports tokens arrays. See the [langchain-chroma](https://github.com/mudler/LocalAI-examples/tree/main/langchain-chroma) example! Note - this update does NOT include https://github.com/ggerganov/llama.cpp/pull/1405 which makes models incompatible.
 - 11-05-2023: __v1.9.0__ released! 🔥 Important whisper updates ( {{< pr "233" >}} {{< pr "229" >}} ) and extended gpt4all model families support ( {{< pr "232" >}} ). Redpajama/dolly experimental ( {{< pr "214" >}} )
 - 10-05-2023: __v1.8.0__ released! 🔥 Added support for fast and accurate embeddings with `bert.cpp` ( {{< pr "222" >}} )
 - 09-05-2023: Added experimental support for transcriptions endpoint ( {{< pr "211" >}} )

docs/data/version.json

@@ -1,3 +1,3 @@
 {
-  "version": "v3.2.3"
+  "version": "v3.3.2"
 }

docs/static/install.sh

@@ -715,11 +715,10 @@ install_docker() {
             $envs \
             -d -p $PORT:8080 --name local-ai localai/localai:$IMAGE_TAG $STARTCOMMAND
     elif [ "$HAS_INTEL" ]; then
-        # Default to FP32 for better compatibility
-        IMAGE_TAG=${LOCALAI_VERSION}-gpu-intel-f32
+        IMAGE_TAG=${LOCALAI_VERSION}-gpu-intel
         # AIO
         if [ "$USE_AIO" = true ]; then
-            IMAGE_TAG=${LOCALAI_VERSION}-aio-gpu-intel-f32
+            IMAGE_TAG=${LOCALAI_VERSION}-aio-gpu-intel
         fi
 
         info "Starting LocalAI Docker container..."

gallery/harmony.yaml

@@ -0,0 +1,69 @@
+---
+name: "harmony"
+
+config_file: |
+  mmap: true
+  backend: "llama-cpp"
+  template:
+    chat_message: |-
+      <|start|>{{ if .FunctionCall -}}functions.{{ .FunctionCall.Name }} to=assistant{{ else if eq .RoleName "assistant"}}assistant<|channel|>final<|message|>{{else}}{{ .RoleName }}{{end}}<|message|>
+      {{- if .Content -}}
+      {{- .Content -}}
+      {{- end -}}
+      {{- if .FunctionCall -}}
+      {{- toJson .FunctionCall -}}
+      {{- end -}}<|end|>
+    function: |-
+      <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
+      Knowledge cutoff: 2024-06
+      Current date: {{ now | date "Mon Jan 2 15:04:05 MST 2006" }}
+
+      Reasoning: {{if eq .ReasoningEffort ""}}medium{{else}}{{.ReasoningEffort}}{{end}}
+
+      # {{with .Metadata}}{{ if ne .system_prompt "" }}{{ .system_prompt }}{{ end }}{{else}}You are a friendly and helpful assistant.{{ end }}<|end|>{{- .Input -}}<|start|>assistant
+
+      # Tools
+
+      ## functions
+
+      namespace functions {
+      {{-range .Functions}}
+      {{if .Description }}
+      // {{ .Description }}
+      {{- end }}
+      {{- if and .Parameters.Properties (gt (len .Parameters.Properties) 0) }}
+      type {{ .Name }} = (_: {
+      {{- range $name, $prop := .Parameters.Properties }}
+      {{- if $prop.Description }}
+        // {{ $prop.Description }}
+      {{- end }}
+        {{ $name }}: {{ if gt (len $prop.Type) 1 }}{{ range $i, $t := $prop.Type }}{{ if $i }} | {{ end }}{{ $t }}{{ end }}{{ else }}{{ index $prop.Type 0 }}{{ end }},
+      {{- end }}
+      }) => any;
+      {{- else }}
+      type {{ .Function.Name }} = () => any;
+      {{- end }}
+      {{- end }}{{/* end of range .Functions */}}
+      } // namespace functions
+
+      # Instructions
+
+      <|end|>{{.Input -}}<|start|>assistant
+    chat: |-
+      <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
+      Knowledge cutoff: 2024-06
+      Current date: {{ now | date "Mon Jan 2 15:04:05 MST 2006" }}
+
+      Reasoning: {{if eq .ReasoningEffort ""}}medium{{else}}{{.ReasoningEffort}}{{end}}
+
+      # {{with .Metadata}}{{ if ne .system_prompt "" }}{{ .system_prompt }}{{ end }}{{else}}You are a friendly and helpful assistant.{{ end }}<|end|>{{- .Input -}}<|start|>assistant
+    completion: |
+      {{.Input}}
+  context_size: 8192
+  f16: true
+  stopwords:
+  - '<|im_end|>'
+  - '<dummy32000>'
+  - '</s>'
+  - '<|endoftext|>'
+  - '<|return|>'

gallery/index.yaml

@@ -1,4 +1,281 @@
 ---
+- name: "kokoro"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://github.com/hexgrad/kokoro
+  license: apache-2.0
+  tags:
+    - tts
+    - kokoro
+    - gpu
+    - cpu
+    - text-to-speech
+  description: |
+    Kokoro is an open-weight TTS model with 82 million parametrs. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects.
+  overrides:
+    backend: "kokoro"
+    name: "kokoro"
+    description: "Kokoro is an open-weight TTS model with 82 million parametrs. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects."
+    parameters:
+      voice: "af_heart"
+    options:
+      # this is for american
+      # 🇺🇸 'a' => American English, 🇬🇧 'b' => British English
+      # 🇪🇸 'e' => Spanish es
+      # 🇫🇷 'f' => French fr-fr
+      # 🇮🇳 'h' => Hindi hi
+      # 🇮🇹 'i' => Italian it
+      # 🇯🇵 'j' => Japanese: pip install misaki[ja]
+      # 🇧🇷 'p' => Brazilian Portuguese pt-br
+      # 🇨🇳 'z' => Mandarin Chinese: pip install misaki[zh]
+      - lang_code:a
+    known_usecases:
+      - tts
+- name: "kitten-tts"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://github.com/KittenML/KittenTTS
+  license: apache-2.0
+  tags:
+    - tts
+    - kitten-tts
+    - gpu
+    - cpu
+    - text-to-speech
+  description: |
+    Kitten TTS is an open-source realistic text-to-speech model with just 15 million parameters, designed for lightweight deployment and high-quality voice synthesis.
+  overrides:
+    backend: "kitten-tts"
+    name: "kitten-tts"
+    description: "Kitten TTS is a text-to-speech model that can generate speech from text."
+    parameters:
+      model: "KittenML/kitten-tts-nano-0.1"
+      voice: "expr-voice-5-f"
+    known_usecases:
+      - tts
+- &qwenimage
+  name: "qwen-image"
+  url: "github:mudler/LocalAI/gallery/qwen-image.yaml@master"
+  urls:
+    - https://huggingface.co/Qwen/Qwen-Image
+  icon: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/qwen_image_logo.png
+  license: apache-2.0
+  tags:
+    - qwen-image
+    - gpu
+    - text-to-image
+  description: |
+    We are thrilled to release Qwen-Image, an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing. Experiments show strong general capabilities in both image generation and editing, with exceptional performance in text rendering, especially for Chinese.
+- &gptoss
+  name: "gpt-oss-20b"
+  url: "github:mudler/LocalAI/gallery/harmony.yaml@master"
+  license: apache-2.0
+  tags:
+    - gguf
+    - gpu
+    - cpu
+    - gguf
+    - openai
+  icon: https://raw.githubusercontent.com/openai/gpt-oss/main/docs/gpt-oss-20b.svg
+  urls:
+    - https://huggingface.co/openai/gpt-oss-20b
+    - https://huggingface.co/ggml-org/gpt-oss-20b-GGUF
+  description: |
+    Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
+
+    We’re releasing two flavors of the open models:
+
+        gpt-oss-120b — for production, general purpose, high reasoning use cases that fits into a single H100 GPU (117B parameters with 5.1B active parameters)
+        gpt-oss-20b — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
+
+    Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
+
+        This model card is dedicated to the smaller gpt-oss-20b model. Check out gpt-oss-120b for the larger model.
+
+    Highlights
+
+        Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
+        Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
+        Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
+        Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
+        Agentic capabilities: Use the models’ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
+        Native MXFP4 quantization: The models are trained with native MXFP4 precision for the MoE layer, making gpt-oss-120b run on a single H100 GPU and the gpt-oss-20b model run within 16GB of memory.
+  overrides:
+    parameters:
+      model: gpt-oss-20b-mxfp4.gguf
+  files:
+    - filename: gpt-oss-20b-mxfp4.gguf
+      uri: huggingface://ggml-org/gpt-oss-20b-GGUF/gpt-oss-20b-mxfp4.gguf
+      sha256: be37a636aca0fc1aae0d32325f82f6b4d21495f06823b5fbc1898ae0303e9935
+- !!merge <<: *gptoss
+  name: "gpt-oss-120b"
+  url: "github:mudler/LocalAI/gallery/harmony.yaml@master"
+  icon: https://raw.githubusercontent.com/openai/gpt-oss/main/docs/gpt-oss-120b.svg
+  urls:
+    - https://huggingface.co/openai/gpt-oss-120b
+    - https://huggingface.co/ggml-org/gpt-oss-120b-GGUF
+  overrides:
+    parameters:
+      model: gpt-oss-120b-mxfp4-00001-of-00003.gguf
+  files:
+    - filename: gpt-oss-120b-mxfp4-00001-of-00003.gguf
+      uri: huggingface://ggml-org/gpt-oss-120b-GGUF/gpt-oss-120b-mxfp4-00001-of-00003.gguf
+      sha256: e2865eb6c1df7b2ffbebf305cd5d9074d5ccc0fe3b862f98d343a46dad1606f9
+    - filename: gpt-oss-120b-mxfp4-00002-of-00003.gguf
+      uri: huggingface://ggml-org/gpt-oss-120b-GGUF/gpt-oss-120b-mxfp4-00002-of-00003.gguf
+      sha256: 346492f65891fb27cac5c74a8c07626cbfeb4211cd391ec4de37dbbe3109a93b
+    - filename: gpt-oss-120b-mxfp4-00003-of-00003.gguf
+      uri: huggingface://ggml-org/gpt-oss-120b-GGUF/gpt-oss-120b-mxfp4-00003-of-00003.gguf
+      sha256: 66dca81040933f5a49177e82c479c51319cefb83bd22dad9f06dad45e25f1463
+- !!merge <<: *gptoss
+  name: "openai_gpt-oss-20b-neo"
+  icon: https://huggingface.co/DavidAU/Openai_gpt-oss-20b-NEO-GGUF/resolve/main/matrix1.gif
+  urls:
+    - https://huggingface.co/DavidAU/Openai_gpt-oss-20b-NEO-GGUF
+  description: |
+    These are NEO Imatrix GGUFs, NEO dataset by DavidAU.
+
+    NEO dataset improves overall performance, and is for all use cases.
+
+    Example output below (creative), using settings below.
+
+    Model also passed "hard" coding test too (6 experts); no issues (IQ4_NL).
+
+    (Forcing the model to create code with no dependencies and limits of coding short cuts, with multiple loops, and in real time with no blocking in a language that does not support it normally.)
+
+    Due to quanting issues with this model (which result in oddball quant sizes / mixtures), only TESTED quants will be uploaded (at the moment).
+  overrides:
+    parameters:
+      model: OpenAI-20B-NEO-MXFP4_MOE4.gguf
+  files:
+    - filename: OpenAI-20B-NEO-MXFP4_MOE4.gguf
+      sha256: 066c84a0844b1f1f4515e5c64095fe4c67e86d5eb70db4e368e283b1134d9c1e
+      uri: huggingface://DavidAU/Openai_gpt-oss-20b-NEO-GGUF/OpenAI-20B-NEO-MXFP4_MOE4.gguf
+- !!merge <<: *gptoss
+  name: "huihui-ai_huihui-gpt-oss-20b-bf16-abliterated"
+  urls:
+    - https://huggingface.co/huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated
+    - https://huggingface.co/bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF
+  description: |
+    This is an uncensored version of unsloth/gpt-oss-20b-BF16 created with abliteration (see remove-refusals-with-transformers to know more about it).
+  overrides:
+    parameters:
+      model: huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-MXFP4_MOE.gguf
+  files:
+    - filename: huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-MXFP4_MOE.gguf
+      sha256: abca50d1bd95c49d71db36aad0f38090ea5465ce148634c496a48bc87030bdd9
+      uri: huggingface://bartowski/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-GGUF/huihui-ai_Huihui-gpt-oss-20b-BF16-abliterated-MXFP4_MOE.gguf
+- !!merge <<: *gptoss
+  name: "openai-gpt-oss-20b-abliterated-uncensored-neo-imatrix"
+  icon: https://huggingface.co/DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf/resolve/main/power-the-matrix.gif
+  urls:
+    - https://huggingface.co/DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf
+  description: |
+    These are NEO Imatrix GGUFs, NEO dataset by DavidAU.
+
+    NEO dataset improves overall performance, and is for all use cases.
+
+    This model uses Huihui-gpt-oss-20b-BF16-abliterated as a base which DE-CENSORS the model and removes refusals.
+
+    Example output below (creative; IQ4_NL), using settings below.
+
+    This model can be a little rough around the edges (due to abliteration) ; make sure you see the settings below for best operation.
+
+    It can also be creative, off the shelf crazy and rational too.
+
+    Enjoy!
+  overrides:
+    parameters:
+      model: OpenAI-20B-NEOPlus-Uncensored-IQ4_NL.gguf
+  files:
+    - filename: OpenAI-20B-NEOPlus-Uncensored-IQ4_NL.gguf
+      sha256: 274ffaaf0783270c071006842ffe60af73600fc63c2b6153c0701b596fc3b122
+      uri: huggingface://DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf/OpenAI-20B-NEOPlus-Uncensored-IQ4_NL.gguf
+- name: "chatterbox"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  icon: https://private-user-images.githubusercontent.com/660224/448166653-bd8c5f03-e91d-4ee5-b680-57355da204d1.png
+  license: "mit"
+  urls:
+    - https://github.com/resemble-ai/chatterbox
+  tags:
+    - tts
+    - dia
+    - gpu
+    - text-to-speech
+  description: |
+    Chatterbox, Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations.
+  overrides:
+    backend: "chatterbox"
+    name: "chatterbox"
+    known_usecases:
+      - tts
+- name: "dia"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  icon: https://github.com/nari-labs/dia/raw/main/dia/static/images/banner.png
+  urls:
+    - https://github.com/nari-labs/dia
+    - https://huggingface.co/nari-labs/Dia-1.6B-0626
+  license: apache-2.0
+  tags:
+    - tts
+    - dia
+    - gpu
+    - text-to-speech
+  overrides:
+    backend: "transformers"
+    name: "dia"
+    description: "Dia is a 1.6B parameter text to speech model created by Nari Labs."
+    parameters:
+      model: nari-labs/Dia-1.6B-0626
+    type: DiaForConditionalGeneration
+    known_usecases:
+      - tts
+- name: "outetts"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://github.com/edwko/OuteTTS
+  license: apache-2.0
+  tags:
+    - tts
+    - gpu
+    - text-to-speech
+  overrides:
+    backend: "transformers"
+    name: "outetts"
+    description: "OuteTTS is a 1.6B parameter text to speech model created by OuteAI."
+    parameters:
+      model: OuteAI/OuteTTS-0.3-1B
+    type: OuteTTS
+    known_usecases:
+      - tts
+- &afm
+  name: "arcee-ai_afm-4.5b"
+  url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
+  icon: https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/Lj9YVLIKKdImV_jID0A1g.png
+  license: aml
+  urls:
+    - https://huggingface.co/arcee-ai/AFM-4.5B
+    - https://huggingface.co/bartowski/arcee-ai_AFM-4.5B-GGUF
+  tags:
+    - gguf
+    - gpu
+    - gpu
+    - text-generation
+  description: |
+    AFM-4.5B is a 4.5 billion parameter instruction-tuned model developed by Arcee.ai, designed for enterprise-grade performance across diverse deployment environments from cloud to edge. The base model was trained on a dataset of 8 trillion tokens, comprising 6.5 trillion tokens of general pretraining data followed by 1.5 trillion tokens of midtraining data with enhanced focus on mathematical reasoning and code generation. Following pretraining, the model underwent supervised fine-tuning on high-quality instruction datasets. The instruction-tuned model was further refined through reinforcement learning on verifiable rewards as well as for human preference. We use a modified version of TorchTitan for pretraining, Axolotl for supervised fine-tuning, and a modified version of Verifiers for reinforcement learning.
+
+    The development of AFM-4.5B prioritized data quality as a fundamental requirement for achieving robust model performance. We collaborated with DatologyAI, a company specializing in large-scale data curation. DatologyAI's curation pipeline integrates a suite of proprietary algorithms—model-based quality filtering, embedding-based curation, target distribution-matching, source mixing, and synthetic data. Their expertise enabled the creation of a curated dataset tailored to support strong real-world performance.
+
+    The model architecture follows a standard transformer decoder-only design based on Vaswani et al., incorporating several key modifications for enhanced performance and efficiency. Notable architectural features include grouped query attention for improved inference efficiency and ReLU^2 activation functions instead of SwiGLU to enable sparsification while maintaining or exceeding performance benchmarks.
+
+    The model available in this repo is the instruct model following supervised fine-tuning and reinforcement learning.
+  overrides:
+    parameters:
+      model: arcee-ai_AFM-4.5B-Q4_K_M.gguf
+  files:
+    - filename: arcee-ai_AFM-4.5B-Q4_K_M.gguf
+      sha256: f05516b323f581bebae1af2cbf900d83a2569b0a60c54366daf4a9c15ae30d4f
+      uri: huggingface://bartowski/arcee-ai_AFM-4.5B-GGUF/arcee-ai_AFM-4.5B-Q4_K_M.gguf
 - &rfdetr
   name: "rfdetr-base"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
@@ -35,7 +312,7 @@
     - https://huggingface.co/Dream-org/Dream-v0-Instruct-7B
     - https://huggingface.co/bartowski/Dream-org_Dream-v0-Instruct-7B-GGUF
   description: |
-      This is the instruct model of Dream 7B, which is an open diffusion large language model with top-tier performance.
+    This is the instruct model of Dream 7B, which is an open diffusion large language model with top-tier performance.
   overrides:
     parameters:
       model: Dream-org_Dream-v0-Instruct-7B-Q4_K_M.gguf
@@ -1878,6 +2155,82 @@
     - filename: Menlo_Lucy-128k-Q4_K_M.gguf
       sha256: fb3e591cccc5d2821f3c615fd6dc2ca86d409f56fbc124275510a9612a90e61f
       uri: huggingface://bartowski/Menlo_Lucy-128k-GGUF/Menlo_Lucy-128k-Q4_K_M.gguf
+- !!merge <<: *qwen3
+  name: "qwen_qwen3-30b-a3b-instruct-2507"
+  urls:
+    - https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507
+    - https://huggingface.co/bartowski/Qwen_Qwen3-30B-A3B-Instruct-2507-GGUF
+  description: |
+    We introduce the updated version of the Qwen3-30B-A3B non-thinking mode, named Qwen3-30B-A3B-Instruct-2507, featuring the following key enhancements:
+
+        Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.
+        Substantial gains in long-tail knowledge coverage across multiple languages.
+        Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation.
+        Enhanced capabilities in 256K long-context understanding.
+  overrides:
+    parameters:
+      model: Qwen_Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf
+  files:
+    - filename: Qwen_Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf
+      sha256: 382b4f5a164d200f93790ee0e339fae12852896d23485cfb203ce868fea33a95
+      uri: huggingface://bartowski/Qwen_Qwen3-30B-A3B-Instruct-2507-GGUF/Qwen_Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf
+- !!merge <<: *qwen3
+  name: "qwen_qwen3-30b-a3b-thinking-2507"
+  urls:
+    - https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507
+    - https://huggingface.co/bartowski/Qwen_Qwen3-30B-A3B-Thinking-2507-GGUF
+  description: |
+    Over the past three months, we have continued to scale the thinking capability of Qwen3-30B-A3B, improving both the quality and depth of reasoning. We are pleased to introduce Qwen3-30B-A3B-Thinking-2507, featuring the following key enhancements:
+    Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise.
+    Markedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences.
+    Enhanced 256K long-context understanding capabilities.
+    NOTE: This version has an increased thinking length. We strongly recommend its use in highly complex reasoning tasks.
+  overrides:
+    parameters:
+      model: Qwen_Qwen3-30B-A3B-Thinking-2507-Q4_K_M.gguf
+  files:
+    - filename: Qwen_Qwen3-30B-A3B-Thinking-2507-Q4_K_M.gguf
+      sha256: 1359aa08e2f2dfe7ce4b5ff88c4c996e6494c9d916b1ebacd214bb74bbd5a9db
+      uri: huggingface://bartowski/Qwen_Qwen3-30B-A3B-Thinking-2507-GGUF/Qwen_Qwen3-30B-A3B-Thinking-2507-Q4_K_M.gguf
+- !!merge <<: *qwen3
+  name: "qwen_qwen3-4b-instruct-2507"
+  urls:
+    - https://huggingface.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF
+    - https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507
+  description: |
+    We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements:
+
+    Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.
+    Substantial gains in long-tail knowledge coverage across multiple languages.
+    Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation.
+    Enhanced capabilities in 256K long-context understanding.
+  overrides:
+    parameters:
+      model: Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf
+  files:
+    - filename: Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf
+      sha256: 260b5b5b6ad73e44df81a43ea1f5c11c37007b6bac18eb3cd2016e8667c19662
+      uri: huggingface://bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF/Qwen_Qwen3-4B-Instruct-2507-Q8_0.gguf
+- !!merge <<: *qwen3
+  name: "qwen_qwen3-4b-thinking-2507"
+  urls:
+    - https://huggingface.co/bartowski/Qwen_Qwen3-4B-Thinking-2507-GGUF
+    - https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507
+  description: |
+    Over the past three months, we have continued to scale the thinking capability of Qwen3-4B, improving both the quality and depth of reasoning. We are pleased to introduce Qwen3-4B-Thinking-2507, featuring the following key enhancements:
+
+        Significantly improved performance on reasoning tasks, including logical reasoning, mathematics, science, coding, and academic benchmarks that typically require human expertise.
+        Markedly better general capabilities, such as instruction following, tool usage, text generation, and alignment with human preferences.
+        Enhanced 256K long-context understanding capabilities.
+
+    NOTE: This version has an increased thinking length. We strongly recommend its use in highly complex reasoning tasks.
+  overrides:
+    parameters:
+      model: Qwen_Qwen3-4B-Thinking-2507-Q8_0.gguf
+  files:
+    - filename: Qwen_Qwen3-4B-Thinking-2507-Q8_0.gguf
+      sha256: 2c08db093bc57c2c77222d27ffe8d41cb0b5648e66ba84e5fb9ceab429f6735c
+      uri: huggingface://bartowski/Qwen_Qwen3-4B-Thinking-2507-GGUF/Qwen_Qwen3-4B-Thinking-2507-Q8_0.gguf
 - &gemma3
   url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
   name: "gemma-3-27b-it"
@@ -11576,6 +11929,29 @@
     - filename: ockerman0_AnubisLemonade-70B-v1.1-Q4_K_M.gguf
       sha256: e217b2c39d4fae8499ca2a24ff8c7025ec93cd16883aa57f43ac9240222c4754
       uri: huggingface://bartowski/ockerman0_AnubisLemonade-70B-v1.1-GGUF/ockerman0_AnubisLemonade-70B-v1.1-Q4_K_M.gguf
+- !!merge <<: *llama31
+  name: "tarek07_nomad-llama-70b"
+  icon: https://cdn-uploads.huggingface.co/production/uploads/64909c086073a0cd172d0411/5F7S8kdO8NTMua6iCRTUO.png
+  urls:
+    - https://huggingface.co/Tarek07/Nomad-LLaMa-70B
+    - https://huggingface.co/bartowski/Tarek07_Nomad-LLaMa-70B-GGUF
+  description: |
+    I decided to make a simple model for a change, with some models I was curious to see work together.
+    models:
+      - model: ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large
+      - model: TheDrummer/Anubis-70B-v1.1
+      - model: Mawdistical/Vulpine-Seduction-70B
+      - model: Darkhn/L3.3-70B-Animus-V5-Pro
+      - model: zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B
+      - model: Sao10K/Llama-3.3-70B-Vulpecula-r1
+    base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
+  overrides:
+    parameters:
+      model: Tarek07_Nomad-LLaMa-70B-Q4_K_M.gguf
+  files:
+    - filename: Tarek07_Nomad-LLaMa-70B-Q4_K_M.gguf
+      sha256: 734c7042a84cd6c059c4ddd3ffb84b23752aeaaf670c5cbb0031f8128ec5ffc8
+      uri: huggingface://bartowski/Tarek07_Nomad-LLaMa-70B-GGUF/Tarek07_Nomad-LLaMa-70B-Q4_K_M.gguf
 - &deepseek
   url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" ## Deepseek
   name: "deepseek-coder-v2-lite-instruct"
@@ -14070,6 +14446,21 @@
     - filename: entfane_math-genius-7B-Q4_K_M.gguf
       sha256: cd3a3c898a2dfb03d17a66db81b743f2d66981e0ceb92e8669a4af61217feed7
       uri: huggingface://bartowski/entfane_math-genius-7B-GGUF/entfane_math-genius-7B-Q4_K_M.gguf
+- !!merge <<: *mistral03
+  name: "impish_nemo_12b"
+  url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
+  icon: https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B/resolve/main/Images/Impish_Nemo_12B.png
+  urls:
+    - https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B
+    - https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B_GGUF
+  description: "August 2025, Impish_Nemo_12B — my best model yet. And unlike a typical Nemo, this one can take in much higher temperatures (works well with 1+). Oh, and regarding following the character card: It somehow gotten even better, to the point of it being straight up uncanny \U0001F643 (I had to check twice that this model was loaded, and not some 70B!)\n\nI feel like this model could easily replace models much larger than itself for adventure or roleplay, for assistant tasks, obviously not, but the creativity here? Off the charts. Characters have never felt so alive and in the moment before — they’ll use insinuation, manipulation, and, if needed (or provoked) — force. They feel so very present.\n\nThat look on Neo’s face when he opened his eyes and said, “I know Kung Fu”? Well, Impish_Nemo_12B had pretty much the same moment — and it now knows more than just Kung Fu, much, much more. It wasn’t easy, and it’s a niche within a niche, but as promised almost half a year ago — it is now done.\n\nImpish_Nemo_12B is smart, sassy, creative, and got a lot of unhingedness too — these are baked-in deep into every interaction. It took the innate Mistral's relative freedom, and turned it up to 11. It very well maybe too much for many, but after testing and interacting with so many models, I find this 'edge' of sorts, rather fun and refreshing.\n\nAnyway, the dataset used is absolutely massive, tons of new types of data and new domains of knowledge (Morrowind fandom, fighting, etc...). The whole dataset is a very well-balanced mix, and resulted in a model with extremely strong common sense for a 12B. Regarding response length — there's almost no response-length bias here, this one is very much dynamic and will easily adjust reply length based on 1–3 examples of provided dialogue.\n\nOh, and the model comes with 3 new Character Cards, 2 Roleplay and 1 Adventure!\n"
+  overrides:
+    parameters:
+      model: Impish_Nemo_12B-Q6_K.gguf
+  files:
+    - filename: Impish_Nemo_12B-Q6_K.gguf
+      sha256: e0ce3adbed2718e144f477721c2ad68b6e3cccd95fc27dbe8f0135be76c99c72
+      uri: huggingface://SicariusSicariiStuff/Impish_Nemo_12B_GGUF/Impish_Nemo_12B-Q6_K.gguf
 - &mudler
   url: "github:mudler/LocalAI/gallery/mudler.yaml@master" ### START mudler's LocalAI specific-models
   name: "LocalAI-llama3-8b-function-call-v0.2"
@@ -19079,6 +19470,148 @@
   overrides:
     parameters:
       model: SicariusSicariiStuff/flux.1dev-abliteratedv2
+- name: flux.1-kontext-dev
+  license: flux-1-dev-non-commercial-license
+  url: "github:mudler/LocalAI/gallery/flux-ggml.yaml@master"
+  icon: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/media/main/teaser.png
+  description: |
+    FLUX.1 Kontext [dev] is a 12 billion parameter rectified flow transformer capable of editing images based on text instructions. For more information, please read our blog post and our technical report. You can find information about the [pro] version in here.
+    Key Features
+        Change existing images based on an edit instruction.
+        Have character, style and object reference without any finetuning.
+        Robust consistency allows users to refine an image through multiple successive edits with minimal visual drift.
+        Trained using guidance distillation, making FLUX.1 Kontext [dev] more efficient.
+        Open weights to drive new scientific research, and empower artists to develop innovative workflows.
+        Generated outputs can be used for personal, scientific, and commercial purposes, as described in the FLUX.1 [dev] Non-Commercial License.
+  urls:
+    - https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev
+    - https://huggingface.co/QuantStack/FLUX.1-Kontext-dev-GGUF
+  tags:
+    - image-to-image
+    - flux
+    - gpu
+    - cpu
+  overrides:
+    parameters:
+      model: flux1-kontext-dev-Q8_0.gguf
+  files:
+    - filename: "flux1-kontext-dev-Q8_0.gguf"
+      sha256: "ff2ff71c3755c8ab394398a412252c23382a83138b65190b16e736d457b80f73"
+      uri: "huggingface://QuantStack/FLUX.1-Kontext-dev-GGUF/flux1-kontext-dev-Q8_0.gguf"
+    - filename: ae.safetensors
+      sha256: afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
+      uri: https://huggingface.co/ChuckMcSneed/FLUX.1-dev/resolve/main/ae.safetensors
+    - filename: clip_l.safetensors
+      sha256: 660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors
+    - filename: t5xxl_fp16.safetensors
+      sha256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors
+- !!merge <<: *flux
+  name: flux.1-dev-ggml-q8_0
+  license: flux-1-dev-non-commercial-license
+  url: "github:mudler/LocalAI/gallery/flux-ggml.yaml@master"
+  urls:
+    - https://huggingface.co/black-forest-labs/FLUX.1-dev
+    - https://huggingface.co/city96/FLUX.1-dev-gguf
+  overrides:
+    parameters:
+      model: flux1-dev-Q8_0.gguf
+  files:
+    - filename: "flux1-dev-Q8_0.gguf"
+      sha256: "129032f32224bf7138f16e18673d8008ba5f84c1ec74063bf4511a8bb4cf553d"
+      uri: "huggingface://city96/FLUX.1-dev-gguf/flux1-dev-Q8_0.gguf"
+    - filename: ae.safetensors
+      sha256: afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
+      uri: https://huggingface.co/ChuckMcSneed/FLUX.1-dev/resolve/main/ae.safetensors
+    - filename: clip_l.safetensors
+      sha256: 660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors
+    - filename: t5xxl_fp16.safetensors
+      sha256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors
+- !!merge <<: *flux
+  name: flux.1-dev-ggml-abliterated-v2-q8_0
+  url: "github:mudler/LocalAI/gallery/flux-ggml.yaml@master"
+  description: |
+    FLUX.1 [dev] is an abliterated version of FLUX.1 [dev]
+  urls:
+    - https://huggingface.co/black-forest-labs/FLUX.1-dev
+    - https://huggingface.co/t8star/flux.1-dev-abliterated-V2-GGUF
+  overrides:
+    parameters:
+      model: T8-flux.1-dev-abliterated-V2-GGUF-Q8_0.gguf
+  files:
+    - filename: "T8-flux.1-dev-abliterated-V2-GGUF-Q8_0.gguf"
+      sha256: "aba8163ff644018da195212a1c33aeddbf802a0c2bba96abc584a2d0b6b42272"
+      uri: "huggingface://t8star/flux.1-dev-abliterated-V2-GGUF/T8-flux.1-dev-abliterated-V2-GGUF-Q8_0.gguf"
+    - filename: ae.safetensors
+      sha256: afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
+      uri: https://huggingface.co/ChuckMcSneed/FLUX.1-dev/resolve/main/ae.safetensors
+    - filename: clip_l.safetensors
+      sha256: 660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors
+    - filename: t5xxl_fp16.safetensors
+      sha256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors
+- !!merge <<: *flux
+  name: flux.1-krea-dev-ggml
+  url: "github:mudler/LocalAI/gallery/flux-ggml.yaml@master"
+  description: |
+    FLUX.1 Krea [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post and Krea's blog post.
+    Cutting-edge output quality, with a focus on aesthetic photography.
+    Competitive prompt following, matching the performance of closed source alternatives.
+    Trained using guidance distillation, making FLUX.1 Krea [dev] more efficient.
+    Open weights to drive new scientific research, and empower artists to develop innovative workflows.
+    Generated outputs can be used for personal, scientific, and commercial purposes, as described in the flux-1-dev-non-commercial-license.
+  urls:
+    - https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev
+    - https://huggingface.co/QuantStack/FLUX.1-Krea-dev-GGUF
+  overrides:
+    parameters:
+      model: flux1-krea-dev-Q4_K_M.gguf
+  files:
+    - filename: "flux1-krea-dev-Q4_K_M.gguf"
+      sha256: "cf199b88509be2b3476a3372ff03eaaa662cb2b5d3710abf939ebb4838dbdcaf"
+      uri: "huggingface://QuantStack/FLUX.1-Krea-dev-GGUF/flux1-krea-dev-Q4_K_M.gguf"
+    - filename: ae.safetensors
+      sha256: afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
+      uri: https://huggingface.co/ChuckMcSneed/FLUX.1-dev/resolve/main/ae.safetensors
+    - filename: clip_l.safetensors
+      sha256: 660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors
+    - filename: t5xxl_fp16.safetensors
+      sha256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors
+- !!merge <<: *flux
+  name: flux.1-krea-dev-ggml-q8_0
+  url: "github:mudler/LocalAI/gallery/flux-ggml.yaml@master"
+  description: |
+    FLUX.1 Krea [dev] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our blog post and Krea's blog post.
+    Cutting-edge output quality, with a focus on aesthetic photography.
+    Competitive prompt following, matching the performance of closed source alternatives.
+    Trained using guidance distillation, making FLUX.1 Krea [dev] more efficient.
+    Open weights to drive new scientific research, and empower artists to develop innovative workflows.
+    Generated outputs can be used for personal, scientific, and commercial purposes, as described in the flux-1-dev-non-commercial-license.
+  urls:
+    - https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev
+    - https://huggingface.co/markury/FLUX.1-Krea-dev-gguf
+  overrides:
+    parameters:
+      model: flux1-krea-dev-Q8_0.gguf
+  files:
+    - filename: "flux1-krea-dev-Q8_0.gguf"
+      sha256: "0d085b1e3ae0b90e5dbf74da049a80a565617de622a147d28ee37a07761fbd90"
+      uri: "huggingface://markury/FLUX.1-Krea-dev-gguf/flux1-krea-dev-Q8_0.gguf"
+    - filename: ae.safetensors
+      sha256: afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
+      uri: https://huggingface.co/ChuckMcSneed/FLUX.1-dev/resolve/main/ae.safetensors
+    - filename: clip_l.safetensors
+      sha256: 660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors
+    - filename: t5xxl_fp16.safetensors
+      sha256: 6e480b09fae049a72d2a8c5fbccb8d3e92febeb233bbe9dfe7256958a9167635
+      uri: https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors
 - &whisper
   url: "github:mudler/LocalAI/gallery/whisper-base.yaml@master" ## Whisper
   name: "whisper-1"

gallery/qwen-image.yaml

@@ -0,0 +1,19 @@
+---
+name: "qwen-image"
+
+config_file: |
+    backend: diffusers
+    cfg_scale: 0
+    diffusers:
+      cuda: true
+      enable_parameters: num_inference_steps
+      pipeline_type: DiffusionPipeline
+    f16: true
+    low_vram: true
+    name: qwen-image
+    parameters:
+      model: Qwen/Qwen-Image
+    step: 50
+    options:
+      - true_cfg_scale:4.0
+      - torch_dtype:bf16

go.mod

@@ -1,8 +1,8 @@
 module github.com/mudler/LocalAI
 
-go 1.23.0
+go 1.23.8
 
-toolchain go1.23.1
+toolchain go1.24.5
 
 require (
 	dario.cat/mergo v1.0.1
@@ -28,18 +28,19 @@ require (
 	github.com/ipfs/go-log v1.0.5
 	github.com/jaypipes/ghw v0.12.0
 	github.com/joho/godotenv v1.5.1
-	github.com/klauspost/cpuid/v2 v2.2.9
-	github.com/libp2p/go-libp2p v0.40.0
+	github.com/klauspost/cpuid/v2 v2.2.10
+	github.com/libp2p/go-libp2p v0.43.0
 	github.com/mholt/archiver/v3 v3.5.1
 	github.com/microcosm-cc/bluemonday v1.0.26
-	github.com/mudler/edgevpn v0.30.2
+	github.com/mudler/edgevpn v0.31.0
 	github.com/mudler/go-processmanager v0.0.0-20240820160718-8b802d3ecf82
 	github.com/nikolalohinski/gonja/v2 v2.3.2
-	github.com/onsi/ginkgo/v2 v2.22.2
+	github.com/onsi/ginkgo/v2 v2.23.3
 	github.com/onsi/gomega v1.36.2
+	github.com/otiai10/copy v1.14.1
 	github.com/otiai10/openaigo v1.7.0
 	github.com/phayes/freeport v0.0.0-20220201140144-74d24b5ae9f5
-	github.com/prometheus/client_golang v1.21.0
+	github.com/prometheus/client_golang v1.22.0
 	github.com/rs/zerolog v1.33.0
 	github.com/russross/blackfriday v1.6.0
 	github.com/sashabaranov/go-openai v1.26.2
@@ -51,12 +52,12 @@ require (
 	github.com/testcontainers/testcontainers-go v0.35.0
 	github.com/tmc/langchaingo v0.1.12
 	github.com/valyala/fasthttp v1.55.0
-	go.opentelemetry.io/otel v1.34.0
+	go.opentelemetry.io/otel v1.35.0
 	go.opentelemetry.io/otel/exporters/prometheus v0.50.0
-	go.opentelemetry.io/otel/metric v1.34.0
+	go.opentelemetry.io/otel/metric v1.35.0
 	go.opentelemetry.io/otel/sdk/metric v1.28.0
 	google.golang.org/grpc v1.67.1
-	google.golang.org/protobuf v1.36.5
+	google.golang.org/protobuf v1.36.6
 	gopkg.in/yaml.v2 v2.4.0
 	gopkg.in/yaml.v3 v3.0.1
 	oras.land/oras-go/v2 v2.5.0
@@ -65,16 +66,13 @@ require (
 require (
 	github.com/containerd/platforms v0.2.1 // indirect
 	github.com/cpuguy83/dockercfg v0.3.2 // indirect
-	github.com/cpuguy83/go-md2man/v2 v2.0.5 // indirect
 	github.com/distribution/reference v0.6.0 // indirect
 	github.com/dustin/go-humanize v1.0.1 // indirect
 	github.com/fasthttp/websocket v1.5.8 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
 	github.com/go-task/slim-sprig/v3 v3.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
-	github.com/labstack/echo/v4 v4.13.3 // indirect
-	github.com/labstack/gommon v0.4.2 // indirect
-	github.com/libp2p/go-yamux/v5 v5.0.0 // indirect
+	github.com/libp2p/go-yamux/v5 v5.0.1 // indirect
 	github.com/magiconair/properties v1.8.7 // indirect
 	github.com/moby/docker-image-spec v1.3.1 // indirect
 	github.com/moby/patternmatcher v0.6.0 // indirect
@@ -83,40 +81,34 @@ require (
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/morikuni/aec v1.0.0 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
+	github.com/otiai10/mint v1.6.3 // indirect
 	github.com/pion/datachannel v1.5.10 // indirect
 	github.com/pion/dtls/v2 v2.2.12 // indirect
-	github.com/pion/dtls/v3 v3.0.4 // indirect
-	github.com/pion/ice/v2 v2.3.37 // indirect
-	github.com/pion/ice/v4 v4.0.6 // indirect
-	github.com/pion/interceptor v0.1.37 // indirect
+	github.com/pion/dtls/v3 v3.0.6 // indirect
+	github.com/pion/ice/v4 v4.0.10 // indirect
+	github.com/pion/interceptor v0.1.40 // indirect
 	github.com/pion/logging v0.2.3 // indirect
-	github.com/pion/mdns v0.0.12 // indirect
 	github.com/pion/mdns/v2 v2.0.7 // indirect
 	github.com/pion/randutil v0.1.0 // indirect
 	github.com/pion/rtcp v1.2.15 // indirect
-	github.com/pion/rtp v1.8.11 // indirect
-	github.com/pion/sctp v1.8.35 // indirect
-	github.com/pion/sdp/v3 v3.0.10 // indirect
-	github.com/pion/srtp/v3 v3.0.4 // indirect
+	github.com/pion/rtp v1.8.19 // indirect
+	github.com/pion/sctp v1.8.39 // indirect
+	github.com/pion/sdp/v3 v3.0.13 // indirect
+	github.com/pion/srtp/v3 v3.0.6 // indirect
 	github.com/pion/stun v0.6.1 // indirect
 	github.com/pion/stun/v3 v3.0.0 // indirect
 	github.com/pion/transport/v2 v2.2.10 // indirect
 	github.com/pion/transport/v3 v3.0.7 // indirect
-	github.com/pion/turn/v2 v2.1.6 // indirect
-	github.com/pion/turn/v4 v4.0.0 // indirect
-	github.com/pion/webrtc/v4 v4.0.9 // indirect
+	github.com/pion/turn/v4 v4.0.2 // indirect
+	github.com/pion/webrtc/v4 v4.1.2 // indirect
 	github.com/rs/dnscache v0.0.0-20230804202142-fc85eb664529 // indirect
-	github.com/russross/blackfriday/v2 v2.1.0 // indirect
 	github.com/savsgio/gotils v0.0.0-20240303185622-093b76447511 // indirect
 	github.com/shirou/gopsutil/v4 v4.24.7 // indirect
-	github.com/urfave/cli/v2 v2.27.5 // indirect
-	github.com/valyala/fasttemplate v1.2.2 // indirect
 	github.com/wlynxg/anet v0.0.5 // indirect
-	github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1 // indirect
 	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.56.0 // indirect
-	go.uber.org/mock v0.5.0 // indirect
-	golang.org/x/time v0.8.0 // indirect
+	go.uber.org/mock v0.5.2 // indirect
+	golang.org/x/time v0.12.0 // indirect
 )
 
 require (
@@ -141,7 +133,6 @@ require (
 	github.com/containerd/errdefs v0.1.0 // indirect
 	github.com/containerd/log v0.1.0 // indirect
 	github.com/containerd/stargz-snapshotter/estargz v0.14.3 // indirect
-	github.com/coreos/go-systemd/v22 v22.5.0 // indirect
 	github.com/creachadair/otp v0.5.0 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/davidlazar/go-crypto v0.0.0-20200604182044-b73af7476f6c // indirect
@@ -154,7 +145,6 @@ require (
 	github.com/docker/go-connections v0.5.0
 	github.com/docker/go-units v0.5.0 // indirect
 	github.com/dsnet/compress v0.0.2-0.20210315054119-f66993602bf5 // indirect
-	github.com/elastic/gosigar v0.14.3 // indirect
 	github.com/flynn/noise v1.1.0 // indirect
 	github.com/francoispqt/gojay v1.2.13 // indirect
 	github.com/ghodss/yaml v1.0.0 // indirect
@@ -167,7 +157,6 @@ require (
 	github.com/go-openapi/jsonreference v0.21.0 // indirect
 	github.com/go-openapi/spec v0.21.0 // indirect
 	github.com/go-openapi/swag v0.23.0 // indirect
-	github.com/godbus/dbus/v5 v5.1.0 // indirect
 	github.com/gofiber/contrib/fiberzerolog v1.0.2
 	github.com/gofiber/template v1.8.3 // indirect
 	github.com/gofiber/utils v1.1.0 // indirect
@@ -175,45 +164,40 @@ require (
 	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
 	github.com/golang/snappy v0.0.4 // indirect
 	github.com/google/btree v1.1.3 // indirect
-	github.com/google/go-cmp v0.6.0 // indirect
+	github.com/google/go-cmp v0.7.0 // indirect
 	github.com/google/gopacket v1.1.19 // indirect
 	github.com/google/pprof v0.0.0-20250208200701-d0013a598941 // indirect
 	github.com/gorilla/css v1.0.1 // indirect
 	github.com/gorilla/websocket v1.5.3 // indirect
-	github.com/hashicorp/errwrap v1.1.0 // indirect
-	github.com/hashicorp/go-multierror v1.1.1 // indirect
 	github.com/hashicorp/golang-lru v1.0.2 // indirect
 	github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
 	github.com/henvic/httpretty v0.1.4 // indirect
 	github.com/huandu/xstrings v1.5.0 // indirect
 	github.com/huin/goupnp v1.3.0 // indirect
-	github.com/ipfs/boxo v0.27.4 // indirect
+	github.com/ipfs/boxo v0.30.0 // indirect
 	github.com/ipfs/go-cid v0.5.0 // indirect
-	github.com/ipfs/go-datastore v0.7.0 // indirect
-	github.com/ipfs/go-log/v2 v2.5.1 // indirect
+	github.com/ipfs/go-datastore v0.8.2 // indirect
+	github.com/ipfs/go-log/v2 v2.6.0 // indirect
 	github.com/ipld/go-ipld-prime v0.21.0 // indirect
 	github.com/jackpal/go-nat-pmp v1.0.2 // indirect
 	github.com/jaypipes/pcidb v1.0.0 // indirect
 	github.com/jbenet/go-temp-err-catcher v0.1.0 // indirect
-	github.com/jbenet/goprocess v0.1.4 // indirect
 	github.com/josharian/intern v1.0.0 // indirect
-	github.com/klauspost/compress v1.17.11 // indirect
+	github.com/klauspost/compress v1.18.0 // indirect
 	github.com/klauspost/pgzip v1.2.5 // indirect
-	github.com/koron/go-ssdp v0.0.5 // indirect
+	github.com/koron/go-ssdp v0.0.6 // indirect
 	github.com/libp2p/go-buffer-pool v0.1.0 // indirect
 	github.com/libp2p/go-cidranger v1.1.0 // indirect
 	github.com/libp2p/go-flow-metrics v0.2.0 // indirect
 	github.com/libp2p/go-libp2p-asn-util v0.4.1 // indirect
-	github.com/libp2p/go-libp2p-kad-dht v0.29.1 // indirect
-	github.com/libp2p/go-libp2p-kbucket v0.6.5 // indirect
-	github.com/libp2p/go-libp2p-pubsub v0.13.0 // indirect
+	github.com/libp2p/go-libp2p-kad-dht v0.33.1 // indirect
+	github.com/libp2p/go-libp2p-kbucket v0.7.0 // indirect
+	github.com/libp2p/go-libp2p-pubsub v0.14.2 // indirect
 	github.com/libp2p/go-libp2p-record v0.3.1 // indirect
-	github.com/libp2p/go-libp2p-routing-helpers v0.7.4 // indirect
+	github.com/libp2p/go-libp2p-routing-helpers v0.7.5 // indirect
 	github.com/libp2p/go-msgio v0.3.0 // indirect
-	github.com/libp2p/go-nat v0.2.0 // indirect
 	github.com/libp2p/go-netroute v0.2.2 // indirect
 	github.com/libp2p/go-reuseport v0.4.0 // indirect
-	github.com/libp2p/go-yamux/v4 v4.0.2 // indirect
 	github.com/libp2p/zeroconf/v2 v2.2.0 // indirect
 	github.com/lucasb-eyer/go-colorful v1.2.0 // indirect
 	github.com/lufia/plan9stats v0.0.0-20240819163618-b1d8f4d146e7 // indirect
@@ -222,7 +206,7 @@ require (
 	github.com/mattn/go-colorable v0.1.14 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/mattn/go-runewidth v0.0.15 // indirect
-	github.com/miekg/dns v1.1.63 // indirect
+	github.com/miekg/dns v1.1.66 // indirect
 	github.com/mikioh/tcpinfo v0.0.0-20190314235526-30a79bb1804b // indirect
 	github.com/mikioh/tcpopt v0.0.0-20190314235656-172688c1accc // indirect
 	github.com/minio/sha256-simd v1.0.1 // indirect
@@ -234,24 +218,23 @@ require (
 	github.com/moby/term v0.5.0 // indirect
 	github.com/mr-tron/base58 v1.2.0 // indirect
 	github.com/mudler/go-piper v0.0.0-20241023091659-2494246fd9fc
-	github.com/mudler/water v0.0.0-20221010214108-8c7313014ce0 // indirect
+	github.com/mudler/water v0.0.0-20250808092830-dd90dcf09025 // indirect
 	github.com/muesli/reflow v0.3.0 // indirect
 	github.com/muesli/termenv v0.15.2 // indirect
 	github.com/multiformats/go-base32 v0.1.0 // indirect
 	github.com/multiformats/go-base36 v0.2.0 // indirect
-	github.com/multiformats/go-multiaddr v0.14.0
+	github.com/multiformats/go-multiaddr v0.16.0
 	github.com/multiformats/go-multiaddr-dns v0.4.1 // indirect
 	github.com/multiformats/go-multiaddr-fmt v0.1.0 // indirect
 	github.com/multiformats/go-multibase v0.2.0 // indirect
-	github.com/multiformats/go-multicodec v0.9.0 // indirect
+	github.com/multiformats/go-multicodec v0.9.1 // indirect
 	github.com/multiformats/go-multihash v0.2.3 // indirect
-	github.com/multiformats/go-multistream v0.6.0 // indirect
+	github.com/multiformats/go-multistream v0.6.1 // indirect
 	github.com/multiformats/go-varint v0.0.7 // indirect
 	github.com/nwaples/rardecode v1.1.0 // indirect
 	github.com/olekukonko/tablewriter v0.0.5 // indirect
 	github.com/opencontainers/go-digest v1.0.0 // indirect
 	github.com/opencontainers/image-spec v1.1.0
-	github.com/opencontainers/runtime-spec v1.2.0 // indirect
 	github.com/opentracing/opentracing-go v1.2.0 // indirect
 	github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58 // indirect
 	github.com/peterbourgon/diskv v2.0.1+incompatible // indirect
@@ -262,13 +245,12 @@ require (
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/polydawn/refmt v0.89.0 // indirect
 	github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 // indirect
-	github.com/prometheus/client_model v0.6.1 // indirect
-	github.com/prometheus/common v0.62.0 // indirect
-	github.com/prometheus/procfs v0.15.1 // indirect
+	github.com/prometheus/client_model v0.6.2 // indirect
+	github.com/prometheus/common v0.64.0 // indirect
+	github.com/prometheus/procfs v0.16.1 // indirect
 	github.com/quic-go/qpack v0.5.1 // indirect
-	github.com/quic-go/quic-go v0.49.0 // indirect
-	github.com/quic-go/webtransport-go v0.8.1-0.20241018022711-4ac2c9250e66 // indirect
-	github.com/raulk/go-watchdog v1.3.0 // indirect
+	github.com/quic-go/quic-go v0.54.0 // indirect
+	github.com/quic-go/webtransport-go v0.9.0 // indirect
 	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/shoenig/go-m1cpu v0.1.6 // indirect
 	github.com/shopspring/decimal v1.4.0 // indirect
@@ -294,27 +276,27 @@ require (
 	github.com/yusufpapurcu/wmi v1.2.4 // indirect
 	go.opencensus.io v0.24.0 // indirect
 	go.opentelemetry.io/otel/sdk v1.31.0 // indirect
-	go.opentelemetry.io/otel/trace v1.34.0 // indirect
-	go.uber.org/dig v1.18.0 // indirect
-	go.uber.org/fx v1.23.0 // indirect
+	go.opentelemetry.io/otel/trace v1.35.0 // indirect
+	go.uber.org/dig v1.19.0 // indirect
+	go.uber.org/fx v1.24.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.0 // indirect
-	golang.org/x/crypto v0.33.0 // indirect
-	golang.org/x/exp v0.0.0-20250218142911-aa4b98e5adaa // indirect
-	golang.org/x/mod v0.23.0 // indirect
-	golang.org/x/net v0.35.0 // indirect
-	golang.org/x/sync v0.11.0 // indirect
-	golang.org/x/sys v0.30.0 // indirect
-	golang.org/x/term v0.29.0 // indirect
-	golang.org/x/text v0.22.0 // indirect
-	golang.org/x/tools v0.30.0 // indirect
+	golang.org/x/crypto v0.39.0 // indirect
+	golang.org/x/exp v0.0.0-20250606033433-dcc06ee1d476 // indirect
+	golang.org/x/mod v0.25.0 // indirect
+	golang.org/x/net v0.41.0 // indirect
+	golang.org/x/sync v0.15.0 // indirect
+	golang.org/x/sys v0.33.0 // indirect
+	golang.org/x/term v0.32.0 // indirect
+	golang.org/x/text v0.26.0 // indirect
+	golang.org/x/tools v0.34.0 // indirect
 	golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2 // indirect
-	golang.zx2c4.com/wireguard v0.0.0-20231211153847-12269c276173 // indirect
+	golang.zx2c4.com/wireguard v0.0.0-20250521234502-f333402bd9cb // indirect
 	golang.zx2c4.com/wireguard/windows v0.5.3 // indirect
-	gonum.org/v1/gonum v0.15.1 // indirect
+	gonum.org/v1/gonum v0.16.0 // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20241007155032-5fefd90f89a9 // indirect
 	gopkg.in/fsnotify.v1 v1.4.7 // indirect
 	gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 // indirect
 	howett.net/plist v1.0.0 // indirect
-	lukechampine.com/blake3 v1.3.0 // indirect
+	lukechampine.com/blake3 v1.4.1 // indirect
 )

go.sum

@@ -47,8 +47,6 @@ github.com/aymanbagabas/go-osc52/v2 v2.0.1 h1:HwpRHbFMcZLEVr42D4p7XBqjyuxQH5SMiE
 github.com/aymanbagabas/go-osc52/v2 v2.0.1/go.mod h1:uYgXzlJ7ZpABp8OJ+exZzJJhRNQ2ASbcXHWsFqH8hp8=
 github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=
 github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=
-github.com/benbjohnson/clock v1.1.0/go.mod h1:J11/hYXuz8f4ySSvYwY0FKfm+ezbsZBKZxNJlLklBHA=
-github.com/benbjohnson/clock v1.3.0/go.mod h1:J11/hYXuz8f4ySSvYwY0FKfm+ezbsZBKZxNJlLklBHA=
 github.com/benbjohnson/clock v1.3.5 h1:VvXlSJBzZpA/zum6Sj74hxwYI2DIxRWuNIoXAzHZz5o=
 github.com/benbjohnson/clock v1.3.5/go.mod h1:J11/hYXuz8f4ySSvYwY0FKfm+ezbsZBKZxNJlLklBHA=
 github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
@@ -67,10 +65,8 @@ github.com/charmbracelet/glamour v0.7.0 h1:2BtKGZ4iVJCDfMF229EzbeR1QRKLWztO9dMtj
 github.com/charmbracelet/glamour v0.7.0/go.mod h1:jUMh5MeihljJPQbJ/wf4ldw2+yBP59+ctV36jASy7ps=
 github.com/chasefleming/elem-go v0.26.0 h1:RB20oElG4J8W2aQx6jfUuESPQJ52KvC37eLEAPxwJDA=
 github.com/chasefleming/elem-go v0.26.0/go.mod h1:hz73qILBIKnTgOujnSMtEj20/epI+f6vg71RUilJAA4=
-github.com/cilium/ebpf v0.2.0/go.mod h1:To2CFviqOWL/M0gIMsvSMlqe7em/l1ALkX1PyjrX2Qs=
 github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
 github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
-github.com/containerd/cgroups v0.0.0-20201119153540-4cbc285b3327/go.mod h1:ZJeTFisyysqgcCdecO57Dj79RfL0LNeGiFUqLYQRYLE=
 github.com/containerd/cgroups v1.1.0 h1:v8rEWFl6EoqHB+swVNjVoCJE8o3jX7e8nqBGPLaDFBM=
 github.com/containerd/cgroups v1.1.0/go.mod h1:6ppBcbh/NOOUU+dMKrykgaBnK9lCIBxHqJDGwsa1mIw=
 github.com/containerd/containerd v1.7.19 h1:/xQ4XRJ0tamDkdzrrBAUy/LE5nCcxFKdBm4EcPrSMEE=
@@ -86,16 +82,11 @@ github.com/containerd/platforms v0.2.1/go.mod h1:XHCb+2/hzowdiut9rkudds9bE5yJ7np
 github.com/containerd/stargz-snapshotter/estargz v0.14.3 h1:OqlDCK3ZVUO6C3B/5FSkDwbkEETK84kQgEeFwDC+62k=
 github.com/containerd/stargz-snapshotter/estargz v0.14.3/go.mod h1:KY//uOCIkSuNAHhJogcZtrNHdKrA99/FCCRjE3HD36o=
 github.com/coreos/go-systemd v0.0.0-20181012123002-c6f51f82210d/go.mod h1:F5haX7vjVVG0kc13fIWeqUViNPyEJxv/OmvnBo0Yme4=
-github.com/coreos/go-systemd/v22 v22.1.0/go.mod h1:xO0FLkIi5MaZafQlIrOotqXZ90ih+1atmu1JpKERPPk=
-github.com/coreos/go-systemd/v22 v22.5.0 h1:RrqgGjYQKalulkV8NGVIfkXQf6YYmOyiJKk8iXXhfZs=
 github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
 github.com/cpuguy83/dockercfg v0.3.2 h1:DlJTyZGBDlXqUZ2Dk2Q3xHs/FtnooJJVaad2S9GKorA=
 github.com/cpuguy83/dockercfg v0.3.2/go.mod h1:sugsbF4//dDlL/i+S+rtpIWp+5h0BHJHfjj5/jFyUJc=
 github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
-github.com/cpuguy83/go-md2man/v2 v2.0.0/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
 github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
-github.com/cpuguy83/go-md2man/v2 v2.0.5 h1:ZtcqGrnekaHpVLArFSe4HK5DoKx1T0rq2DwVB0alcyc=
-github.com/cpuguy83/go-md2man/v2 v2.0.5/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
 github.com/creachadair/mds v0.21.3 h1:RRgEAPIb52cU0q7UxGyN+13QlCVTZIL4slRr0cYYQfA=
 github.com/creachadair/mds v0.21.3/go.mod h1:1ltMWZd9yXhaHEoZwBialMaviWVUpRPvMwVP7saFAzM=
 github.com/creachadair/otp v0.5.0 h1:q3Th7CXm2zlmCdBjw5tEPFOj4oWJMnVL5HXlq0sNKS0=
@@ -109,11 +100,8 @@ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davidlazar/go-crypto v0.0.0-20200604182044-b73af7476f6c h1:pFUpOrbxDR6AkioZ1ySsx5yxlDQZ8stG2b88gTPxgJU=
 github.com/davidlazar/go-crypto v0.0.0-20200604182044-b73af7476f6c/go.mod h1:6UhI8N9EjYm1c2odKpFpAYeR8dsBeM7PtzQhRgxRr9U=
-github.com/decred/dcrd/crypto/blake256 v1.0.1 h1:7PltbUIQB7u/FfZ39+DGa/ShuMyJ5ilcvdfma9wOH6Y=
-github.com/decred/dcrd/crypto/blake256 v1.0.1/go.mod h1:2OfgNZ5wDpcsFmHmCK5gZTPcCXqlm2ArzUIkw9czNJo=
 github.com/decred/dcrd/crypto/blake256 v1.1.0 h1:zPMNGQCm0g4QTY27fOCorQW7EryeQ/U0x++OzVrdms8=
-github.com/decred/dcrd/dcrec/secp256k1/v4 v4.3.0 h1:rpfIENRNNilwHwZeG5+P150SMrnNEcHYvcCuK6dPZSg=
-github.com/decred/dcrd/dcrec/secp256k1/v4 v4.3.0/go.mod h1:v57UDF4pDQJcEfFUCRop3lJL149eHGSe9Jvczhzjo/0=
+github.com/decred/dcrd/crypto/blake256 v1.1.0/go.mod h1:2OfgNZ5wDpcsFmHmCK5gZTPcCXqlm2ArzUIkw9czNJo=
 github.com/decred/dcrd/dcrec/secp256k1/v4 v4.4.0 h1:NMZiJj8QnKe1LgsbDayM4UoHwbvwDRwnI3hwNaAHRnc=
 github.com/decred/dcrd/dcrec/secp256k1/v4 v4.4.0/go.mod h1:ZXNYxsqcloTdSy/rNShjYzMhyjf0LaoftYK0p+A3h40=
 github.com/distribution/reference v0.6.0 h1:0IXCQ5g4/QMHHkarYzh5l+u8T3t73zM5QvfrDyIgxBk=
@@ -130,7 +118,6 @@ github.com/docker/docker-credential-helpers v0.7.0 h1:xtCHsjxogADNZcdv1pKUHXryef
 github.com/docker/docker-credential-helpers v0.7.0/go.mod h1:rETQfLdHNT3foU5kuNkFR1R1V12OJRRO5lzt2D1b5X0=
 github.com/docker/go-connections v0.5.0 h1:USnMq7hx7gwdVZq1L49hLXaFtUdTADjXGp+uj1Br63c=
 github.com/docker/go-connections v0.5.0/go.mod h1:ov60Kzw0kKElRwhNs9UlUHAE/F9Fe6GLaXnqyDdmEXc=
-github.com/docker/go-units v0.4.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
 github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4=
 github.com/docker/go-units v0.5.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
 github.com/dsnet/compress v0.0.2-0.20210315054119-f66993602bf5 h1:iFaUwBSo5Svw6L7HYpRu/0lE3e0BaElwnNO1qkNQxBY=
@@ -139,9 +126,6 @@ github.com/dsnet/golib v0.0.0-20171103203638-1ea166775780/go.mod h1:Lj+Z9rebOhdf
 github.com/dustin/go-humanize v1.0.0/go.mod h1:HtrtbFcZ19U5GC7JDqmcUSB87Iq5E25KnS6fMYU6eOk=
 github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
-github.com/elastic/gosigar v0.12.0/go.mod h1:iXRIGg2tLnu7LBdpqzyQfGDEidKCfWcCMS0WKyPWoMs=
-github.com/elastic/gosigar v0.14.3 h1:xwkKwPia+hSfg9GqrCUKYdId102m9qTJIIr7egmK/uo=
-github.com/elastic/gosigar v0.14.3/go.mod h1:iXRIGg2tLnu7LBdpqzyQfGDEidKCfWcCMS0WKyPWoMs=
 github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
 github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
 github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98=
@@ -194,10 +178,7 @@ github.com/go-skynet/go-llama.cpp v0.0.0-20240314183750-6a8041ef6b46/go.mod h1:i
 github.com/go-task/slim-sprig/v3 v3.0.0 h1:sUs3vkvUymDpBKi3qH1YSqBQk9+9D/8M2mN1vB6EwHI=
 github.com/go-task/slim-sprig/v3 v3.0.0/go.mod h1:W848ghGpv3Qj3dhTPRyJypKRiqCdHZiAzKg9hl15HA8=
 github.com/go-yaml/yaml v2.1.0+incompatible/go.mod h1:w2MrLa16VYP0jy6N7M5kHaCkaLENm+P+Tv+MfurjSw0=
-github.com/godbus/dbus/v5 v5.0.3/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
-github.com/godbus/dbus/v5 v5.1.0 h1:4KLkAxT3aOY8Li4FRJe/KvhoNFFxo0m6fNuFUO8QJUk=
-github.com/godbus/dbus/v5 v5.1.0/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/gofiber/contrib/fiberzerolog v1.0.2 h1:LMa/luarQVeINoRwZLHtLQYepLPDIwUNB5OmdZKk+s8=
 github.com/gofiber/contrib/fiberzerolog v1.0.2/go.mod h1:aTPsgArSgxRWcUeJ/K6PiICz3mbQENR1QOR426QwOoQ=
 github.com/gofiber/fiber/v2 v2.52.5 h1:tWoP1MJQjGEe4GB5TUGOi7P2E0ZMMRx5ZTG4rT+yGMo=
@@ -215,7 +196,6 @@ github.com/gofiber/websocket/v2 v2.2.1/go.mod h1:Ao/+nyNnX5u/hIFPuHl28a+NIkrqK7P
 github.com/gofrs/flock v0.12.1 h1:MTLVXXHf8ekldpJk3AKicLij9MdwOWkZ+a/jHHZby9E=
 github.com/gofrs/flock v0.12.1/go.mod h1:9zxTsyu5xtJ9DK+1tFZyibEV7y3uwDxPPfbxeeHCoD0=
 github.com/gogo/protobuf v1.1.1/go.mod h1:r8qH/GZQm5c6nD/R0oafs1akxWv10x8SbQlK7atdtwQ=
-github.com/gogo/protobuf v1.3.1/go.mod h1:SlYgWuQ5SjCEi6WLHjHCa1yvBfUnHcTbrrZtXPKa29o=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
 github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
@@ -246,11 +226,11 @@ github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMyw
 github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
 github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.3/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
 github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
+github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
 github.com/google/go-containerregistry v0.19.2 h1:TannFKE1QSajsP6hPWb5oJNgKe1IKjHukIKDUmvsV6w=
 github.com/google/go-containerregistry v0.19.2/go.mod h1:YCMFNQeeXeLF+dnhhWkqDItx/JSkH01j1Kis4PsjzFI=
 github.com/google/go-github v17.0.0+incompatible/go.mod h1:zLgOLi98H3fifZn+44m+umXrS52loVEgC2AApnigrVQ=
@@ -264,7 +244,6 @@ github.com/google/pprof v0.0.0-20250208200701-d0013a598941 h1:43XjGa6toxLpeksjcx
 github.com/google/pprof v0.0.0-20250208200701-d0013a598941/go.mod h1:vavhavw2zAxS5dIdcRluK6cSGGPlZynqzFM8NdvU144=
 github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
 github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
-github.com/google/uuid v1.3.1/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/googleapis/gax-go v2.0.0+incompatible/go.mod h1:SFVmujtThgffbyetf+mdk2eWhX2bMyUtNHzFKcPA9HY=
@@ -283,11 +262,6 @@ github.com/grpc-ecosystem/grpc-gateway v1.5.0 h1:WcmKMm43DR7RdtlkEXQJyo5ws8iTp98
 github.com/grpc-ecosystem/grpc-gateway v1.5.0/go.mod h1:RSKVYQBd5MCa4OVpNdGskqpgL2+G+NZTnrVHpWWfpdw=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.22.0 h1:asbCHRVmodnJTuQ3qamDwqVOIjwqUPTYmYuemVOx+Ys=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.22.0/go.mod h1:ggCgvZ2r7uOoQjOyu2Y1NhHmEPPzzuhWgcza5M1Ji1I=
-github.com/hashicorp/errwrap v1.0.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
-github.com/hashicorp/errwrap v1.1.0 h1:OxrOeh75EUXMY8TBjag2fzXGZ40LB6IKw45YeGUDY2I=
-github.com/hashicorp/errwrap v1.1.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
-github.com/hashicorp/go-multierror v1.1.1 h1:H5DkEtf6CXdFp0N0Em5UCwQpXMWke8IA0+lD48awMYo=
-github.com/hashicorp/go-multierror v1.1.1/go.mod h1:iw975J/qwKPdAO1clOe2L8331t/9/fmwbPZ6JB6eMoM=
 github.com/hashicorp/golang-lru v1.0.2 h1:dV3g9Z/unq5DpblPpw+Oqcv4dU/1omnb4Ok8iPY6p1c=
 github.com/hashicorp/golang-lru v1.0.2/go.mod h1:iADmTwqILo4mZ8BN3D2Q6+9jd8WM5uGBxy+E8yxSoD4=
 github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
@@ -302,16 +276,14 @@ github.com/huandu/xstrings v1.5.0 h1:2ag3IFq9ZDANvthTwTiqSSZLjDc+BedvHPAp5tJy2TI
 github.com/huandu/xstrings v1.5.0/go.mod h1:y5/lhBue+AyNmUVz9RLU9xbLR0o4KIIExikq4ovT0aE=
 github.com/huin/goupnp v1.3.0 h1:UvLUlWDNpoUdYzb2TCn+MuTWtcjXKSza2n6CBdQ0xXc=
 github.com/huin/goupnp v1.3.0/go.mod h1:gnGPsThkYa7bFi/KWmEysQRf48l2dvR5bxr2OFckNX8=
-github.com/ipfs/boxo v0.27.4 h1:6nC8lY5GnR6whAbW88hFz6L13wZUj2vr5BRe3iTvYBI=
-github.com/ipfs/boxo v0.27.4/go.mod h1:qEIRrGNr0bitDedTCzyzBHxzNWqYmyuHgK8LG9Q83EM=
+github.com/ipfs/boxo v0.30.0 h1:7afsoxPGGqfoH7Dum/wOTGUB9M5fb8HyKPMlLfBvIEQ=
+github.com/ipfs/boxo v0.30.0/go.mod h1:BPqgGGyHB9rZZcPSzah2Dc9C+5Or3U1aQe7EH1H7370=
 github.com/ipfs/go-block-format v0.2.0 h1:ZqrkxBA2ICbDRbK8KJs/u0O3dlp6gmAuuXUJNiW1Ycs=
 github.com/ipfs/go-block-format v0.2.0/go.mod h1:+jpL11nFx5A/SPpsoBn6Bzkra/zaArfSmsknbPMYgzM=
 github.com/ipfs/go-cid v0.5.0 h1:goEKKhaGm0ul11IHA7I6p1GmKz8kEYniqFopaB5Otwg=
 github.com/ipfs/go-cid v0.5.0/go.mod h1:0L7vmeNXpQpUS9vt+yEARkJ8rOg43DF3iPgn4GIN0mk=
-github.com/ipfs/go-datastore v0.6.0 h1:JKyz+Gvz1QEZw0LsX1IBn+JFCJQH4SJVFtM4uWU0Myk=
-github.com/ipfs/go-datastore v0.6.0/go.mod h1:rt5M3nNbSO/8q1t4LNkLyUwRs8HupMeN/8O4Vn9YAT8=
-github.com/ipfs/go-datastore v0.7.0 h1:a6JMuRFKYhw6XXmIVoTthF8ZFm4QQXvLDXFhXRVv8Go=
-github.com/ipfs/go-datastore v0.7.0/go.mod h1:ucOWMfbOPI6ZEyaIB1q/+78RPLBPERfuUVYX1EPnNpQ=
+github.com/ipfs/go-datastore v0.8.2 h1:Jy3wjqQR6sg/LhyY0NIePZC3Vux19nLtg7dx0TVqr6U=
+github.com/ipfs/go-datastore v0.8.2/go.mod h1:W+pI1NsUsz3tcsAACMtfC+IZdnQTnC/7VfPoJBQuts0=
 github.com/ipfs/go-detect-race v0.0.1 h1:qX/xay2W3E4Q1U7d9lNs1sU9nvguX0a7319XbyQ6cOk=
 github.com/ipfs/go-detect-race v0.0.1/go.mod h1:8BNT7shDZPo99Q74BpGMK+4D8Mn4j46UU0LZ723meps=
 github.com/ipfs/go-ipfs-util v0.0.3 h1:2RFdGez6bu2ZlZdI+rWfIdbQb1KudQp3VGwPtdNCmE0=
@@ -319,10 +291,10 @@ github.com/ipfs/go-ipfs-util v0.0.3/go.mod h1:LHzG1a0Ig4G+iZ26UUOMjHd+lfM84LZCrn
 github.com/ipfs/go-log v1.0.5 h1:2dOuUCB1Z7uoczMWgAyDck5JLb72zHzrMnGnCNNbvY8=
 github.com/ipfs/go-log v1.0.5/go.mod h1:j0b8ZoR+7+R99LD9jZ6+AJsrzkPbSXbZfGakb5JPtIo=
 github.com/ipfs/go-log/v2 v2.1.3/go.mod h1:/8d0SH3Su5Ooc31QlL1WysJhvyOTDCjcCZ9Axpmri6g=
-github.com/ipfs/go-log/v2 v2.5.1 h1:1XdUzF7048prq4aBjDQQ4SL5RxftpRGdXhNRwKSAlcY=
-github.com/ipfs/go-log/v2 v2.5.1/go.mod h1:prSpmC1Gpllc9UYWxDiZDreBYw7zp4Iqp1kOLU9U5UI=
-github.com/ipfs/go-test v0.0.4 h1:DKT66T6GBB6PsDFLoO56QZPrOmzJkqU1FZH5C9ySkew=
-github.com/ipfs/go-test v0.0.4/go.mod h1:qhIM1EluEfElKKM6fnWxGn822/z9knUGM1+I/OAQNKI=
+github.com/ipfs/go-log/v2 v2.6.0 h1:2Nu1KKQQ2ayonKp4MPo6pXCjqw1ULc9iohRqWV5EYqg=
+github.com/ipfs/go-log/v2 v2.6.0/go.mod h1:p+Efr3qaY5YXpx9TX7MoLCSEZX5boSWj9wh86P5HJa8=
+github.com/ipfs/go-test v0.2.1 h1:/D/a8xZ2JzkYqcVcV/7HYlCnc7bv/pKHQiX5TdClkPE=
+github.com/ipfs/go-test v0.2.1/go.mod h1:dzu+KB9cmWjuJnXFDYJwC25T3j1GcN57byN+ixmK39M=
 github.com/ipld/go-ipld-prime v0.21.0 h1:n4JmcpOlPDIxBcY037SVfpd1G+Sj1nKZah0m6QH9C2E=
 github.com/ipld/go-ipld-prime v0.21.0/go.mod h1:3RLqy//ERg/y5oShXXdx5YIp50cFGOanyMctpPjsvxQ=
 github.com/jackpal/go-nat-pmp v1.0.2 h1:KzKSgb7qkJvOUTqYl9/Hg/me3pWgBmERKrTGD7BdWus=
@@ -331,11 +303,8 @@ github.com/jaypipes/ghw v0.12.0 h1:xU2/MDJfWmBhJnujHY9qwXQLs3DBsf0/Xa9vECY0Tho=
 github.com/jaypipes/ghw v0.12.0/go.mod h1:jeJGbkRB2lL3/gxYzNYzEDETV1ZJ56OKr+CSeSEym+g=
 github.com/jaypipes/pcidb v1.0.0 h1:vtZIfkiCUE42oYbJS0TAq9XSfSmcsgo9IdxSm9qzYU8=
 github.com/jaypipes/pcidb v1.0.0/go.mod h1:TnYUvqhPBzCKnH34KrIX22kAeEbDCSRJ9cqLRCuNDfk=
-github.com/jbenet/go-cienv v0.1.0/go.mod h1:TqNnHUmJgXau0nCzC7kXWeotg3J9W34CUv5Djy1+FlA=
 github.com/jbenet/go-temp-err-catcher v0.1.0 h1:zpb3ZH6wIE8Shj2sKS+khgRvf7T7RABoLk/+KKHggpk=
 github.com/jbenet/go-temp-err-catcher v0.1.0/go.mod h1:0kJRvmDZXNMIiJirNPEYfhpPwbGVtZVWC34vc5WLsDk=
-github.com/jbenet/goprocess v0.1.4 h1:DRGOFReOMqqDNXwW70QkacFW0YN9QnwLV0Vqk+3oU0o=
-github.com/jbenet/goprocess v0.1.4/go.mod h1:5yspPrukOVuOLORacaBi858NqyClJPQxYZlqdZVfqY4=
 github.com/jellevandenhooff/dkim v0.0.0-20150330215556-f50fe3d243e1/go.mod h1:E0B/fFc00Y+Rasa88328GlI/XbtyysCtTHZS8h7IrBU=
 github.com/jessevdk/go-flags v1.4.0/go.mod h1:4FA24M0QyGHXBuZZK/XkWh8h0e1EYbRYJSGM75WSRxI=
 github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
@@ -349,20 +318,19 @@ github.com/jstemmer/go-junit-report v0.0.0-20190106144839-af01ea7f8024/go.mod h1
 github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
 github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
 github.com/k0kubun/go-ansi v0.0.0-20180517002512-3bf9e2903213/go.mod h1:vNUNkEQ1e29fT/6vq2aBdFsgNPmy8qMdSay1npru+Sw=
-github.com/kisielk/errcheck v1.2.0/go.mod h1:/BMXB+zMLi60iA8Vv6Ksmxu/1UDYcXs4uQLJ+jE2L00=
 github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/klauspost/compress v1.4.1/go.mod h1:RyIbtBH6LamlWaDj8nUwkbUhJ87Yi3uG0guNDohfE1A=
 github.com/klauspost/compress v1.11.4/go.mod h1:aoV0uJVorq1K+umq18yTdKaF57EivdYsUV+/s2qKfXs=
-github.com/klauspost/compress v1.17.11 h1:In6xLpyWOi1+C7tXUUWv2ot1QvBjxevKAaI6IXrJmUc=
-github.com/klauspost/compress v1.17.11/go.mod h1:pMDklpSncoRMuLFrf1W9Ss9KT+0rH90U12bZKk7uwG0=
+github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
+github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ=
 github.com/klauspost/cpuid v1.2.0/go.mod h1:Pj4uuM528wm8OyEC2QMXAi2YiTZ96dNQPGgoMS4s3ek=
-github.com/klauspost/cpuid/v2 v2.2.9 h1:66ze0taIn2H33fBvCkXuv9BmCwDfafmiIVpKV9kKGuY=
-github.com/klauspost/cpuid/v2 v2.2.9/go.mod h1:rqkxqrZ1EhYM9G+hXH7YdowN5R5RGN6NK4QwQ3WMXF8=
+github.com/klauspost/cpuid/v2 v2.2.10 h1:tBs3QSyvjDyFTq3uoc/9xFpCuOsJQFNPiAhYdw2skhE=
+github.com/klauspost/cpuid/v2 v2.2.10/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0=
 github.com/klauspost/pgzip v1.2.5 h1:qnWYvvKqedOF2ulHpMG72XQol4ILEJ8k2wwRl/Km8oE=
 github.com/klauspost/pgzip v1.2.5/go.mod h1:Ch1tH69qFZu15pkjo5kYi6mth2Zzwzt50oCQKQE9RUs=
-github.com/koron/go-ssdp v0.0.5 h1:E1iSMxIs4WqxTbIBLtmNBeOOC+1sCIXQeqTWVnpmwhk=
-github.com/koron/go-ssdp v0.0.5/go.mod h1:Qm59B7hpKpDqfyRNWRNr00jGwLdXjDyZh6y7rH6VS0w=
+github.com/koron/go-ssdp v0.0.6 h1:Jb0h04599eq/CY7rB5YEqPS83HmRfHP2azkxMN2rFtU=
+github.com/koron/go-ssdp v0.0.6/go.mod h1:0R9LfRJGek1zWTjN3JUNlm5INCDYGpRDfAptnct63fI=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
@@ -374,48 +342,36 @@ github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
 github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
-github.com/labstack/echo/v4 v4.13.3 h1:pwhpCPrTl5qry5HRdM5FwdXnhXSLSY+WE+YQSeCaafY=
-github.com/labstack/echo/v4 v4.13.3/go.mod h1:o90YNEeQWjDozo584l7AwhJMHN0bOC4tAfg+Xox9q5g=
-github.com/labstack/gommon v0.4.2 h1:F8qTUNXgG1+6WQmqoUWnz8WiEU60mXVVw0P4ht1WRA0=
-github.com/labstack/gommon v0.4.2/go.mod h1:QlUFxVM+SNXhDL/Z7YhocGIBYOiwB0mXm1+1bAPHPyU=
 github.com/libp2p/go-buffer-pool v0.1.0 h1:oK4mSFcQz7cTQIfqbe4MIj9gLW+mnanjyFtc6cdF0Y8=
 github.com/libp2p/go-buffer-pool v0.1.0/go.mod h1:N+vh8gMqimBzdKkSMVuydVDq+UV5QTWy5HSiZacSbPg=
 github.com/libp2p/go-cidranger v1.1.0 h1:ewPN8EZ0dd1LSnrtuwd4709PXVcITVeuwbag38yPW7c=
 github.com/libp2p/go-cidranger v1.1.0/go.mod h1:KWZTfSr+r9qEo9OkI9/SIEeAtw+NNoU0dXIXt15Okic=
 github.com/libp2p/go-flow-metrics v0.2.0 h1:EIZzjmeOE6c8Dav0sNv35vhZxATIXWZg6j/C08XmmDw=
 github.com/libp2p/go-flow-metrics v0.2.0/go.mod h1:st3qqfu8+pMfh+9Mzqb2GTiwrAGjIPszEjZmtksN8Jc=
-github.com/libp2p/go-libp2p v0.39.1 h1:1Ur6rPCf3GR+g8jkrnaQaM0ha2IGespsnNlCqJLLALE=
-github.com/libp2p/go-libp2p v0.39.1/go.mod h1:3zicI8Lp7Isun+Afo/JOACUbbJqqR2owK6RQWFsVAbI=
-github.com/libp2p/go-libp2p v0.40.0 h1:1LOMO3gigxeXFs50HGEc1U79OINewUQB7o4gTKGPC3U=
-github.com/libp2p/go-libp2p v0.40.0/go.mod h1:hOzj2EAIYsXpVpBnyA1pRHzpUJGF9nbWiDLjgasnbF0=
+github.com/libp2p/go-libp2p v0.43.0 h1:b2bg2cRNmY4HpLK8VHYQXLX2d3iND95OjodLFymvqXU=
+github.com/libp2p/go-libp2p v0.43.0/go.mod h1:IiSqAXDyP2sWH+J2gs43pNmB/y4FOi2XQPbsb+8qvzc=
 github.com/libp2p/go-libp2p-asn-util v0.4.1 h1:xqL7++IKD9TBFMgnLPZR6/6iYhawHKHl950SO9L6n94=
 github.com/libp2p/go-libp2p-asn-util v0.4.1/go.mod h1:d/NI6XZ9qxw67b4e+NgpQexCIiFYJjErASrYW4PFDN8=
-github.com/libp2p/go-libp2p-kad-dht v0.29.0 h1:045eW21lGlMSD9aKSZZGH4fnBMIInPwQLxIQ35P962I=
-github.com/libp2p/go-libp2p-kad-dht v0.29.0/go.mod h1:mIci3rHSwDsxQWcCjfmxD8vMTgh5xLuvwb1D5WP8ZNk=
-github.com/libp2p/go-libp2p-kad-dht v0.29.1 h1:RyD1RnnkXOh1gwBCrMQ6ZVfTJECY5yDOY6qxt9VNqE4=
-github.com/libp2p/go-libp2p-kad-dht v0.29.1/go.mod h1:tZEFTKWCsY0xngypKyAIwNDNZOBiikSUIgd/BjTF5Ms=
-github.com/libp2p/go-libp2p-kbucket v0.6.5 h1:Fsl1YvZcMwqrR4DYrTO02yo9PGYs2HBQIT3lGXFMTxg=
-github.com/libp2p/go-libp2p-kbucket v0.6.5/go.mod h1:U6WOd0BvnSp03IQSrjgM54tg7zh1UUNsXLJqAQzClTA=
-github.com/libp2p/go-libp2p-pubsub v0.13.0 h1:RmFQ2XAy3zQtbt2iNPy7Tt0/3fwTnHpCQSSnmGnt1Ps=
-github.com/libp2p/go-libp2p-pubsub v0.13.0/go.mod h1:m0gpUOyrXKXdE7c8FNQ9/HLfWbxaEw7xku45w+PaqZo=
+github.com/libp2p/go-libp2p-kad-dht v0.33.1 h1:hKFhHMf7WH69LDjaxsJUWOU6qZm71uO47M/a5ijkiP0=
+github.com/libp2p/go-libp2p-kad-dht v0.33.1/go.mod h1:CdmNk4VeGJa9EXM9SLNyNVySEvduKvb+5rSC/H4pLAo=
+github.com/libp2p/go-libp2p-kbucket v0.7.0 h1:vYDvRjkyJPeWunQXqcW2Z6E93Ywx7fX0jgzb/dGOKCs=
+github.com/libp2p/go-libp2p-kbucket v0.7.0/go.mod h1:blOINGIj1yiPYlVEX0Rj9QwEkmVnz3EP8LK1dRKBC6g=
+github.com/libp2p/go-libp2p-pubsub v0.14.2 h1:nT5lFHPQOFJcp9CW8hpKtvbpQNdl2udJuzLQWbgRum8=
+github.com/libp2p/go-libp2p-pubsub v0.14.2/go.mod h1:MKPU5vMI8RRFyTP0HfdsF9cLmL1nHAeJm44AxJGJx44=
 github.com/libp2p/go-libp2p-record v0.3.1 h1:cly48Xi5GjNw5Wq+7gmjfBiG9HCzQVkiZOUZ8kUl+Fg=
 github.com/libp2p/go-libp2p-record v0.3.1/go.mod h1:T8itUkLcWQLCYMqtX7Th6r7SexyUJpIyPgks757td/E=
-github.com/libp2p/go-libp2p-routing-helpers v0.7.4 h1:6LqS1Bzn5CfDJ4tzvP9uwh42IB7TJLNFJA6dEeGBv84=
-github.com/libp2p/go-libp2p-routing-helpers v0.7.4/go.mod h1:we5WDj9tbolBXOuF1hGOkR+r7Uh1408tQbAKaT5n1LE=
+github.com/libp2p/go-libp2p-routing-helpers v0.7.5 h1:HdwZj9NKovMx0vqq6YNPTh6aaNzey5zHD7HeLJtq6fI=
+github.com/libp2p/go-libp2p-routing-helpers v0.7.5/go.mod h1:3YaxrwP0OBPDD7my3D0KxfR89FlcX/IEbxDEDfAmj98=
 github.com/libp2p/go-libp2p-testing v0.12.0 h1:EPvBb4kKMWO29qP4mZGyhVzUyR25dvfUIK5WDu6iPUA=
 github.com/libp2p/go-libp2p-testing v0.12.0/go.mod h1:KcGDRXyN7sQCllucn1cOOS+Dmm7ujhfEyXQL5lvkcPg=
 github.com/libp2p/go-msgio v0.3.0 h1:mf3Z8B1xcFN314sWX+2vOTShIE0Mmn2TXn3YCUQGNj0=
 github.com/libp2p/go-msgio v0.3.0/go.mod h1:nyRM819GmVaF9LX3l03RMh10QdOroF++NBbxAb0mmDM=
-github.com/libp2p/go-nat v0.2.0 h1:Tyz+bUFAYqGyJ/ppPPymMGbIgNRH+WqC5QrT5fKrrGk=
-github.com/libp2p/go-nat v0.2.0/go.mod h1:3MJr+GRpRkyT65EpVPBstXLvOlAPzUVlG6Pwg9ohLJk=
 github.com/libp2p/go-netroute v0.2.2 h1:Dejd8cQ47Qx2kRABg6lPwknU7+nBnFRpko45/fFPuZ8=
 github.com/libp2p/go-netroute v0.2.2/go.mod h1:Rntq6jUAH0l9Gg17w5bFGhcC9a+vk4KNXs6s7IljKYE=
 github.com/libp2p/go-reuseport v0.4.0 h1:nR5KU7hD0WxXCJbmw7r2rhRYruNRl2koHw8fQscQm2s=
 github.com/libp2p/go-reuseport v0.4.0/go.mod h1:ZtI03j/wO5hZVDFo2jKywN6bYKWLOy8Se6DrI2E1cLU=
-github.com/libp2p/go-yamux/v4 v4.0.2 h1:nrLh89LN/LEiqcFiqdKDRHjGstN300C1269K/EX0CPU=
-github.com/libp2p/go-yamux/v4 v4.0.2/go.mod h1:C808cCRgOs1iBwY4S71T5oxgMxgLmqUw56qh4AeBW2o=
-github.com/libp2p/go-yamux/v5 v5.0.0 h1:2djUh96d3Jiac/JpGkKs4TO49YhsfLopAoryfPmf+Po=
-github.com/libp2p/go-yamux/v5 v5.0.0/go.mod h1:en+3cdX51U0ZslwRdRLrvQsdayFt3TSUKvBGErzpWbU=
+github.com/libp2p/go-yamux/v5 v5.0.1 h1:f0WoX/bEF2E8SbE4c/k1Mo+/9z0O4oC/hWEA+nfYRSg=
+github.com/libp2p/go-yamux/v5 v5.0.1/go.mod h1:en+3cdX51U0ZslwRdRLrvQsdayFt3TSUKvBGErzpWbU=
 github.com/libp2p/zeroconf/v2 v2.2.0 h1:Cup06Jv6u81HLhIj1KasuNM/RHHrJ8T7wOTS4+Tv53Q=
 github.com/libp2p/zeroconf/v2 v2.2.0/go.mod h1:fuJqLnUwZTshS3U/bMRJ3+ow/v9oid1n0DmyYyNO1Xs=
 github.com/lucasb-eyer/go-colorful v1.2.0 h1:1nnpGOrhyZZuNyfu1QjKiUICQ74+3FNCN69Aj6K7nkY=
@@ -433,7 +389,6 @@ github.com/marten-seemann/tcp v0.0.0-20210406111302-dfbc87cc63fd/go.mod h1:QuCEs
 github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
 github.com/mattn/go-colorable v0.1.14 h1:9A9LHSqF/7dyVVX6g0U9cwm9pG3kP9gSzcuIPHPsaIE=
 github.com/mattn/go-colorable v0.1.14/go.mod h1:6LmQG8QLFO4G5z1gPvYEzlUgJ2wF+stgPZH1UqBm1s8=
-github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
 github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
 github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
@@ -449,8 +404,8 @@ github.com/microcosm-cc/bluemonday v1.0.1/go.mod h1:hsXNsILzKxV+sX77C5b8FSuKF00v
 github.com/microcosm-cc/bluemonday v1.0.26 h1:xbqSvqzQMeEHCqMi64VAs4d8uy6Mequs3rQ0k/Khz58=
 github.com/microcosm-cc/bluemonday v1.0.26/go.mod h1:JyzOCs9gkyQyjs+6h10UEVSe02CGwkhd72Xdqh78TWs=
 github.com/miekg/dns v1.1.43/go.mod h1:+evo5L0630/F6ca/Z9+GAqzhjGyn8/c+TBaOyfEl0V4=
-github.com/miekg/dns v1.1.63 h1:8M5aAw6OMZfFXTT7K5V0Eu5YiiL8l7nUAkyN6C9YwaY=
-github.com/miekg/dns v1.1.63/go.mod h1:6NGHfjhpmr5lt3XPLuyfDJi5AXbNIPM9PY6H6sF1Nfs=
+github.com/miekg/dns v1.1.66 h1:FeZXOS3VCVsKnEAd+wBkjMC3D2K+ww66Cq3VnCINuJE=
+github.com/miekg/dns v1.1.66/go.mod h1:jGFzBsSNbJw6z1HYut1RKBKHA9PBdxeHrZG8J+gC2WE=
 github.com/mikioh/tcp v0.0.0-20190314235350-803a9b46060c h1:bzE/A84HN25pxAuk9Eej1Kz9OUelF97nAc82bDquQI8=
 github.com/mikioh/tcp v0.0.0-20190314235350-803a9b46060c/go.mod h1:0SQS9kMwD2VsyFEB++InYyBJroV/FRmBgcydeSUcJms=
 github.com/mikioh/tcpinfo v0.0.0-20190314235526-30a79bb1804b h1:z78hV3sbSMAUoyUMM0I83AUIT6Hu17AWfgjzIbtrYFc=
@@ -492,16 +447,14 @@ github.com/morikuni/aec v1.0.0/go.mod h1:BbKIizmSmc5MMPqRYbxO4ZU0S0+P200+tUnFx7P
 github.com/mr-tron/base58 v1.1.2/go.mod h1:BinMc/sQntlIE1frQmRFPUoPA1Zkr8VRgBdjWI2mNwc=
 github.com/mr-tron/base58 v1.2.0 h1:T/HDJBh4ZCPbU39/+c3rRvE0uKBQlU27+QI8LJ4t64o=
 github.com/mr-tron/base58 v1.2.0/go.mod h1:BinMc/sQntlIE1frQmRFPUoPA1Zkr8VRgBdjWI2mNwc=
-github.com/mudler/edgevpn v0.30.1 h1:4yyhNFJX62NpRp50sxiyZE5E/sdAqEZX+aE5Mv7QS60=
-github.com/mudler/edgevpn v0.30.1/go.mod h1:IAJkkJ0oH3rwsSGOGTFT4UBYFqYuD/QyaKzTLB3P/eU=
-github.com/mudler/edgevpn v0.30.2 h1:3cD0UM8BHM8tQ1v3WIZOyzmktgZbKPAQQDH3KoH15rs=
-github.com/mudler/edgevpn v0.30.2/go.mod h1:bGUdGQzwLOuMs3SII1N6SazoI1qQ1ekxdxNatOCS5ZM=
+github.com/mudler/edgevpn v0.31.0 h1:CXwxQ2ZygzE7iKGl1J+vq9pL5PvsW2uc3qI/zgpNpp4=
+github.com/mudler/edgevpn v0.31.0/go.mod h1:DKgh9Wu/NM3UbZoPyheMXFvpu1dSLkXrqAOy3oKJN3I=
 github.com/mudler/go-piper v0.0.0-20241023091659-2494246fd9fc h1:RxwneJl1VgvikiX28EkpdAyL4yQVnJMrbquKospjHyA=
 github.com/mudler/go-piper v0.0.0-20241023091659-2494246fd9fc/go.mod h1:O7SwdSWMilAWhBZMK9N9Y/oBDyMMzshE3ju8Xkexwig=
 github.com/mudler/go-processmanager v0.0.0-20240820160718-8b802d3ecf82 h1:FVT07EI8njvsD4tC2Hw8Xhactp5AWhsQWD4oTeQuSAU=
 github.com/mudler/go-processmanager v0.0.0-20240820160718-8b802d3ecf82/go.mod h1:Urp7LG5jylKoDq0663qeBh0pINGcRl35nXdKx82PSoU=
-github.com/mudler/water v0.0.0-20221010214108-8c7313014ce0 h1:Qh6ghkMgTu6siFbTf7L3IszJmshMhXxNL4V+t7IIA6w=
-github.com/mudler/water v0.0.0-20221010214108-8c7313014ce0/go.mod h1:nViSE8jcOcraZwhi34joEqn7HYFISgs0M8/YujzY5Xk=
+github.com/mudler/water v0.0.0-20250808092830-dd90dcf09025 h1:WFLP5FHInarYGXi6B/Ze204x7Xy6q/I4nCZnWEyPHK0=
+github.com/mudler/water v0.0.0-20250808092830-dd90dcf09025/go.mod h1:QuIFdRstyGJt+MTTkWY+mtD7U6xwjOR6SwKUjmLZtR4=
 github.com/muesli/reflow v0.3.0 h1:IFsN6K9NfGtjeggFP+68I4chLZV2yIKsXJFNZ+eWh6s=
 github.com/muesli/reflow v0.3.0/go.mod h1:pbwTDkVPibjO2kyvBQRBxTWEEGDGq0FlB1BIKtnHY/8=
 github.com/muesli/termenv v0.15.2 h1:GohcuySI0QmI3wN8Ok9PtKGkgkFIk7y6Vpb5PvrY+Wo=
@@ -511,21 +464,21 @@ github.com/multiformats/go-base32 v0.1.0/go.mod h1:Kj3tFY6zNr+ABYMqeUNeGvkIC/UYg
 github.com/multiformats/go-base36 v0.2.0 h1:lFsAbNOGeKtuKozrtBsAkSVhv1p9D0/qedU9rQyccr0=
 github.com/multiformats/go-base36 v0.2.0/go.mod h1:qvnKE++v+2MWCfePClUEjE78Z7P2a1UV0xHgWc0hkp4=
 github.com/multiformats/go-multiaddr v0.1.1/go.mod h1:aMKBKNEYmzmDmxfX88/vz+J5IU55txyt0p4aiWVohjo=
-github.com/multiformats/go-multiaddr v0.14.0 h1:bfrHrJhrRuh/NXH5mCnemjpbGjzRw/b+tJFOD41g2tU=
-github.com/multiformats/go-multiaddr v0.14.0/go.mod h1:6EkVAxtznq2yC3QT5CM1UTAwG0GTP3EWAIcjHuzQ+r4=
+github.com/multiformats/go-multiaddr v0.16.0 h1:oGWEVKioVQcdIOBlYM8BH1rZDWOGJSqr9/BKl6zQ4qc=
+github.com/multiformats/go-multiaddr v0.16.0/go.mod h1:JSVUmXDjsVFiW7RjIFMP7+Ev+h1DTbiJgVeTV/tcmP0=
 github.com/multiformats/go-multiaddr-dns v0.4.1 h1:whi/uCLbDS3mSEUMb1MsoT4uzUeZB0N32yzufqS0i5M=
 github.com/multiformats/go-multiaddr-dns v0.4.1/go.mod h1:7hfthtB4E4pQwirrz+J0CcDUfbWzTqEzVyYKKIKpgkc=
 github.com/multiformats/go-multiaddr-fmt v0.1.0 h1:WLEFClPycPkp4fnIzoFoV9FVd49/eQsuaL3/CWe167E=
 github.com/multiformats/go-multiaddr-fmt v0.1.0/go.mod h1:hGtDIW4PU4BqJ50gW2quDuPVjyWNZxToGUh/HwTZYJo=
 github.com/multiformats/go-multibase v0.2.0 h1:isdYCVLvksgWlMW9OZRYJEa9pZETFivncJHmHnnd87g=
 github.com/multiformats/go-multibase v0.2.0/go.mod h1:bFBZX4lKCA/2lyOFSAoKH5SS6oPyjtnzK/XTFDPkNuk=
-github.com/multiformats/go-multicodec v0.9.0 h1:pb/dlPnzee/Sxv/j4PmkDRxCOi3hXTz3IbPKOXWJkmg=
-github.com/multiformats/go-multicodec v0.9.0/go.mod h1:L3QTQvMIaVBkXOXXtVmYE+LI16i14xuaojr/H7Ai54k=
+github.com/multiformats/go-multicodec v0.9.1 h1:x/Fuxr7ZuR4jJV4Os5g444F7xC4XmyUaT/FWtE+9Zjo=
+github.com/multiformats/go-multicodec v0.9.1/go.mod h1:LLWNMtyV5ithSBUo3vFIMaeDy+h3EbkMTek1m+Fybbo=
 github.com/multiformats/go-multihash v0.0.8/go.mod h1:YSLudS+Pi8NHE7o6tb3D8vrpKa63epEDmG8nTduyAew=
 github.com/multiformats/go-multihash v0.2.3 h1:7Lyc8XfX/IY2jWb/gI7JP+o7JEq9hOa7BFvVU9RSh+U=
 github.com/multiformats/go-multihash v0.2.3/go.mod h1:dXgKXCXjBzdscBLk9JkjINiEsCKRVch90MdaGiKsvSM=
-github.com/multiformats/go-multistream v0.6.0 h1:ZaHKbsL404720283o4c/IHQXiS6gb8qAN5EIJ4PN5EA=
-github.com/multiformats/go-multistream v0.6.0/go.mod h1:MOyoG5otO24cHIg8kf9QW2/NozURlkP/rvi2FQJyCPg=
+github.com/multiformats/go-multistream v0.6.1 h1:4aoX5v6T+yWmc2raBHsTvzmFhOI8WVOer28DeBBEYdQ=
+github.com/multiformats/go-multistream v0.6.1/go.mod h1:ksQf6kqHAb6zIsyw7Zm+gAuVo57Qbq84E27YlYqavqw=
 github.com/multiformats/go-varint v0.0.7 h1:sWSGR+f/eu5ABZA2ZpYKBILXTTs9JWpdEM/nEGOHFS8=
 github.com/multiformats/go-varint v0.0.7/go.mod h1:r8PUYw/fD/SjBCiKOoDlGF6QawOELpZAu9eioSos/OU=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
@@ -536,28 +489,27 @@ github.com/nikolalohinski/gonja/v2 v2.3.2 h1:UgLFfqi7L9XfX0PEcE4eUpvGojVQL5KhBfJ
 github.com/nikolalohinski/gonja/v2 v2.3.2/go.mod h1:1Wcc/5huTu6y36e0sOFR1XQoFlylw3c3H3L5WOz0RDg=
 github.com/nwaples/rardecode v1.1.0 h1:vSxaY8vQhOcVr4mm5e8XllHWTiM4JF507A0Katqw7MQ=
 github.com/nwaples/rardecode v1.1.0/go.mod h1:5DzqNKiOdpKKBH87u8VlvAnPZMXcGRhxWkRpHbbfGS0=
-github.com/nxadm/tail v1.4.11 h1:8feyoE3OzPrcshW5/MJ4sGESc5cqmGkGCWlco4l0bqY=
-github.com/nxadm/tail v1.4.11/go.mod h1:OTaG3NK980DZzxbRq6lEuzgU+mug70nY11sMd4JXXHc=
+github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
+github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
 github.com/olekukonko/tablewriter v0.0.5 h1:P2Ga83D34wi1o9J6Wh1mRuqd4mF/x/lgBS7N7AbDhec=
 github.com/olekukonko/tablewriter v0.0.5/go.mod h1:hPp6KlRPjbx+hW8ykQs1w3UBbZlj6HuIJcUGPhkA7kY=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
 github.com/onsi/ginkgo v1.16.5/go.mod h1:+E8gABHa3K6zRBolWtd+ROzc/U5bkGt0FwiG042wbpU=
-github.com/onsi/ginkgo/v2 v2.22.2 h1:/3X8Panh8/WwhU/3Ssa6rCKqPLuAkVY2I0RoyDLySlU=
-github.com/onsi/ginkgo/v2 v2.22.2/go.mod h1:oeMosUL+8LtarXBHu/c0bx2D/K9zyQ6uX3cTyztHwsk=
+github.com/onsi/ginkgo/v2 v2.23.3 h1:edHxnszytJ4lD9D5Jjc4tiDkPBZ3siDeJJkUZJJVkp0=
+github.com/onsi/ginkgo/v2 v2.23.3/go.mod h1:zXTP6xIp3U8aVuXN8ENK9IXRaTjFnpVB9mGmaSRvxnM=
 github.com/onsi/gomega v1.36.2 h1:koNYke6TVk6ZmnyHrCXba/T/MoLBXFjeC1PtvYgw0A8=
 github.com/onsi/gomega v1.36.2/go.mod h1:DdwyADRjrc825LhMEkD76cHR5+pUnjhUN8GlHlRPHzY=
 github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
 github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM=
 github.com/opencontainers/image-spec v1.1.0 h1:8SG7/vwALn54lVB/0yZ/MMwhFrPYtpEHQb2IpWsCzug=
 github.com/opencontainers/image-spec v1.1.0/go.mod h1:W4s4sFTMaBeK1BQLXbG4AdM2szdn85PY75RI83NrTrM=
-github.com/opencontainers/runtime-spec v1.0.2/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
-github.com/opencontainers/runtime-spec v1.2.0 h1:z97+pHb3uELt/yiAWD691HNHQIF07bE7dzrbT927iTk=
-github.com/opencontainers/runtime-spec v1.2.0/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
 github.com/opentracing/opentracing-go v1.2.0 h1:uEJPy/1a5RIPAJ0Ov+OIO8OxWu77jEv+1B0VhjKrZUs=
 github.com/opentracing/opentracing-go v1.2.0/go.mod h1:GxEUsuufX4nBwe+T+Wl9TAgYrxe9dPLANfrWvHYVTgc=
 github.com/openzipkin/zipkin-go v0.1.1/go.mod h1:NtoC/o8u3JlF1lSlyPNswIbeQH9bJTmOf0Erfk+hxe8=
-github.com/otiai10/mint v1.6.1 h1:kgbTJmOpp/0ce7hk3H8jiSuR0MXmpwWRfqUdKww17qg=
-github.com/otiai10/mint v1.6.1/go.mod h1:MJm72SBthJjz8qhefc4z1PYEieWmy8Bku7CjcAqyUSM=
+github.com/otiai10/copy v1.14.1 h1:5/7E6qsUMBaH5AnQ0sSLzzTg1oTECmcCmT6lvF45Na8=
+github.com/otiai10/copy v1.14.1/go.mod h1:oQwrEDDOci3IM8dJF0d8+jnbfPDllW6vUjNc3DoZm9I=
+github.com/otiai10/mint v1.6.3 h1:87qsV/aw1F5as1eH1zS/yqHY85ANKVMgkDrf9rcxbQs=
+github.com/otiai10/mint v1.6.3/go.mod h1:MJm72SBthJjz8qhefc4z1PYEieWmy8Bku7CjcAqyUSM=
 github.com/otiai10/openaigo v1.7.0 h1:AOQcOjRRM57ABvz+aI2oJA/Qsz1AydKbdZAlGiKyCqg=
 github.com/otiai10/openaigo v1.7.0/go.mod h1:kIaXc3V+Xy5JLplcBxehVyGYDtufHp3PFPy04jOwOAI=
 github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58 h1:onHthvaw9LFnH4t2DcNVpwGmV9E1BkGknEliJkfwQj0=
@@ -575,33 +527,29 @@ github.com/pion/datachannel v1.5.10/go.mod h1:p/jJfC9arb29W7WrxyKbepTU20CFgyx5oL
 github.com/pion/dtls/v2 v2.2.7/go.mod h1:8WiMkebSHFD0T+dIU+UeBaoV7kDhOW5oDCzZ7WZ/F9s=
 github.com/pion/dtls/v2 v2.2.12 h1:KP7H5/c1EiVAAKUmXyCzPiQe5+bCJrpOeKg/L05dunk=
 github.com/pion/dtls/v2 v2.2.12/go.mod h1:d9SYc9fch0CqK90mRk1dC7AkzzpwJj6u2GU3u+9pqFE=
-github.com/pion/dtls/v3 v3.0.4 h1:44CZekewMzfrn9pmGrj5BNnTMDCFwr+6sLH+cCuLM7U=
-github.com/pion/dtls/v3 v3.0.4/go.mod h1:R373CsjxWqNPf6MEkfdy3aSe9niZvL/JaKlGeFphtMg=
-github.com/pion/ice/v2 v2.3.37 h1:ObIdaNDu1rCo7hObhs34YSBcO7fjslJMZV0ux+uZWh0=
-github.com/pion/ice/v2 v2.3.37/go.mod h1:mBF7lnigdqgtB+YHkaY/Y6s6tsyRyo4u4rPGRuOjUBQ=
-github.com/pion/ice/v4 v4.0.6 h1:jmM9HwI9lfetQV/39uD0nY4y++XZNPhvzIPCb8EwxUM=
-github.com/pion/ice/v4 v4.0.6/go.mod h1:y3M18aPhIxLlcO/4dn9X8LzLLSma84cx6emMSu14FGw=
-github.com/pion/interceptor v0.1.37 h1:aRA8Zpab/wE7/c0O3fh1PqY0AJI3fCSEM5lRWJVorwI=
-github.com/pion/interceptor v0.1.37/go.mod h1:JzxbJ4umVTlZAf+/utHzNesY8tmRkM2lVmkS82TTj8Y=
+github.com/pion/dtls/v3 v3.0.6 h1:7Hkd8WhAJNbRgq9RgdNh1aaWlZlGpYTzdqjy9x9sK2E=
+github.com/pion/dtls/v3 v3.0.6/go.mod h1:iJxNQ3Uhn1NZWOMWlLxEEHAN5yX7GyPvvKw04v9bzYU=
+github.com/pion/ice/v4 v4.0.10 h1:P59w1iauC/wPk9PdY8Vjl4fOFL5B+USq1+xbDcN6gT4=
+github.com/pion/ice/v4 v4.0.10/go.mod h1:y3M18aPhIxLlcO/4dn9X8LzLLSma84cx6emMSu14FGw=
+github.com/pion/interceptor v0.1.40 h1:e0BjnPcGpr2CFQgKhrQisBU7V3GXK6wrfYrGYaU6Jq4=
+github.com/pion/interceptor v0.1.40/go.mod h1:Z6kqH7M/FYirg3frjGJ21VLSRJGBXB/KqaTIrdqnOic=
 github.com/pion/logging v0.2.2/go.mod h1:k0/tDVsRCX2Mb2ZEmTqNa7CWsQPc+YYCB7Q+5pahoms=
 github.com/pion/logging v0.2.3 h1:gHuf0zpoh1GW67Nr6Gj4cv5Z9ZscU7g/EaoC/Ke/igI=
 github.com/pion/logging v0.2.3/go.mod h1:z8YfknkquMe1csOrxK5kc+5/ZPAzMxbKLX5aXpbpC90=
-github.com/pion/mdns v0.0.12 h1:CiMYlY+O0azojWDmxdNr7ADGrnZ+V6Ilfner+6mSVK8=
-github.com/pion/mdns v0.0.12/go.mod h1:VExJjv8to/6Wqm1FXK+Ii/Z9tsVk/F5sD/N70cnYFbk=
 github.com/pion/mdns/v2 v2.0.7 h1:c9kM8ewCgjslaAmicYMFQIde2H9/lrZpjBkN8VwoVtM=
 github.com/pion/mdns/v2 v2.0.7/go.mod h1:vAdSYNAT0Jy3Ru0zl2YiW3Rm/fJCwIeM0nToenfOJKA=
 github.com/pion/randutil v0.1.0 h1:CFG1UdESneORglEsnimhUjf33Rwjubwj6xfiOXBa3mA=
 github.com/pion/randutil v0.1.0/go.mod h1:XcJrSMMbbMRhASFVOlj/5hQial/Y8oH/HVo7TBZq+j8=
 github.com/pion/rtcp v1.2.15 h1:LZQi2JbdipLOj4eBjK4wlVoQWfrZbh3Q6eHtWtJBZBo=
 github.com/pion/rtcp v1.2.15/go.mod h1:jlGuAjHMEXwMUHK78RgX0UmEJFV4zUKOFHR7OP+D3D0=
-github.com/pion/rtp v1.8.11 h1:17xjnY5WO5hgO6SD3/NTIUPvSFw/PbLsIJyz1r1yNIk=
-github.com/pion/rtp v1.8.11/go.mod h1:8uMBJj32Pa1wwx8Fuv/AsFhn8jsgw+3rUC2PfoBZ8p4=
-github.com/pion/sctp v1.8.35 h1:qwtKvNK1Wc5tHMIYgTDJhfZk7vATGVHhXbUDfHbYwzA=
-github.com/pion/sctp v1.8.35/go.mod h1:EcXP8zCYVTRy3W9xtOF7wJm1L1aXfKRQzaM33SjQlzg=
-github.com/pion/sdp/v3 v3.0.10 h1:6MChLE/1xYB+CjumMw+gZ9ufp2DPApuVSnDT8t5MIgA=
-github.com/pion/sdp/v3 v3.0.10/go.mod h1:88GMahN5xnScv1hIMTqLdu/cOcUkj6a9ytbncwMCq2E=
-github.com/pion/srtp/v3 v3.0.4 h1:2Z6vDVxzrX3UHEgrUyIGM4rRouoC7v+NiF1IHtp9B5M=
-github.com/pion/srtp/v3 v3.0.4/go.mod h1:1Jx3FwDoxpRaTh1oRV8A/6G1BnFL+QI82eK4ms8EEJQ=
+github.com/pion/rtp v1.8.19 h1:jhdO/3XhL/aKm/wARFVmvTfq0lC/CvN1xwYKmduly3c=
+github.com/pion/rtp v1.8.19/go.mod h1:bAu2UFKScgzyFqvUKmbvzSdPr+NGbZtv6UB2hesqXBk=
+github.com/pion/sctp v1.8.39 h1:PJma40vRHa3UTO3C4MyeJDQ+KIobVYRZQZ0Nt7SjQnE=
+github.com/pion/sctp v1.8.39/go.mod h1:cNiLdchXra8fHQwmIoqw0MbLLMs+f7uQ+dGMG2gWebE=
+github.com/pion/sdp/v3 v3.0.13 h1:uN3SS2b+QDZnWXgdr69SM8KB4EbcnPnPf2Laxhty/l4=
+github.com/pion/sdp/v3 v3.0.13/go.mod h1:88GMahN5xnScv1hIMTqLdu/cOcUkj6a9ytbncwMCq2E=
+github.com/pion/srtp/v3 v3.0.6 h1:E2gyj1f5X10sB/qILUGIkL4C2CqK269Xq167PbGCc/4=
+github.com/pion/srtp/v3 v3.0.6/go.mod h1:BxvziG3v/armJHAaJ87euvkhHqWe9I7iiOy50K2QkhY=
 github.com/pion/stun v0.6.1 h1:8lp6YejULeHBF8NmV8e2787BogQhduZugh5PdhDyyN4=
 github.com/pion/stun v0.6.1/go.mod h1:/hO7APkX4hZKu/D0f2lHzNyvdkTGtIy3NDmLR7kSz/8=
 github.com/pion/stun/v3 v3.0.0 h1:4h1gwhWLWuZWOJIJR9s2ferRO+W3zA/b6ijOI6mKzUw=
@@ -610,16 +558,12 @@ github.com/pion/transport/v2 v2.2.1/go.mod h1:cXXWavvCnFF6McHTft3DWS9iic2Mftcz1A
 github.com/pion/transport/v2 v2.2.4/go.mod h1:q2U/tf9FEfnSBGSW6w5Qp5PFWRLRj3NjLhCCgpRK4p0=
 github.com/pion/transport/v2 v2.2.10 h1:ucLBLE8nuxiHfvkFKnkDQRYWYfp8ejf4YBOPfaQpw6Q=
 github.com/pion/transport/v2 v2.2.10/go.mod h1:sq1kSLWs+cHW9E+2fJP95QudkzbK7wscs8yYgQToO5E=
-github.com/pion/transport/v3 v3.0.1/go.mod h1:UY7kiITrlMv7/IKgd5eTUcaahZx5oUN3l9SzK5f5xE0=
 github.com/pion/transport/v3 v3.0.7 h1:iRbMH05BzSNwhILHoBoAPxoB9xQgOaJk+591KC9P1o0=
 github.com/pion/transport/v3 v3.0.7/go.mod h1:YleKiTZ4vqNxVwh77Z0zytYi7rXHl7j6uPLGhhz9rwo=
-github.com/pion/turn/v2 v2.1.3/go.mod h1:huEpByKKHix2/b9kmTAM3YoX6MKP+/D//0ClgUYR2fY=
-github.com/pion/turn/v2 v2.1.6 h1:Xr2niVsiPTB0FPtt+yAWKFUkU1eotQbGgpTIld4x1Gc=
-github.com/pion/turn/v2 v2.1.6/go.mod h1:huEpByKKHix2/b9kmTAM3YoX6MKP+/D//0ClgUYR2fY=
-github.com/pion/turn/v4 v4.0.0 h1:qxplo3Rxa9Yg1xXDxxH8xaqcyGUtbHYw4QSCvmFWvhM=
-github.com/pion/turn/v4 v4.0.0/go.mod h1:MuPDkm15nYSklKpN8vWJ9W2M0PlyQZqYt1McGuxG7mA=
-github.com/pion/webrtc/v4 v4.0.9 h1:PyOYMRKJgfy0dzPcYtFD/4oW9zaw3Ze3oZzzbj2LV9E=
-github.com/pion/webrtc/v4 v4.0.9/go.mod h1:ViHLVaNpiuvaH8pdiuQxuA9awuE6KVzAXx3vVWilOck=
+github.com/pion/turn/v4 v4.0.2 h1:ZqgQ3+MjP32ug30xAbD6Mn+/K4Sxi3SdNOTFf+7mpps=
+github.com/pion/turn/v4 v4.0.2/go.mod h1:pMMKP/ieNAG/fN5cZiN4SDuyKsXtNTr0ccN7IToA1zs=
+github.com/pion/webrtc/v4 v4.1.2 h1:mpuUo/EJ1zMNKGE79fAdYNFZBX790KE7kQQpLMjjR54=
+github.com/pion/webrtc/v4 v4.1.2/go.mod h1:xsCXiNAmMEjIdFxAYU0MbB3RwRieJsegSB2JZsGN+8U=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
@@ -632,28 +576,24 @@ github.com/polydawn/refmt v0.89.0/go.mod h1:/zvteZs/GwLtCgZ4BL6CBsk9IKIlexP43ObX
 github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 h1:o4JXh1EVt9k/+g42oCprj/FisM4qX9L3sZB3upGN2ZU=
 github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55/go.mod h1:OmDBASR4679mdNQnz2pUhc2G8CO2JrUAVFDRBDP/hJE=
 github.com/prometheus/client_golang v0.8.0/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
-github.com/prometheus/client_golang v1.20.5 h1:cxppBPuYhUnsO6yo/aoRol4L7q7UFfdm+bR9r+8l63Y=
-github.com/prometheus/client_golang v1.20.5/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE=
-github.com/prometheus/client_golang v1.21.0 h1:DIsaGmiaBkSangBgMtWdNfxbMNdku5IK6iNhrEqWvdA=
-github.com/prometheus/client_golang v1.21.0/go.mod h1:U9NM32ykUErtVBxdvD3zfi+EuFkkaBvMb09mIfe0Zgg=
+github.com/prometheus/client_golang v1.22.0 h1:rb93p9lokFEsctTys46VnV1kLCDpVZ0a/Y92Vm0Zc6Q=
+github.com/prometheus/client_golang v1.22.0/go.mod h1:R7ljNsLXhuQXYZYtw6GAE9AZg8Y7vEW5scdCXrWRXC0=
 github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
 github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
-github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E=
-github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
+github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk=
+github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE=
 github.com/prometheus/common v0.0.0-20180801064454-c7de2306084e/go.mod h1:daVV7qP5qjZbuso7PdcryaAu0sAZbrN9i7WWcTMWvro=
-github.com/prometheus/common v0.62.0 h1:xasJaQlnWAeyHdUBeGjXmutelfJHWMRr+Fg4QszZ2Io=
-github.com/prometheus/common v0.62.0/go.mod h1:vyBcEuLSvWos9B1+CyL7JZ2up+uFzXhkqml0W5zIY1I=
+github.com/prometheus/common v0.64.0 h1:pdZeA+g617P7oGv1CzdTzyeShxAGrTBsolKNOLQPGO4=
+github.com/prometheus/common v0.64.0/go.mod h1:0gZns+BLRQ3V6NdaerOhMbwwRbNh9hkGINtQAsP5GS8=
 github.com/prometheus/procfs v0.0.0-20180725123919-05ee40e3a273/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
-github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
-github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
+github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg=
+github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is=
 github.com/quic-go/qpack v0.5.1 h1:giqksBPnT/HDtZ6VhtFKgoLOWmlyo9Ei6u9PqzIMbhI=
 github.com/quic-go/qpack v0.5.1/go.mod h1:+PC4XFrEskIVkcLzpEkbLqq1uCoxPhQuvK5rH1ZgaEg=
-github.com/quic-go/quic-go v0.49.0 h1:w5iJHXwHxs1QxyBv1EHKuC50GX5to8mJAxvtnttJp94=
-github.com/quic-go/quic-go v0.49.0/go.mod h1:s2wDnmCdooUQBmQfpUSTCYBl1/D4FcqbULMMkASvR6s=
-github.com/quic-go/webtransport-go v0.8.1-0.20241018022711-4ac2c9250e66 h1:4WFk6u3sOT6pLa1kQ50ZVdm8BQFgJNA117cepZxtLIg=
-github.com/quic-go/webtransport-go v0.8.1-0.20241018022711-4ac2c9250e66/go.mod h1:Vp72IJajgeOL6ddqrAhmp7IM9zbTcgkQxD/YdxrVwMw=
-github.com/raulk/go-watchdog v1.3.0 h1:oUmdlHxdkXRJlwfG0O9omj8ukerm8MEQavSiDTEtBsk=
-github.com/raulk/go-watchdog v1.3.0/go.mod h1:fIvOnLbF0b0ZwkB9YU4mOW9Did//4vPZtDqv66NfsMU=
+github.com/quic-go/quic-go v0.54.0 h1:6s1YB9QotYI6Ospeiguknbp2Znb/jZYjZLRXn9kMQBg=
+github.com/quic-go/quic-go v0.54.0/go.mod h1:e68ZEaCdyviluZmy44P6Iey98v/Wfz6HCjQEm+l8zTY=
+github.com/quic-go/webtransport-go v0.9.0 h1:jgys+7/wm6JarGDrW+lD/r9BGqBAmqY/ssklE09bA70=
+github.com/quic-go/webtransport-go v0.9.0/go.mod h1:4FUYIiUc75XSsF6HShcLeXXYZJ9AGwo/xh3L8M/P1ao=
 github.com/rivo/uniseg v0.1.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
@@ -670,7 +610,6 @@ github.com/russross/blackfriday v1.5.2/go.mod h1:JO/DiYxRf+HjHt06OyowR9PTA263kcR
 github.com/russross/blackfriday v1.6.0 h1:KqfZb0pUVN2lYqZUYRddxF4OR8ZMURnJIG5Y3VRLtww=
 github.com/russross/blackfriday v1.6.0/go.mod h1:ti0ldHuxg49ri4ksnFxlkCfN+hvslNlmVHqNRXXJNAY=
 github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
-github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/sashabaranov/go-openai v1.26.2 h1:cVlQa3gn3eYqNXRW03pPlpy6zLG52EU4g0FrWXc0EFI=
 github.com/sashabaranov/go-openai v1.26.2/go.mod h1:lj5b/K+zjTSFxVLijLSTDZuP7adOgerWeFyZLUhAKRg=
@@ -712,7 +651,6 @@ github.com/shurcooL/sanitized_anchor_name v0.0.0-20170918181015-86672fcb3f95/go.
 github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
 github.com/shurcooL/users v0.0.0-20180125191416-49c67e49c537/go.mod h1:QJTqeLYEDaXHZDBsXlPCDqdhQuJkuw4NOtaxYe3xii4=
 github.com/shurcooL/webdavfs v0.0.0-20170829043945-18c3829fa133/go.mod h1:hKmq5kWdCj2z2KEozexVbfEZIWiTjhE0+UjmZgPqehw=
-github.com/sirupsen/logrus v1.7.0/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
 github.com/sirupsen/logrus v1.9.0/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
 github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ=
 github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
@@ -767,18 +705,12 @@ github.com/tmc/langchaingo v0.1.12/go.mod h1:cd62xD6h+ouk8k/QQFhOsjRYBSA1JJ5UVKX
 github.com/ulikunitz/xz v0.5.8/go.mod h1:nbz6k7qbPmH4IRqmfOplQw/tblSgqTqBwxkY0oWt/14=
 github.com/ulikunitz/xz v0.5.9 h1:RsKRIA2MO8x56wkkcd3LbtcE/uMszhb6DpRf+3uwa3I=
 github.com/ulikunitz/xz v0.5.9/go.mod h1:nbz6k7qbPmH4IRqmfOplQw/tblSgqTqBwxkY0oWt/14=
-github.com/urfave/cli v1.22.2/go.mod h1:Gos4lmkARVdJ6EkW0WaNv/tZAAMe9V7XWyB60NtXRu0=
 github.com/urfave/cli v1.22.10/go.mod h1:Gos4lmkARVdJ6EkW0WaNv/tZAAMe9V7XWyB60NtXRu0=
-github.com/urfave/cli v1.22.12 h1:igJgVw1JdKH+trcLWLeLwZjU9fEfPesQ+9/e4MQ44S8=
 github.com/urfave/cli v1.22.12/go.mod h1:sSBEIC79qR6OvcmsD4U3KABeOTxDqQtdDnaFuUN30b8=
-github.com/urfave/cli/v2 v2.27.5 h1:WoHEJLdsXr6dDWoJgMq/CboDmyY/8HMMH1fTECbih+w=
-github.com/urfave/cli/v2 v2.27.5/go.mod h1:3Sevf16NykTbInEnD0yKkjDAeZDS0A6bzhBH5hrMvTQ=
 github.com/valyala/bytebufferpool v1.0.0 h1:GqA5TC/0021Y/b9FG4Oi9Mr3q7XYx6KllzawFIhcdPw=
 github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
 github.com/valyala/fasthttp v1.55.0 h1:Zkefzgt6a7+bVKHnu/YaYSOPfNYNisSVBo/unVCf8k8=
 github.com/valyala/fasthttp v1.55.0/go.mod h1:NkY9JtkrpPKmgwV3HTaS2HWaJss9RSIsRVfcxxoHiOM=
-github.com/valyala/fasttemplate v1.2.2 h1:lxLXG0uE3Qnshl9QyaK6XJxMXlQZELvChBOCmQD0Loo=
-github.com/valyala/fasttemplate v1.2.2/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
 github.com/valyala/tcplisten v1.0.0 h1:rBHj/Xf+E1tRGZyWIWwJDiRY0zc1Js+CV5DqwacVSA8=
 github.com/valyala/tcplisten v1.0.0/go.mod h1:T0xQ8SeCZGxckz9qRXTfG43PvQ/mcWh7FwZEA7Ioqkc=
 github.com/vbatts/tar-split v0.11.3 h1:hLFqsOLQ1SsppQNTMpkpPXClLDfC2A3Zgy9OUU+RVck=
@@ -799,11 +731,8 @@ github.com/wlynxg/anet v0.0.5 h1:J3VJGi1gvo0JwZ/P1/Yc/8p63SoW98B5dHkYDmpgvvU=
 github.com/wlynxg/anet v0.0.5/go.mod h1:eay5PRQr7fIVAMbTbchTnO9gG65Hg/uYGdc7mguHxoA=
 github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8 h1:nIPpBwaJSVYIxUFsDv3M8ofmx9yWTog9BfvIu0q41lo=
 github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8/go.mod h1:HUYIGzjTL3rfEspMxjDjgmT5uz5wzYJKVo23qUhYTos=
-github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1 h1:gEOO8jv9F4OT7lGCjxCBTO/36wtF6j2nSip77qHd4x4=
-github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1/go.mod h1:Ohn+xnUBiLI6FVj/9LpzZWtj1/D6lUovWYBkxHVV3aM=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
-github.com/yuin/goldmark v1.3.5/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
 github.com/yuin/goldmark v1.3.7/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 github.com/yuin/goldmark v1.5.4 h1:2uY/xC0roWy8IBEGLgB1ywIoEJFGmRrX21YQcvGZzjU=
@@ -819,42 +748,40 @@ go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJyS
 go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.56.0 h1:UP6IpuHFkUgOQL9FFQFrZ+5LiwhhYRbi7VZSIx6Nj5s=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.56.0/go.mod h1:qxuZLtbq5QDtdeSHsS7bcf6EH6uO6jUAgk764zd3rhM=
-go.opentelemetry.io/otel v1.34.0 h1:zRLXxLCgL1WyKsPVrgbSdMN4c0FMkDAskSTQP+0hdUY=
-go.opentelemetry.io/otel v1.34.0/go.mod h1:OWFPOQ+h4G8xpyjgqo4SxJYdDQ/qmRH+wivy7zzx9oI=
+go.opentelemetry.io/otel v1.35.0 h1:xKWKPxrxB6OtMCbmMY021CqC45J+3Onta9MqjhnusiQ=
+go.opentelemetry.io/otel v1.35.0/go.mod h1:UEqy8Zp11hpkUrL73gSlELM0DupHoiq72dR+Zqel/+Y=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.31.0 h1:K0XaT3DwHAcV4nKLzcQvwAgSyisUghWoY20I7huthMk=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.31.0/go.mod h1:B5Ki776z/MBnVha1Nzwp5arlzBbE3+1jk+pGmaP5HME=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.31.0 h1:lUsI2TYsQw2r1IASwoROaCnjdj2cvC2+Jbxvk6nHnWU=
 go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.31.0/go.mod h1:2HpZxxQurfGxJlJDblybejHB6RX6pmExPNe517hREw4=
 go.opentelemetry.io/otel/exporters/prometheus v0.50.0 h1:2Ewsda6hejmbhGFyUvWZjUThC98Cf8Zy6g0zkIimOng=
 go.opentelemetry.io/otel/exporters/prometheus v0.50.0/go.mod h1:pMm5PkUo5YwbLiuEf7t2xg4wbP0/eSJrMxIMxKosynY=
-go.opentelemetry.io/otel/metric v1.34.0 h1:+eTR3U0MyfWjRDhmFMxe2SsW64QrZ84AOhvqS7Y+PoQ=
-go.opentelemetry.io/otel/metric v1.34.0/go.mod h1:CEDrp0fy2D0MvkXE+dPV7cMi8tWZwX3dmaIhwPOaqHE=
+go.opentelemetry.io/otel/metric v1.35.0 h1:0znxYu2SNyuMSQT4Y9WDWej0VpcsxkuklLa4/siN90M=
+go.opentelemetry.io/otel/metric v1.35.0/go.mod h1:nKVFgxBZ2fReX6IlyW28MgZojkoAkJGaE8CpgeAU3oE=
 go.opentelemetry.io/otel/sdk v1.31.0 h1:xLY3abVHYZ5HSfOg3l2E5LUj2Cwva5Y7yGxnSW9H5Gk=
 go.opentelemetry.io/otel/sdk v1.31.0/go.mod h1:TfRbMdhvxIIr/B2N2LQW2S5v9m3gOQ/08KsbbO5BPT0=
 go.opentelemetry.io/otel/sdk/metric v1.28.0 h1:OkuaKgKrgAbYrrY0t92c+cC+2F6hsFNnCQArXCKlg08=
 go.opentelemetry.io/otel/sdk/metric v1.28.0/go.mod h1:cWPjykihLAPvXKi4iZc1dpER3Jdq2Z0YLse3moQUCpg=
-go.opentelemetry.io/otel/trace v1.34.0 h1:+ouXS2V8Rd4hp4580a8q23bg0azF2nI8cqLYnC8mh/k=
-go.opentelemetry.io/otel/trace v1.34.0/go.mod h1:Svm7lSjQD7kG7KJ/MUHPVXSDGz2OX4h0M2jHBhmSfRE=
+go.opentelemetry.io/otel/trace v1.35.0 h1:dPpEfJu1sDIqruz7BHFG3c7528f6ddfSWfFDVt/xgMs=
+go.opentelemetry.io/otel/trace v1.35.0/go.mod h1:WUk7DtFp1Aw2MkvqGdwiXYDZZNvA/1J8o6xRXLrIkyc=
 go.opentelemetry.io/proto/otlp v1.3.1 h1:TrMUixzpM0yuc/znrFTP9MMRh8trP93mkCiDVeXrui0=
 go.opentelemetry.io/proto/otlp v1.3.1/go.mod h1:0X1WI4de4ZsLrrJNLAQbFeLCm3T7yBkR0XqQ7niQU+8=
 go.uber.org/atomic v1.6.0/go.mod h1:sABNBOSYdrvTF6hTgEIbc7YasKWGhgEQZyfxyTvoXHQ=
 go.uber.org/atomic v1.7.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
-go.uber.org/dig v1.18.0 h1:imUL1UiY0Mg4bqbFfsRQO5G4CGRBec/ZujWTvSVp3pw=
-go.uber.org/dig v1.18.0/go.mod h1:Us0rSJiThwCv2GteUN0Q7OKvU7n5J4dxZ9JKUXozFdE=
-go.uber.org/fx v1.23.0 h1:lIr/gYWQGfTwGcSXWXu4vP5Ws6iqnNEIY+F/aFzCKTg=
-go.uber.org/fx v1.23.0/go.mod h1:o/D9n+2mLP6v1EG+qsdT1O8wKopYAsqZasju97SDFCU=
-go.uber.org/goleak v1.1.11-0.20210813005559-691160354723/go.mod h1:cwTWslyiVhfpKIDGSZEM2HlOvcqm+tG4zioyIeLoqMQ=
+go.uber.org/dig v1.19.0 h1:BACLhebsYdpQ7IROQ1AGPjrXcP5dF80U3gKoFzbaq/4=
+go.uber.org/dig v1.19.0/go.mod h1:Us0rSJiThwCv2GteUN0Q7OKvU7n5J4dxZ9JKUXozFdE=
+go.uber.org/fx v1.24.0 h1:wE8mruvpg2kiiL1Vqd0CC+tr0/24XIB10Iwp2lLWzkg=
+go.uber.org/fx v1.24.0/go.mod h1:AmDeGyS+ZARGKM4tlH4FY2Jr63VjbEDJHtqXTGP5hbo=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
-go.uber.org/mock v0.5.0 h1:KAMbZvZPyBPWgD14IrIQ38QCyjwpvVVV6K/bHl1IwQU=
-go.uber.org/mock v0.5.0/go.mod h1:ge71pBPLYDk7QIi1LupWxdAykm7KIEFchiOqd6z7qMM=
+go.uber.org/mock v0.5.2 h1:LbtPTcP8A5k9WPXj54PPPbjcI4Y6lhyOZXn+VS7wNko=
+go.uber.org/mock v0.5.2/go.mod h1:wLlUxC2vVTPTaE3UD51E0BGOAElKrILxhVSDYQLld5o=
 go.uber.org/multierr v1.5.0/go.mod h1:FeouvMocqHpRaaGuG9EjoKcStLC43Zu/fmqdUMPcKYU=
 go.uber.org/multierr v1.6.0/go.mod h1:cdWPpRnG4AhwMwsgIHip0KRBQjJy5kYEpYjJxpXp9iU=
 go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
 go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
 go.uber.org/tools v0.0.0-20190618225709-2cfd321de3ee/go.mod h1:vJERXedbb3MVM5f9Ejo0C68/HhF8uaILCdgjnY+goOA=
 go.uber.org/zap v1.16.0/go.mod h1:MA8QOfq0BHJwdXa996Y4dYkAqRKB8/1K1QMMZVaNZjQ=
-go.uber.org/zap v1.19.1/go.mod h1:j3DNczoxDZroyBnOT1L/Q79cfUMGZxlv/9dzN7SM1rI=
 go.uber.org/zap v1.27.0 h1:aJMhYGrd5QSmlpLMr2MftRKl7t8J8PTZPA732ud/XR8=
 go.uber.org/zap v1.27.0/go.mod h1:GB2qFLM7cTU87MWRP2mPIjqfIDnGu+VIO4V/SdhGo2E=
 go4.org v0.0.0-20180809161055-417644f6feb5/go.mod h1:MkTOUMDaeVYJUOUsaDXIhWPZYa1yOyC1qaOBpL57BhE=
@@ -872,13 +799,11 @@ golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5y
 golang.org/x/crypto v0.8.0/go.mod h1:mRqEX+O9/h5TFCrQhkgjo2yKi0yYA+9ecGkdQoHrywE=
 golang.org/x/crypto v0.12.0/go.mod h1:NF0Gs7EO5K4qLn+Ylc+fih8BSTeIjAP05siRnAh98yw=
 golang.org/x/crypto v0.18.0/go.mod h1:R0j02AL6hcrfOiy9T4ZYp/rcWeMxM3L6QYxlOuEG1mg=
-golang.org/x/crypto v0.33.0 h1:IOBPskki6Lysi0lo9qQvbxiQ+FvsCC/YWOecCHAixus=
-golang.org/x/crypto v0.33.0/go.mod h1:bVdXmD7IV/4GdElGPozy6U7lWdRXA4qyRVGJV57uQ5M=
+golang.org/x/crypto v0.39.0 h1:SHs+kF4LP+f+p14esP5jAoDpHU8Gu/v9lFRK6IT5imM=
+golang.org/x/crypto v0.39.0/go.mod h1:L+Xg3Wf6HoL4Bn4238Z6ft6KfEpN0tJGo53AAPC632U=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
-golang.org/x/exp v0.0.0-20250215185904-eff6e970281f h1:oFMYAjX0867ZD2jcNiLBrI9BdpmEkvPyi5YrBGXbamg=
-golang.org/x/exp v0.0.0-20250215185904-eff6e970281f/go.mod h1:BHOTPb3L19zxehTsLoJXVaTktb06DFgmdW6Wb9s8jqk=
-golang.org/x/exp v0.0.0-20250218142911-aa4b98e5adaa h1:t2QcU6V556bFjYgu4L6C+6VrCPyJZ+eyRsABUPs1mz4=
-golang.org/x/exp v0.0.0-20250218142911-aa4b98e5adaa/go.mod h1:BHOTPb3L19zxehTsLoJXVaTktb06DFgmdW6Wb9s8jqk=
+golang.org/x/exp v0.0.0-20250606033433-dcc06ee1d476 h1:bsqhLWFR6G6xiQcb+JoGqdKdRU6WzPWmK8E0jxTjzo4=
+golang.org/x/exp v0.0.0-20250606033433-dcc06ee1d476/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=
 golang.org/x/lint v0.0.0-20180702182130-06c8688daad7/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
 golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
 golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
@@ -889,12 +814,11 @@ golang.org/x/mod v0.0.0-20190513183733-4bf6d317e70e/go.mod h1:mXi4GBBbnImb6dmsKG
 golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
 golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
-golang.org/x/mod v0.4.2/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
 golang.org/x/mod v0.7.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
 golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
-golang.org/x/mod v0.23.0 h1:Zb7khfcRGKk+kqfxFaP5tZqCnDZMjC5VtUBs87Hr6QM=
-golang.org/x/mod v0.23.0/go.mod h1:6SkKJ3Xj0I0BrPOZoBy3bdMptDDU9oJrpohJ3eWZ1fY=
+golang.org/x/mod v0.25.0 h1:n7a+ZbQKQA/Ysbyb0/6IbB1H/X41mKgbhfv7AfG/44w=
+golang.org/x/mod v0.25.0/go.mod h1:IXM97Txy2VM4PJ3gI61r1YEk/gAj6zAHN3AdZt6S9Ww=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -911,7 +835,6 @@ golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwY
 golang.org/x/net v0.0.0-20201110031124-69a78807bb2b/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
 golang.org/x/net v0.0.0-20210119194325-5f4716e94777/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/net v0.0.0-20210405180319-a5a99cb37ef4/go.mod h1:p54w0d4576C0XHj96bSt6lcn1PtDYWL6XObtHCRCNQM=
 golang.org/x/net v0.0.0-20210423184538-5f58ad60dda6/go.mod h1:OJAsFXCWl8Ukc7SiCT/9KSuxbyM7479/AVlXFRxuMCk=
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.3.0/go.mod h1:MBQ8lrhLObU/6UmLb4fmbmk5OcyYmqtbGd/9yIeKjEE=
@@ -920,8 +843,8 @@ golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
 golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
 golang.org/x/net v0.14.0/go.mod h1:PpSgVXXLK0OxS0F31C1/tv6XNguvCrnXIDrFMspZIUI=
 golang.org/x/net v0.20.0/go.mod h1:z8BVo6PvndSri0LbOE3hAn0apkU+1YvI6E70E9jsnvY=
-golang.org/x/net v0.35.0 h1:T5GQRQb2y08kTAByq9L4/bz8cipCdA8FbRTXewonqY8=
-golang.org/x/net v0.35.0/go.mod h1:EglIi67kWsHKlRzzVMUD93VMSWGFOMSZgxFjparz1Qk=
+golang.org/x/net v0.41.0 h1:vBTly1HeNPEn3wtREYfy4GZ/NECgw2Cnl+nK6Nz3uvw=
+golang.org/x/net v0.41.0/go.mod h1:B/K4NNqkfmg07DQYrbwvSluqCJOOXwUjeb/5lOisjbA=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20181017192945-9dcd33a902f4/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20181203162652-d668ce993890/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
@@ -937,9 +860,8 @@ golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.11.0 h1:GGz8+XQP4FvTTrjZPzNKTMFtSXH80RAzG+5ghFPgK9w=
-golang.org/x/sync v0.11.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
-golang.org/x/sys v0.0.0-20180810173357-98c5dad5d1a0/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sync v0.15.0 h1:KWH3jNZsfyT6xfAfKiz6MRNmd46ByHDYaZ7KSkCtdW8=
+golang.org/x/sync v0.15.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
 golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181029174526-d69651ed3497/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -947,20 +869,15 @@ golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5h
 golang.org/x/sys v0.0.0-20190316082340-a2f829d7f35f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200124204421-9fbb57f87de9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200602225109-6fdc65e7d980/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201204225414-ed752295db88/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210303074136-134d130e1a04/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210330210617-4fbd30eecc44/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210426080607-c94f62235c83/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210510120138-977fb7262007/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20210616094352-59db8d763f22/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -973,14 +890,13 @@ golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.9.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.16.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.30.0 h1:QjkSwP/36a20jFYWkSue1YwXzLmsV5Gfq7Eiy72C1uc=
-golang.org/x/sys v0.30.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.33.0 h1:q3i8TbbEz+JRD9ywIRlyRAQbM0qF7hu24q3teo2hbuw=
+golang.org/x/sys v0.33.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.3.0/go.mod h1:q750SLmJuPmVoN1blW3UFBPREJfb1KmY3vwxfr+nFDA=
@@ -990,8 +906,8 @@ golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
 golang.org/x/term v0.11.0/go.mod h1:zC9APTIj3jG3FdV/Ons+XE1riIZXG4aZ4GTHiPZJPIU=
 golang.org/x/term v0.16.0/go.mod h1:yn7UURbUtPyrVJPGPq404EukNFxcm/foM+bV/bfcDsY=
 golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
-golang.org/x/term v0.29.0 h1:L6pJp37ocefwRRtYPKSWOWzOtWSxVajvz2ldH/xi3iU=
-golang.org/x/term v0.29.0/go.mod h1:6bl4lRlvVuDgSf3179VpIxBF0o10JUpXWOnI7nErv7s=
+golang.org/x/term v0.32.0 h1:DR4lr0TjUs3epypdhTOkMmuF5CDFJ/8pOnbzMZPQ7bg=
+golang.org/x/term v0.32.0/go.mod h1:uZG1FhGx848Sqfsq4/DlJr3xGGsYMu/L5GW4abiaEPQ=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
@@ -1002,16 +918,15 @@ golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 golang.org/x/text v0.12.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
-golang.org/x/text v0.22.0 h1:bofq7m3/HAFvbF51jz3Q9wLg3jkvSPuiZu/pD1XwgtM=
-golang.org/x/text v0.22.0/go.mod h1:YRoo4H8PVmsu+E3Ou7cqLVH8oXWIHVoX0jqUWALQhfY=
+golang.org/x/text v0.26.0 h1:P42AVeLghgTYr4+xUnTRKDMqpar+PtX7KWuNQL21L8M=
+golang.org/x/text v0.26.0/go.mod h1:QK15LZJUUQVJxhz7wXgxSy/CJaTFjd0G+YLonydOVQA=
 golang.org/x/time v0.0.0-20180412165947-fbb02b2291d2/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.8.0 h1:9i3RxcPv3PZnitoVGMPDKZSq1xW1gK1Xy3ArNOGZfEg=
-golang.org/x/time v0.8.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
+golang.org/x/time v0.12.0 h1:ScB/8o8olJvc+CQPWrK3fPZNfh7qgwCrY0zJmoEQLSE=
+golang.org/x/time v0.12.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=
 golang.org/x/tools v0.0.0-20180828015842-6cd1fcedba52/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20181030000716-a0a13e073c7b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
-golang.org/x/tools v0.0.0-20181030221726-6c7e314b6563/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
 golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
@@ -1024,24 +939,23 @@ golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtn
 golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
 golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
-golang.org/x/tools v0.1.5/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
 golang.org/x/tools v0.4.0/go.mod h1:UE5sM2OK9E/d67R0ANs2xJizIymRP5gJU295PvKXxjQ=
 golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
-golang.org/x/tools v0.30.0 h1:BgcpHewrV5AUp2G9MebG4XPFI1E2W41zU1SaqVA9vJY=
-golang.org/x/tools v0.30.0/go.mod h1:c347cR/OJfw5TI+GfX7RUPNMdDRRbjvYTS0jPyvsVtY=
+golang.org/x/tools v0.34.0 h1:qIpSLOxeCYGg9TrcJokLBG4KFA6d795g0xkBkiESGlo=
+golang.org/x/tools v0.34.0/go.mod h1:pAP9OwEaY1CAW3HOmg3hLZC5Z0CCmzjAF2UQMSqNARg=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2 h1:B82qJJgjvYKsXS9jeunTOisW56dUokqW/FOteYJJ/yg=
 golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2/go.mod h1:deeaetjYA+DHMHg+sMSMI58GrEteJUUzzw7en6TJQcI=
-golang.zx2c4.com/wireguard v0.0.0-20231211153847-12269c276173 h1:/jFs0duh4rdb8uIfPMv78iAJGcPKDeqAFnaLBropIC4=
-golang.zx2c4.com/wireguard v0.0.0-20231211153847-12269c276173/go.mod h1:tkCQ4FQXmpAgYVh++1cq16/dH4QJtmvpRv19DWGAHSA=
+golang.zx2c4.com/wireguard v0.0.0-20250521234502-f333402bd9cb h1:whnFRlWMcXI9d+ZbWg+4sHnLp52d5yiIPUxMBSt4X9A=
+golang.zx2c4.com/wireguard v0.0.0-20250521234502-f333402bd9cb/go.mod h1:rpwXGsirqLqN2L0JDJQlwOboGHmptD5ZD6T2VmcqhTw=
 golang.zx2c4.com/wireguard/windows v0.5.3 h1:On6j2Rpn3OEMXqBq00QEDC7bWSZrPIHKIus8eIuExIE=
 golang.zx2c4.com/wireguard/windows v0.5.3/go.mod h1:9TEe8TJmtwyQebdFwAkEWOPr3prrtqm+REGFifP60hI=
-gonum.org/v1/gonum v0.15.1 h1:FNy7N6OUZVUaWG9pTiD+jlhdQ3lMP+/LcTpJ6+a8sQ0=
-gonum.org/v1/gonum v0.15.1/go.mod h1:eZTZuRFrzu5pcyjN5wJhcIhnUdNijYxX1T2IcrOGY0o=
+gonum.org/v1/gonum v0.16.0 h1:5+ul4Swaf3ESvrOnidPp4GZbzf0mxVQpDCYUQE7OJfk=
+gonum.org/v1/gonum v0.16.0/go.mod h1:fef3am4MQ93R2HHpKnLk4/Tbh/s0+wqD5nfa6Pnwy4E=
 google.golang.org/api v0.0.0-20180910000450-7ca32eb868bf/go.mod h1:4mhQ8q/RsB7i+udVvVy5NUi08OU8ZlA0gRVgrF7VFY0=
 google.golang.org/api v0.0.0-20181030000543-1d582fd0359e/go.mod h1:4mhQ8q/RsB7i+udVvVy5NUi08OU8ZlA0gRVgrF7VFY0=
 google.golang.org/api v0.1.0/go.mod h1:UGEZY7KEX120AnNLIHFMKIo4obdJhkp2tPbaPlQx13Y=
@@ -1080,11 +994,10 @@ google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2
 google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
 google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
 google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c=
-google.golang.org/protobuf v1.36.5 h1:tPhr+woSbjfYvY6/GPufUoYizxw1cF/yFoxJ2fmpwlM=
-google.golang.org/protobuf v1.36.5/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
+google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=
+google.golang.org/protobuf v1.36.6/go.mod h1:jduwjTPXsFjZGTmRluh+L6NjiWu7pchiJ2/5YcXBHnY=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
 gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
@@ -1096,18 +1009,16 @@ gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWD
 gopkg.in/yaml.v1 v1.0.0-20140924161607-9f9df34309c0/go.mod h1:WDnlLJ4WF5VGsH/HVa3CI79GS0ol3YnhVnKP89i0kNg=
 gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
-gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
 gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
-gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gotest.tools/v3 v3.5.1 h1:EENdUnS3pdur5nybKYIh2Vfgc8IUNBjxDPSjtiJcOzU=
 gotest.tools/v3 v3.5.1/go.mod h1:isy3WKz7GK6uNw/sbHzfKBLvlvXwUyV06n6brMxxopU=
 grpc.go4.org v0.0.0-20170609214715-11d0a25b4919/go.mod h1:77eQGdRu53HpSqPFJFmuJdjuHRquDANNeA4x7B8WQ9o=
-gvisor.dev/gvisor v0.0.0-20230927004350-cbd86285d259 h1:TbRPT0HtzFP3Cno1zZo7yPzEEnfu8EjLfl6IU9VfqkQ=
-gvisor.dev/gvisor v0.0.0-20230927004350-cbd86285d259/go.mod h1:AVgIgHMwK63XvmAzWG9vLQ41YnVHN0du0tEC46fI7yY=
+gvisor.dev/gvisor v0.0.0-20250503011706-39ed1f5ac29c h1:m/r7OM+Y2Ty1sgBQ7Qb27VgIMBW8ZZhT4gLnUyDIhzI=
+gvisor.dev/gvisor v0.0.0-20250503011706-39ed1f5ac29c/go.mod h1:3r5CMtNQMKIvBlrmM9xWUNamjKBYPOWyXOjmg5Kts3g=
 honnef.co/go/tools v0.0.0-20180728063816-88497007e858/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
 honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
 honnef.co/go/tools v0.0.0-20190106161140-3f1c8253044a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
@@ -1115,8 +1026,8 @@ honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWh
 honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt0JzvZhAg=
 howett.net/plist v1.0.0 h1:7CrbWYbPPO/PyNy38b2EB/+gYbjCe2DXBxgtOOZbSQM=
 howett.net/plist v1.0.0/go.mod h1:lqaXoTrLY4hg8tnEzNru53gicrbv7rrk+2xJA/7hw9g=
-lukechampine.com/blake3 v1.3.0 h1:sJ3XhFINmHSrYCgl958hscfIa3bw8x4DqMP3u1YvoYE=
-lukechampine.com/blake3 v1.3.0/go.mod h1:0OFRp7fBtAylGVCO40o87sbupkyIGgbpv1+M1k1LM6k=
+lukechampine.com/blake3 v1.4.1 h1:I3Smz7gso8w4/TunLKec6K2fn+kyKtDxr/xcQEN84Wg=
+lukechampine.com/blake3 v1.4.1/go.mod h1:QFosUxmjB8mnrWFSNwKmvxHpfY72bmD2tQ0kBMM3kwo=
 oras.land/oras-go/v2 v2.5.0 h1:o8Me9kLY74Vp5uw07QXPiitjsw7qNXi8Twd+19Zf02c=
 oras.land/oras-go/v2 v2.5.0/go.mod h1:z4eisnLP530vwIOUOJeBIj0aGI0L1C3d53atvCBqZHg=
 sigs.k8s.io/yaml v1.3.0 h1:a2VclLzOGrwOHDiV8EfBGhvjHvP46CtW5j6POvhYGGo=

pkg/downloader/uri.go

@@ -98,19 +98,19 @@ func (uri URI) DownloadWithAuthorizationAndCallback(basePath string, authorizati
 }
 
 func (u URI) FilenameFromUrl() (string, error) {
-	f, err := filenameFromUrl(string(u))
-	if err != nil || f == "" {
-		f = utils.MD5(string(u))
-		if strings.HasSuffix(string(u), ".yaml") || strings.HasSuffix(string(u), ".yml") {
-			f = f + ".yaml"
-		}
-		err = nil
+	if f := filenameFromUrl(string(u)); f != "" {
+		return f, nil
 	}
 
-	return f, err
+	f := utils.MD5(string(u))
+	if strings.HasSuffix(string(u), ".yaml") || strings.HasSuffix(string(u), ".yml") {
+		f = f + ".yaml"
+	}
+
+	return f, nil
 }
 
-func filenameFromUrl(urlstr string) (string, error) {
+func filenameFromUrl(urlstr string) string {
 	// strip anything after @
 	if strings.Contains(urlstr, "@") {
 		urlstr = strings.Split(urlstr, "@")[0]
@@ -118,13 +118,13 @@ func filenameFromUrl(urlstr string) (string, error) {
 
 	u, err := url.Parse(urlstr)
 	if err != nil {
-		return "", fmt.Errorf("error due to parsing url: %w", err)
+		return ""
 	}
 	x, err := url.QueryUnescape(u.EscapedPath())
 	if err != nil {
-		return "", fmt.Errorf("error due to escaping: %w", err)
+		return ""
 	}
-	return filepath.Base(x), nil
+	return filepath.Base(x)
 }
 
 func (u URI) LooksLikeURL() bool {
@@ -144,6 +144,11 @@ func (u URI) LooksLikeHTTPURL() bool {
 		strings.HasPrefix(string(u), HTTPSPrefix)
 }
 
+func (u URI) LooksLikeDir() bool {
+	f, err := os.Stat(string(u))
+	return err == nil && f.IsDir()
+}
+
 func (s URI) LooksLikeOCI() bool {
 	return strings.HasPrefix(string(s), "quay.io") ||
 		strings.HasPrefix(string(s), OCIPrefix) ||
@@ -153,6 +158,10 @@ func (s URI) LooksLikeOCI() bool {
 		strings.HasPrefix(string(s), "docker.io")
 }
 
+func (s URI) LooksLikeOCIFile() bool {
+	return strings.HasPrefix(string(s), OCIFilePrefix)
+}
+
 func (s URI) ResolveURL() string {
 	switch {
 	case strings.HasPrefix(string(s), GithubURI2):

pkg/system/capabilities.go

@@ -18,6 +18,13 @@ const (
 	nvidiaL4T         = "nvidia-l4t"
 	darwinX86         = "darwin-x86"
 	metal             = "metal"
+	nvidia            = "nvidia"
+	amd               = "amd"
+	intel             = "intel"
+
+	capabilityEnv        = "LOCALAI_FORCE_META_BACKEND_CAPABILITY"
+	capabilityRunFileEnv = "LOCALAI_FORCE_META_BACKEND_CAPABILITY_RUN_FILE"
+	defaultRunFile       = "/run/localai/capability"
 )
 
 func (s *SystemState) Capability(capMap map[string]string) string {
@@ -35,15 +42,16 @@ func (s *SystemState) Capability(capMap map[string]string) string {
 }
 
 func (s *SystemState) getSystemCapabilities() string {
-	if os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY") != "" {
-		log.Debug().Str("LOCALAI_FORCE_META_BACKEND_CAPABILITY", os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY")).Msg("Using forced capability")
-		return os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY")
+	capability := os.Getenv(capabilityEnv)
+	if capability != "" {
+		log.Info().Str("capability", capability).Msgf("Using forced capability from environment variable (%s)", capabilityEnv)
+		return capability
 	}
 
-	capabilityRunFile := "/run/localai/capability"
-	if os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY_RUN_FILE") != "" {
-		log.Debug().Str("LOCALAI_FORCE_META_BACKEND_CAPABILITY_RUN_FILE", os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY_RUN_FILE")).Msg("Using forced capability run file")
-		capabilityRunFile = os.Getenv("LOCALAI_FORCE_META_BACKEND_CAPABILITY_RUN_FILE")
+	capabilityRunFile := defaultRunFile
+	capabilityRunFileEnv := os.Getenv(capabilityRunFileEnv)
+	if capabilityRunFileEnv != "" {
+		capabilityRunFile = capabilityRunFileEnv
 	}
 
 	// Check if /run/localai/capability exists and use it
@@ -52,37 +60,37 @@ func (s *SystemState) getSystemCapabilities() string {
 	if _, err := os.Stat(capabilityRunFile); err == nil {
 		capability, err := os.ReadFile(capabilityRunFile)
 		if err == nil {
-			log.Debug().Str("capability", string(capability)).Msg("Using capability from run file")
+			log.Info().Str("capabilityRunFile", capabilityRunFile).Str("capability", string(capability)).Msgf("Using forced capability run file (%s)", capabilityRunFileEnv)
 			return strings.Trim(strings.TrimSpace(string(capability)), "\n")
 		}
 	}
 
 	// If we are on mac and arm64, we will return metal
 	if runtime.GOOS == "darwin" && runtime.GOARCH == "arm64" {
-		log.Debug().Msg("Using metal capability")
+		log.Info().Msgf("Using metal capability (arm64 on mac), set %s to override", capabilityEnv)
 		return metal
 	}
 
 	// If we are on mac and x86, we will return darwin-x86
 	if runtime.GOOS == "darwin" && runtime.GOARCH == "amd64" {
-		log.Debug().Msg("Using darwin-x86 capability")
+		log.Info().Msgf("Using darwin-x86 capability (amd64 on mac), set %s to override", capabilityEnv)
 		return darwinX86
 	}
 
 	// If arm64 on linux and a nvidia gpu is detected, we will return nvidia-l4t
 	if runtime.GOOS == "linux" && runtime.GOARCH == "arm64" {
 		if s.GPUVendor == "nvidia" {
-			log.Debug().Msg("Using nvidia-l4t capability")
+			log.Info().Msgf("Using nvidia-l4t capability (arm64 on linux), set %s to override", capabilityEnv)
 			return nvidiaL4T
 		}
 	}
 
 	if s.GPUVendor == "" {
-		log.Debug().Msg("Using default capability")
+		log.Info().Msgf("Default capability (no GPU detected), set %s to override", capabilityEnv)
 		return defaultCapability
 	}
 
-	log.Debug().Str("GPUVendor", s.GPUVendor).Msg("Using GPU vendor capability")
+	log.Info().Str("Capability", s.GPUVendor).Msgf("Capability automatically detected, set %s to override", capabilityEnv)
 	return s.GPUVendor
 }
 
@@ -106,18 +114,16 @@ func detectGPUVendor() (string, error) {
 			if gpu.DeviceInfo.Vendor != nil {
 				gpuVendorName := strings.ToUpper(gpu.DeviceInfo.Vendor.Name)
 				if strings.Contains(gpuVendorName, "NVIDIA") {
-					return "nvidia", nil
+					return nvidia, nil
 				}
 				if strings.Contains(gpuVendorName, "AMD") {
-					return "amd", nil
+					return amd, nil
 				}
 				if strings.Contains(gpuVendorName, "INTEL") {
-					return "intel", nil
+					return intel, nil
 				}
-				return "nvidia", nil
 			}
 		}
-
 	}
 
 	return "", nil

swagger/docs.go

@@ -92,6 +92,129 @@ const docTemplate = `{
                 "responses": {}
             }
         },
+        "/backends": {
+            "get": {
+                "summary": "List all Backends",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "type": "array",
+                            "items": {
+                                "$ref": "#/definitions/gallery.GalleryBackend"
+                            }
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/apply": {
+            "post": {
+                "summary": "Install backends to LocalAI.",
+                "parameters": [
+                    {
+                        "description": "query params",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/localai.GalleryBackend"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/schema.BackendResponse"
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/available": {
+            "get": {
+                "summary": "List all available Backends",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "type": "array",
+                            "items": {
+                                "$ref": "#/definitions/gallery.GalleryBackend"
+                            }
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/delete/{name}": {
+            "post": {
+                "summary": "delete backends from LocalAI.",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Backend name",
+                        "name": "name",
+                        "in": "path",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/schema.BackendResponse"
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/galleries": {
+            "get": {
+                "summary": "List all Galleries",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "type": "array",
+                            "items": {
+                                "$ref": "#/definitions/config.Gallery"
+                            }
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/jobs": {
+            "get": {
+                "summary": "Returns all the jobs status progress",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": {
+                                "$ref": "#/definitions/services.GalleryOpStatus"
+                            }
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/jobs/{uuid}": {
+            "get": {
+                "summary": "Returns the job status",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/services.GalleryOpStatus"
+                        }
+                    }
+                }
+            }
+        },
         "/metrics": {
             "get": {
                 "summary": "Prometheus metrics endpoint",
@@ -185,56 +308,6 @@ const docTemplate = `{
                         }
                     }
                 }
-            },
-            "post": {
-                "summary": "Adds a gallery in LocalAI",
-                "parameters": [
-                    {
-                        "description": "Gallery details",
-                        "name": "request",
-                        "in": "body",
-                        "required": true,
-                        "schema": {
-                            "$ref": "#/definitions/config.Gallery"
-                        }
-                    }
-                ],
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "type": "array",
-                            "items": {
-                                "$ref": "#/definitions/config.Gallery"
-                            }
-                        }
-                    }
-                }
-            },
-            "delete": {
-                "summary": "removes a gallery from LocalAI",
-                "parameters": [
-                    {
-                        "description": "Gallery details",
-                        "name": "request",
-                        "in": "body",
-                        "required": true,
-                        "schema": {
-                            "$ref": "#/definitions/config.Gallery"
-                        }
-                    }
-                ],
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "type": "array",
-                            "items": {
-                                "$ref": "#/definitions/config.Gallery"
-                            }
-                        }
-                    }
-                }
             }
         },
         "/models/jobs": {
@@ -328,94 +401,6 @@ const docTemplate = `{
                 }
             }
         },
-        "/v1/assistants": {
-            "get": {
-                "summary": "List available assistents",
-                "parameters": [
-                    {
-                        "type": "integer",
-                        "description": "Limit the number of assistants returned",
-                        "name": "limit",
-                        "in": "query"
-                    },
-                    {
-                        "type": "string",
-                        "description": "Order of assistants returned",
-                        "name": "order",
-                        "in": "query"
-                    },
-                    {
-                        "type": "string",
-                        "description": "Return assistants created after the given ID",
-                        "name": "after",
-                        "in": "query"
-                    },
-                    {
-                        "type": "string",
-                        "description": "Return assistants created before the given ID",
-                        "name": "before",
-                        "in": "query"
-                    }
-                ],
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "type": "array",
-                            "items": {
-                                "$ref": "#/definitions/openai.Assistant"
-                            }
-                        }
-                    }
-                }
-            },
-            "post": {
-                "summary": "Create an assistant with a model and instructions.",
-                "parameters": [
-                    {
-                        "description": "query params",
-                        "name": "request",
-                        "in": "body",
-                        "required": true,
-                        "schema": {
-                            "$ref": "#/definitions/openai.AssistantRequest"
-                        }
-                    }
-                ],
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/openai.Assistant"
-                        }
-                    }
-                }
-            }
-        },
-        "/v1/assistants/{assistant_id}": {
-            "get": {
-                "summary": "Get assistent data",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/openai.Assistant"
-                        }
-                    }
-                }
-            },
-            "delete": {
-                "summary": "Delete assistents",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/schema.DeleteAssistantResponse"
-                        }
-                    }
-                }
-            }
-        },
         "/v1/audio/speech": {
             "post": {
                 "consumes": [
@@ -529,6 +514,30 @@ const docTemplate = `{
                 }
             }
         },
+        "/v1/detection": {
+            "post": {
+                "summary": "Detects objects in the input image.",
+                "parameters": [
+                    {
+                        "description": "query params",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/schema.DetectionRequest"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/schema.DetectionResponse"
+                        }
+                    }
+                }
+            }
+        },
         "/v1/edits": {
             "post": {
                 "summary": "OpenAI edit endpoint",
@@ -577,56 +586,6 @@ const docTemplate = `{
                 }
             }
         },
-        "/v1/files": {
-            "get": {
-                "summary": "List files.",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/schema.ListFiles"
-                        }
-                    }
-                }
-            }
-        },
-        "/v1/files/{file_id}": {
-            "get": {
-                "summary": "Returns information about a specific file.",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/schema.File"
-                        }
-                    }
-                }
-            },
-            "delete": {
-                "summary": "Delete a file.",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/openai.DeleteStatus"
-                        }
-                    }
-                }
-            }
-        },
-        "/v1/files/{file_id}/content": {
-            "get": {
-                "summary": "Returns information about a specific file.",
-                "responses": {
-                    "200": {
-                        "description": "file",
-                        "schema": {
-                            "type": "string"
-                        }
-                    }
-                }
-            }
-        },
         "/v1/images/generations": {
             "post": {
                 "summary": "Creates an image given a prompt.",
@@ -926,6 +885,75 @@ const docTemplate = `{
                 }
             }
         },
+        "gallery.GalleryBackend": {
+            "type": "object",
+            "properties": {
+                "alias": {
+                    "type": "string"
+                },
+                "capabilities": {
+                    "type": "object",
+                    "additionalProperties": {
+                        "type": "string"
+                    }
+                },
+                "description": {
+                    "type": "string"
+                },
+                "files": {
+                    "description": "AdditionalFiles are used to add additional files to the model",
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/gallery.File"
+                    }
+                },
+                "gallery": {
+                    "description": "Gallery is a reference to the gallery which contains the model",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/config.Gallery"
+                        }
+                    ]
+                },
+                "icon": {
+                    "type": "string"
+                },
+                "installed": {
+                    "description": "Installed is used to indicate if the model is installed or not",
+                    "type": "boolean"
+                },
+                "license": {
+                    "type": "string"
+                },
+                "mirrors": {
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
+                "name": {
+                    "type": "string"
+                },
+                "tags": {
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
+                "uri": {
+                    "type": "string"
+                },
+                "url": {
+                    "type": "string"
+                },
+                "urls": {
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                }
+            }
+        },
         "gallery.GalleryModel": {
             "type": "object",
             "properties": {
@@ -987,34 +1015,11 @@ const docTemplate = `{
                 }
             }
         },
-        "services.GalleryOpStatus": {
+        "localai.GalleryBackend": {
             "type": "object",
             "properties": {
-                "deletion": {
-                    "description": "Deletion is true if the operation is a deletion",
-                    "type": "boolean"
-                },
-                "downloaded_size": {
+                "id": {
                     "type": "string"
-                },
-                "error": {},
-                "file_name": {
-                    "type": "string"
-                },
-                "file_size": {
-                    "type": "string"
-                },
-                "gallery_model_name": {
-                    "type": "string"
-                },
-                "message": {
-                    "type": "string"
-                },
-                "processed": {
-                    "type": "boolean"
-                },
-                "progress": {
-                    "type": "number"
                 }
             }
         },
@@ -1026,9 +1031,6 @@ const docTemplate = `{
                     "type": "object",
                     "additionalProperties": true
                 },
-                "config_url": {
-                    "type": "string"
-                },
                 "description": {
                     "type": "string"
                 },
@@ -1085,130 +1087,6 @@ const docTemplate = `{
                 }
             }
         },
-        "openai.Assistant": {
-            "type": "object",
-            "properties": {
-                "created": {
-                    "description": "The time at which the assistant was created.",
-                    "type": "integer"
-                },
-                "description": {
-                    "description": "The description of the assistant.",
-                    "type": "string"
-                },
-                "file_ids": {
-                    "description": "A list of file IDs attached to this assistant.",
-                    "type": "array",
-                    "items": {
-                        "type": "string"
-                    }
-                },
-                "id": {
-                    "description": "The unique identifier of the assistant.",
-                    "type": "string"
-                },
-                "instructions": {
-                    "description": "The system instructions that the assistant uses.",
-                    "type": "string"
-                },
-                "metadata": {
-                    "description": "Set of key-value pairs attached to the assistant.",
-                    "type": "object",
-                    "additionalProperties": {
-                        "type": "string"
-                    }
-                },
-                "model": {
-                    "description": "The model ID used by the assistant.",
-                    "type": "string"
-                },
-                "name": {
-                    "description": "The name of the assistant.",
-                    "type": "string"
-                },
-                "object": {
-                    "description": "Object type, which is \"assistant\".",
-                    "type": "string"
-                },
-                "tools": {
-                    "description": "A list of tools enabled on the assistant.",
-                    "type": "array",
-                    "items": {
-                        "$ref": "#/definitions/openai.Tool"
-                    }
-                }
-            }
-        },
-        "openai.AssistantRequest": {
-            "type": "object",
-            "properties": {
-                "description": {
-                    "type": "string"
-                },
-                "file_ids": {
-                    "type": "array",
-                    "items": {
-                        "type": "string"
-                    }
-                },
-                "instructions": {
-                    "type": "string"
-                },
-                "metadata": {
-                    "type": "object",
-                    "additionalProperties": {
-                        "type": "string"
-                    }
-                },
-                "model": {
-                    "type": "string"
-                },
-                "name": {
-                    "type": "string"
-                },
-                "tools": {
-                    "type": "array",
-                    "items": {
-                        "$ref": "#/definitions/openai.Tool"
-                    }
-                }
-            }
-        },
-        "openai.DeleteStatus": {
-            "type": "object",
-            "properties": {
-                "deleted": {
-                    "type": "boolean"
-                },
-                "id": {
-                    "type": "string"
-                },
-                "object": {
-                    "type": "string"
-                }
-            }
-        },
-        "openai.Tool": {
-            "type": "object",
-            "properties": {
-                "type": {
-                    "$ref": "#/definitions/openai.ToolType"
-                }
-            }
-        },
-        "openai.ToolType": {
-            "type": "string",
-            "enum": [
-                "code_interpreter",
-                "retrieval",
-                "function"
-            ],
-            "x-enum-varnames": [
-                "CodeInterpreter",
-                "Retrieval",
-                "Function"
-            ]
-        },
         "p2p.NodeData": {
             "type": "object",
             "properties": {
@@ -1235,7 +1113,8 @@ const docTemplate = `{
                 "breakdown": {
                     "type": "object",
                     "additionalProperties": {
-                        "type": "integer"
+                        "type": "integer",
+                        "format": "int64"
                     }
                 },
                 "total": {
@@ -1256,6 +1135,7 @@ const docTemplate = `{
         },
         "proto.StatusResponse_State": {
             "type": "integer",
+            "format": "int32",
             "enum": [
                 0,
                 1,
@@ -1299,6 +1179,17 @@ const docTemplate = `{
                 }
             }
         },
+        "schema.BackendResponse": {
+            "type": "object",
+            "properties": {
+                "id": {
+                    "type": "string"
+                },
+                "status_url": {
+                    "type": "string"
+                }
+            }
+        },
         "schema.Choice": {
             "type": "object",
             "properties": {
@@ -1319,17 +1210,45 @@ const docTemplate = `{
                 }
             }
         },
-        "schema.DeleteAssistantResponse": {
+        "schema.Detection": {
             "type": "object",
             "properties": {
-                "deleted": {
-                    "type": "boolean"
-                },
-                "id": {
+                "class_name": {
                     "type": "string"
                 },
-                "object": {
+                "height": {
+                    "type": "number"
+                },
+                "width": {
+                    "type": "number"
+                },
+                "x": {
+                    "type": "number"
+                },
+                "y": {
+                    "type": "number"
+                }
+            }
+        },
+        "schema.DetectionRequest": {
+            "type": "object",
+            "properties": {
+                "image": {
                     "type": "string"
+                },
+                "model": {
+                    "type": "string"
+                }
+            }
+        },
+        "schema.DetectionResponse": {
+            "type": "object",
+            "properties": {
+                "detections": {
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/schema.Detection"
+                    }
                 }
             }
         },
@@ -1353,35 +1272,6 @@ const docTemplate = `{
                 }
             }
         },
-        "schema.File": {
-            "type": "object",
-            "properties": {
-                "bytes": {
-                    "description": "Size of the file in bytes",
-                    "type": "integer"
-                },
-                "created_at": {
-                    "description": "The time at which the file was created",
-                    "type": "string"
-                },
-                "filename": {
-                    "description": "The name of the file",
-                    "type": "string"
-                },
-                "id": {
-                    "description": "Unique identifier for the file",
-                    "type": "string"
-                },
-                "object": {
-                    "description": "Type of the object (e.g., \"file\")",
-                    "type": "string"
-                },
-                "purpose": {
-                    "description": "The purpose of the file (e.g., \"fine-tune\", \"classifications\", etc.)",
-                    "type": "string"
-                }
-            }
-        },
         "schema.FunctionCall": {
             "type": "object",
             "properties": {
@@ -1501,20 +1391,6 @@ const docTemplate = `{
                 }
             }
         },
-        "schema.ListFiles": {
-            "type": "object",
-            "properties": {
-                "data": {
-                    "type": "array",
-                    "items": {
-                        "$ref": "#/definitions/schema.File"
-                    }
-                },
-                "object": {
-                    "type": "string"
-                }
-            }
-        },
         "schema.Message": {
             "type": "object",
             "properties": {
@@ -1610,6 +1486,13 @@ const docTemplate = `{
                     "description": "whisper",
                     "type": "string"
                 },
+                "files": {
+                    "description": "Multiple input images for img2img or inpainting",
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
                 "frequency_penalty": {
                     "type": "number"
                 },
@@ -1652,6 +1535,12 @@ const docTemplate = `{
                         "$ref": "#/definitions/schema.Message"
                     }
                 },
+                "metadata": {
+                    "type": "object",
+                    "additionalProperties": {
+                        "type": "string"
+                    }
+                },
                 "mode": {
                     "description": "Image (not supported by OpenAI)",
                     "type": "integer"
@@ -1684,6 +1573,16 @@ const docTemplate = `{
                 "quality": {
                     "type": "string"
                 },
+                "reasoning_effort": {
+                    "type": "string"
+                },
+                "ref_images": {
+                    "description": "Reference images for models that support them (e.g., Flux Kontext)",
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
                 "repeat_last_n": {
                     "type": "integer"
                 },
@@ -1923,6 +1822,37 @@ const docTemplate = `{
                     "type": "string"
                 }
             }
+        },
+        "services.GalleryOpStatus": {
+            "type": "object",
+            "properties": {
+                "deletion": {
+                    "description": "Deletion is true if the operation is a deletion",
+                    "type": "boolean"
+                },
+                "downloaded_size": {
+                    "type": "string"
+                },
+                "error": {},
+                "file_name": {
+                    "type": "string"
+                },
+                "file_size": {
+                    "type": "string"
+                },
+                "gallery_element_name": {
+                    "type": "string"
+                },
+                "message": {
+                    "type": "string"
+                },
+                "processed": {
+                    "type": "boolean"
+                },
+                "progress": {
+                    "type": "number"
+                }
+            }
         }
     },
     "securityDefinitions": {

swagger/swagger.json

@@ -85,6 +85,129 @@
                 "responses": {}
             }
         },
+        "/backends": {
+            "get": {
+                "summary": "List all Backends",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "type": "array",
+                            "items": {
+                                "$ref": "#/definitions/gallery.GalleryBackend"
+                            }
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/apply": {
+            "post": {
+                "summary": "Install backends to LocalAI.",
+                "parameters": [
+                    {
+                        "description": "query params",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/localai.GalleryBackend"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/schema.BackendResponse"
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/available": {
+            "get": {
+                "summary": "List all available Backends",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "type": "array",
+                            "items": {
+                                "$ref": "#/definitions/gallery.GalleryBackend"
+                            }
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/delete/{name}": {
+            "post": {
+                "summary": "delete backends from LocalAI.",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Backend name",
+                        "name": "name",
+                        "in": "path",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/schema.BackendResponse"
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/galleries": {
+            "get": {
+                "summary": "List all Galleries",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "type": "array",
+                            "items": {
+                                "$ref": "#/definitions/config.Gallery"
+                            }
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/jobs": {
+            "get": {
+                "summary": "Returns all the jobs status progress",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "type": "object",
+                            "additionalProperties": {
+                                "$ref": "#/definitions/services.GalleryOpStatus"
+                            }
+                        }
+                    }
+                }
+            }
+        },
+        "/backends/jobs/{uuid}": {
+            "get": {
+                "summary": "Returns the job status",
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/services.GalleryOpStatus"
+                        }
+                    }
+                }
+            }
+        },
         "/metrics": {
             "get": {
                 "summary": "Prometheus metrics endpoint",
@@ -178,56 +301,6 @@
                         }
                     }
                 }
-            },
-            "post": {
-                "summary": "Adds a gallery in LocalAI",
-                "parameters": [
-                    {
-                        "description": "Gallery details",
-                        "name": "request",
-                        "in": "body",
-                        "required": true,
-                        "schema": {
-                            "$ref": "#/definitions/config.Gallery"
-                        }
-                    }
-                ],
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "type": "array",
-                            "items": {
-                                "$ref": "#/definitions/config.Gallery"
-                            }
-                        }
-                    }
-                }
-            },
-            "delete": {
-                "summary": "removes a gallery from LocalAI",
-                "parameters": [
-                    {
-                        "description": "Gallery details",
-                        "name": "request",
-                        "in": "body",
-                        "required": true,
-                        "schema": {
-                            "$ref": "#/definitions/config.Gallery"
-                        }
-                    }
-                ],
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "type": "array",
-                            "items": {
-                                "$ref": "#/definitions/config.Gallery"
-                            }
-                        }
-                    }
-                }
             }
         },
         "/models/jobs": {
@@ -321,94 +394,6 @@
                 }
             }
         },
-        "/v1/assistants": {
-            "get": {
-                "summary": "List available assistents",
-                "parameters": [
-                    {
-                        "type": "integer",
-                        "description": "Limit the number of assistants returned",
-                        "name": "limit",
-                        "in": "query"
-                    },
-                    {
-                        "type": "string",
-                        "description": "Order of assistants returned",
-                        "name": "order",
-                        "in": "query"
-                    },
-                    {
-                        "type": "string",
-                        "description": "Return assistants created after the given ID",
-                        "name": "after",
-                        "in": "query"
-                    },
-                    {
-                        "type": "string",
-                        "description": "Return assistants created before the given ID",
-                        "name": "before",
-                        "in": "query"
-                    }
-                ],
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "type": "array",
-                            "items": {
-                                "$ref": "#/definitions/openai.Assistant"
-                            }
-                        }
-                    }
-                }
-            },
-            "post": {
-                "summary": "Create an assistant with a model and instructions.",
-                "parameters": [
-                    {
-                        "description": "query params",
-                        "name": "request",
-                        "in": "body",
-                        "required": true,
-                        "schema": {
-                            "$ref": "#/definitions/openai.AssistantRequest"
-                        }
-                    }
-                ],
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/openai.Assistant"
-                        }
-                    }
-                }
-            }
-        },
-        "/v1/assistants/{assistant_id}": {
-            "get": {
-                "summary": "Get assistent data",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/openai.Assistant"
-                        }
-                    }
-                }
-            },
-            "delete": {
-                "summary": "Delete assistents",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/schema.DeleteAssistantResponse"
-                        }
-                    }
-                }
-            }
-        },
         "/v1/audio/speech": {
             "post": {
                 "consumes": [
@@ -522,6 +507,30 @@
                 }
             }
         },
+        "/v1/detection": {
+            "post": {
+                "summary": "Detects objects in the input image.",
+                "parameters": [
+                    {
+                        "description": "query params",
+                        "name": "request",
+                        "in": "body",
+                        "required": true,
+                        "schema": {
+                            "$ref": "#/definitions/schema.DetectionRequest"
+                        }
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Response",
+                        "schema": {
+                            "$ref": "#/definitions/schema.DetectionResponse"
+                        }
+                    }
+                }
+            }
+        },
         "/v1/edits": {
             "post": {
                 "summary": "OpenAI edit endpoint",
@@ -570,56 +579,6 @@
                 }
             }
         },
-        "/v1/files": {
-            "get": {
-                "summary": "List files.",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/schema.ListFiles"
-                        }
-                    }
-                }
-            }
-        },
-        "/v1/files/{file_id}": {
-            "get": {
-                "summary": "Returns information about a specific file.",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/schema.File"
-                        }
-                    }
-                }
-            },
-            "delete": {
-                "summary": "Delete a file.",
-                "responses": {
-                    "200": {
-                        "description": "Response",
-                        "schema": {
-                            "$ref": "#/definitions/openai.DeleteStatus"
-                        }
-                    }
-                }
-            }
-        },
-        "/v1/files/{file_id}/content": {
-            "get": {
-                "summary": "Returns information about a specific file.",
-                "responses": {
-                    "200": {
-                        "description": "file",
-                        "schema": {
-                            "type": "string"
-                        }
-                    }
-                }
-            }
-        },
         "/v1/images/generations": {
             "post": {
                 "summary": "Creates an image given a prompt.",
@@ -919,6 +878,75 @@
                 }
             }
         },
+        "gallery.GalleryBackend": {
+            "type": "object",
+            "properties": {
+                "alias": {
+                    "type": "string"
+                },
+                "capabilities": {
+                    "type": "object",
+                    "additionalProperties": {
+                        "type": "string"
+                    }
+                },
+                "description": {
+                    "type": "string"
+                },
+                "files": {
+                    "description": "AdditionalFiles are used to add additional files to the model",
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/gallery.File"
+                    }
+                },
+                "gallery": {
+                    "description": "Gallery is a reference to the gallery which contains the model",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/config.Gallery"
+                        }
+                    ]
+                },
+                "icon": {
+                    "type": "string"
+                },
+                "installed": {
+                    "description": "Installed is used to indicate if the model is installed or not",
+                    "type": "boolean"
+                },
+                "license": {
+                    "type": "string"
+                },
+                "mirrors": {
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
+                "name": {
+                    "type": "string"
+                },
+                "tags": {
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
+                "uri": {
+                    "type": "string"
+                },
+                "url": {
+                    "type": "string"
+                },
+                "urls": {
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                }
+            }
+        },
         "gallery.GalleryModel": {
             "type": "object",
             "properties": {
@@ -980,34 +1008,11 @@
                 }
             }
         },
-        "services.GalleryOpStatus": {
+        "localai.GalleryBackend": {
             "type": "object",
             "properties": {
-                "deletion": {
-                    "description": "Deletion is true if the operation is a deletion",
-                    "type": "boolean"
-                },
-                "downloaded_size": {
+                "id": {
                     "type": "string"
-                },
-                "error": {},
-                "file_name": {
-                    "type": "string"
-                },
-                "file_size": {
-                    "type": "string"
-                },
-                "gallery_model_name": {
-                    "type": "string"
-                },
-                "message": {
-                    "type": "string"
-                },
-                "processed": {
-                    "type": "boolean"
-                },
-                "progress": {
-                    "type": "number"
                 }
             }
         },
@@ -1019,9 +1024,6 @@
                     "type": "object",
                     "additionalProperties": true
                 },
-                "config_url": {
-                    "type": "string"
-                },
                 "description": {
                     "type": "string"
                 },
@@ -1078,130 +1080,6 @@
                 }
             }
         },
-        "openai.Assistant": {
-            "type": "object",
-            "properties": {
-                "created": {
-                    "description": "The time at which the assistant was created.",
-                    "type": "integer"
-                },
-                "description": {
-                    "description": "The description of the assistant.",
-                    "type": "string"
-                },
-                "file_ids": {
-                    "description": "A list of file IDs attached to this assistant.",
-                    "type": "array",
-                    "items": {
-                        "type": "string"
-                    }
-                },
-                "id": {
-                    "description": "The unique identifier of the assistant.",
-                    "type": "string"
-                },
-                "instructions": {
-                    "description": "The system instructions that the assistant uses.",
-                    "type": "string"
-                },
-                "metadata": {
-                    "description": "Set of key-value pairs attached to the assistant.",
-                    "type": "object",
-                    "additionalProperties": {
-                        "type": "string"
-                    }
-                },
-                "model": {
-                    "description": "The model ID used by the assistant.",
-                    "type": "string"
-                },
-                "name": {
-                    "description": "The name of the assistant.",
-                    "type": "string"
-                },
-                "object": {
-                    "description": "Object type, which is \"assistant\".",
-                    "type": "string"
-                },
-                "tools": {
-                    "description": "A list of tools enabled on the assistant.",
-                    "type": "array",
-                    "items": {
-                        "$ref": "#/definitions/openai.Tool"
-                    }
-                }
-            }
-        },
-        "openai.AssistantRequest": {
-            "type": "object",
-            "properties": {
-                "description": {
-                    "type": "string"
-                },
-                "file_ids": {
-                    "type": "array",
-                    "items": {
-                        "type": "string"
-                    }
-                },
-                "instructions": {
-                    "type": "string"
-                },
-                "metadata": {
-                    "type": "object",
-                    "additionalProperties": {
-                        "type": "string"
-                    }
-                },
-                "model": {
-                    "type": "string"
-                },
-                "name": {
-                    "type": "string"
-                },
-                "tools": {
-                    "type": "array",
-                    "items": {
-                        "$ref": "#/definitions/openai.Tool"
-                    }
-                }
-            }
-        },
-        "openai.DeleteStatus": {
-            "type": "object",
-            "properties": {
-                "deleted": {
-                    "type": "boolean"
-                },
-                "id": {
-                    "type": "string"
-                },
-                "object": {
-                    "type": "string"
-                }
-            }
-        },
-        "openai.Tool": {
-            "type": "object",
-            "properties": {
-                "type": {
-                    "$ref": "#/definitions/openai.ToolType"
-                }
-            }
-        },
-        "openai.ToolType": {
-            "type": "string",
-            "enum": [
-                "code_interpreter",
-                "retrieval",
-                "function"
-            ],
-            "x-enum-varnames": [
-                "CodeInterpreter",
-                "Retrieval",
-                "Function"
-            ]
-        },
         "p2p.NodeData": {
             "type": "object",
             "properties": {
@@ -1228,7 +1106,8 @@
                 "breakdown": {
                     "type": "object",
                     "additionalProperties": {
-                        "type": "integer"
+                        "type": "integer",
+                        "format": "int64"
                     }
                 },
                 "total": {
@@ -1249,6 +1128,7 @@
         },
         "proto.StatusResponse_State": {
             "type": "integer",
+            "format": "int32",
             "enum": [
                 0,
                 1,
@@ -1292,6 +1172,17 @@
                 }
             }
         },
+        "schema.BackendResponse": {
+            "type": "object",
+            "properties": {
+                "id": {
+                    "type": "string"
+                },
+                "status_url": {
+                    "type": "string"
+                }
+            }
+        },
         "schema.Choice": {
             "type": "object",
             "properties": {
@@ -1312,17 +1203,45 @@
                 }
             }
         },
-        "schema.DeleteAssistantResponse": {
+        "schema.Detection": {
             "type": "object",
             "properties": {
-                "deleted": {
-                    "type": "boolean"
-                },
-                "id": {
+                "class_name": {
                     "type": "string"
                 },
-                "object": {
+                "height": {
+                    "type": "number"
+                },
+                "width": {
+                    "type": "number"
+                },
+                "x": {
+                    "type": "number"
+                },
+                "y": {
+                    "type": "number"
+                }
+            }
+        },
+        "schema.DetectionRequest": {
+            "type": "object",
+            "properties": {
+                "image": {
                     "type": "string"
+                },
+                "model": {
+                    "type": "string"
+                }
+            }
+        },
+        "schema.DetectionResponse": {
+            "type": "object",
+            "properties": {
+                "detections": {
+                    "type": "array",
+                    "items": {
+                        "$ref": "#/definitions/schema.Detection"
+                    }
                 }
             }
         },
@@ -1346,35 +1265,6 @@
                 }
             }
         },
-        "schema.File": {
-            "type": "object",
-            "properties": {
-                "bytes": {
-                    "description": "Size of the file in bytes",
-                    "type": "integer"
-                },
-                "created_at": {
-                    "description": "The time at which the file was created",
-                    "type": "string"
-                },
-                "filename": {
-                    "description": "The name of the file",
-                    "type": "string"
-                },
-                "id": {
-                    "description": "Unique identifier for the file",
-                    "type": "string"
-                },
-                "object": {
-                    "description": "Type of the object (e.g., \"file\")",
-                    "type": "string"
-                },
-                "purpose": {
-                    "description": "The purpose of the file (e.g., \"fine-tune\", \"classifications\", etc.)",
-                    "type": "string"
-                }
-            }
-        },
         "schema.FunctionCall": {
             "type": "object",
             "properties": {
@@ -1494,20 +1384,6 @@
                 }
             }
         },
-        "schema.ListFiles": {
-            "type": "object",
-            "properties": {
-                "data": {
-                    "type": "array",
-                    "items": {
-                        "$ref": "#/definitions/schema.File"
-                    }
-                },
-                "object": {
-                    "type": "string"
-                }
-            }
-        },
         "schema.Message": {
             "type": "object",
             "properties": {
@@ -1603,6 +1479,13 @@
                     "description": "whisper",
                     "type": "string"
                 },
+                "files": {
+                    "description": "Multiple input images for img2img or inpainting",
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
                 "frequency_penalty": {
                     "type": "number"
                 },
@@ -1645,6 +1528,12 @@
                         "$ref": "#/definitions/schema.Message"
                     }
                 },
+                "metadata": {
+                    "type": "object",
+                    "additionalProperties": {
+                        "type": "string"
+                    }
+                },
                 "mode": {
                     "description": "Image (not supported by OpenAI)",
                     "type": "integer"
@@ -1677,6 +1566,16 @@
                 "quality": {
                     "type": "string"
                 },
+                "reasoning_effort": {
+                    "type": "string"
+                },
+                "ref_images": {
+                    "description": "Reference images for models that support them (e.g., Flux Kontext)",
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                },
                 "repeat_last_n": {
                     "type": "integer"
                 },
@@ -1916,6 +1815,37 @@
                     "type": "string"
                 }
             }
+        },
+        "services.GalleryOpStatus": {
+            "type": "object",
+            "properties": {
+                "deletion": {
+                    "description": "Deletion is true if the operation is a deletion",
+                    "type": "boolean"
+                },
+                "downloaded_size": {
+                    "type": "string"
+                },
+                "error": {},
+                "file_name": {
+                    "type": "string"
+                },
+                "file_size": {
+                    "type": "string"
+                },
+                "gallery_element_name": {
+                    "type": "string"
+                },
+                "message": {
+                    "type": "string"
+                },
+                "processed": {
+                    "type": "boolean"
+                },
+                "progress": {
+                    "type": "number"
+                }
+            }
         }
     },
     "securityDefinitions": {

swagger/swagger.yaml

@@ -57,6 +57,51 @@ definitions:
       uri:
         type: string
     type: object
+  gallery.GalleryBackend:
+    properties:
+      alias:
+        type: string
+      capabilities:
+        additionalProperties:
+          type: string
+        type: object
+      description:
+        type: string
+      files:
+        description: AdditionalFiles are used to add additional files to the model
+        items:
+          $ref: '#/definitions/gallery.File'
+        type: array
+      gallery:
+        allOf:
+        - $ref: '#/definitions/config.Gallery'
+        description: Gallery is a reference to the gallery which contains the model
+      icon:
+        type: string
+      installed:
+        description: Installed is used to indicate if the model is installed or not
+        type: boolean
+      license:
+        type: string
+      mirrors:
+        items:
+          type: string
+        type: array
+      name:
+        type: string
+      tags:
+        items:
+          type: string
+        type: array
+      uri:
+        type: string
+      url:
+        type: string
+      urls:
+        items:
+          type: string
+        type: array
+    type: object
   gallery.GalleryModel:
     properties:
       config_file:
@@ -100,26 +145,10 @@ definitions:
           type: string
         type: array
     type: object
-  services.GalleryOpStatus:
+  localai.GalleryBackend:
     properties:
-      deletion:
-        description: Deletion is true if the operation is a deletion
-        type: boolean
-      downloaded_size:
+      id:
         type: string
-      error: {}
-      file_name:
-        type: string
-      file_size:
-        type: string
-      gallery_model_name:
-        type: string
-      message:
-        type: string
-      processed:
-        type: boolean
-      progress:
-        type: number
     type: object
   localai.GalleryModel:
     properties:
@@ -128,8 +157,6 @@ definitions:
         description: config_file is read in the situation where URL is blank - and
           therefore this is a base config.
         type: object
-      config_url:
-        type: string
       description:
         type: string
       files:
@@ -168,92 +195,6 @@ definitions:
           type: string
         type: array
     type: object
-  openai.Assistant:
-    properties:
-      created:
-        description: The time at which the assistant was created.
-        type: integer
-      description:
-        description: The description of the assistant.
-        type: string
-      file_ids:
-        description: A list of file IDs attached to this assistant.
-        items:
-          type: string
-        type: array
-      id:
-        description: The unique identifier of the assistant.
-        type: string
-      instructions:
-        description: The system instructions that the assistant uses.
-        type: string
-      metadata:
-        additionalProperties:
-          type: string
-        description: Set of key-value pairs attached to the assistant.
-        type: object
-      model:
-        description: The model ID used by the assistant.
-        type: string
-      name:
-        description: The name of the assistant.
-        type: string
-      object:
-        description: Object type, which is "assistant".
-        type: string
-      tools:
-        description: A list of tools enabled on the assistant.
-        items:
-          $ref: '#/definitions/openai.Tool'
-        type: array
-    type: object
-  openai.AssistantRequest:
-    properties:
-      description:
-        type: string
-      file_ids:
-        items:
-          type: string
-        type: array
-      instructions:
-        type: string
-      metadata:
-        additionalProperties:
-          type: string
-        type: object
-      model:
-        type: string
-      name:
-        type: string
-      tools:
-        items:
-          $ref: '#/definitions/openai.Tool'
-        type: array
-    type: object
-  openai.DeleteStatus:
-    properties:
-      deleted:
-        type: boolean
-      id:
-        type: string
-      object:
-        type: string
-    type: object
-  openai.Tool:
-    properties:
-      type:
-        $ref: '#/definitions/openai.ToolType'
-    type: object
-  openai.ToolType:
-    enum:
-    - code_interpreter
-    - retrieval
-    - function
-    type: string
-    x-enum-varnames:
-    - CodeInterpreter
-    - Retrieval
-    - Function
   p2p.NodeData:
     properties:
       id:
@@ -271,6 +212,7 @@ definitions:
     properties:
       breakdown:
         additionalProperties:
+          format: int64
           type: integer
         type: object
       total:
@@ -289,6 +231,7 @@ definitions:
     - 1
     - 2
     - -1
+    format: int32
     type: integer
     x-enum-varnames:
     - StatusResponse_UNINITIALIZED
@@ -314,6 +257,13 @@ definitions:
       model:
         type: string
     type: object
+  schema.BackendResponse:
+    properties:
+      id:
+        type: string
+      status_url:
+        type: string
+    type: object
   schema.Choice:
     properties:
       delta:
@@ -327,14 +277,32 @@ definitions:
       text:
         type: string
     type: object
-  schema.DeleteAssistantResponse:
+  schema.Detection:
     properties:
-      deleted:
-        type: boolean
-      id:
+      class_name:
         type: string
-      object:
+      height:
+        type: number
+      width:
+        type: number
+      x:
+        type: number
+      "y":
+        type: number
+    type: object
+  schema.DetectionRequest:
+    properties:
+      image:
         type: string
+      model:
+        type: string
+    type: object
+  schema.DetectionResponse:
+    properties:
+      detections:
+        items:
+          $ref: '#/definitions/schema.Detection'
+        type: array
     type: object
   schema.ElevenLabsSoundGenerationRequest:
     properties:
@@ -349,28 +317,6 @@ definitions:
       text:
         type: string
     type: object
-  schema.File:
-    properties:
-      bytes:
-        description: Size of the file in bytes
-        type: integer
-      created_at:
-        description: The time at which the file was created
-        type: string
-      filename:
-        description: The name of the file
-        type: string
-      id:
-        description: Unique identifier for the file
-        type: string
-      object:
-        description: Type of the object (e.g., "file")
-        type: string
-      purpose:
-        description: The purpose of the file (e.g., "fine-tune", "classifications",
-          etc.)
-        type: string
-    type: object
   schema.FunctionCall:
     properties:
       arguments:
@@ -448,15 +394,6 @@ definitions:
       total_tokens:
         type: integer
     type: object
-  schema.ListFiles:
-    properties:
-      data:
-        items:
-          $ref: '#/definitions/schema.File'
-        type: array
-      object:
-        type: string
-    type: object
   schema.Message:
     properties:
       content:
@@ -519,6 +456,11 @@ definitions:
       file:
         description: whisper
         type: string
+      files:
+        description: Multiple input images for img2img or inpainting
+        items:
+          type: string
+        type: array
       frequency_penalty:
         type: number
       function_call:
@@ -549,6 +491,10 @@ definitions:
         items:
           $ref: '#/definitions/schema.Message'
         type: array
+      metadata:
+        additionalProperties:
+          type: string
+        type: object
       mode:
         description: Image (not supported by OpenAI)
         type: integer
@@ -572,6 +518,13 @@ definitions:
         description: Prompt is read only by completion/image API calls
       quality:
         type: string
+      reasoning_effort:
+        type: string
+      ref_images:
+        description: Reference images for models that support them (e.g., Flux Kontext)
+        items:
+          type: string
+        type: array
       repeat_last_n:
         type: integer
       repeat_penalty:
@@ -737,6 +690,27 @@ definitions:
       model:
         type: string
     type: object
+  services.GalleryOpStatus:
+    properties:
+      deletion:
+        description: Deletion is true if the operation is a deletion
+        type: boolean
+      downloaded_size:
+        type: string
+      error: {}
+      file_name:
+        type: string
+      file_size:
+        type: string
+      gallery_element_name:
+        type: string
+      message:
+        type: string
+      processed:
+        type: boolean
+      progress:
+        type: number
+    type: object
 info:
   contact:
     name: LocalAI
@@ -792,6 +766,83 @@ paths:
           $ref: '#/definitions/schema.BackendMonitorRequest'
       responses: {}
       summary: Backend monitor endpoint
+  /backends:
+    get:
+      responses:
+        "200":
+          description: Response
+          schema:
+            items:
+              $ref: '#/definitions/gallery.GalleryBackend'
+            type: array
+      summary: List all Backends
+  /backends/apply:
+    post:
+      parameters:
+      - description: query params
+        in: body
+        name: request
+        required: true
+        schema:
+          $ref: '#/definitions/localai.GalleryBackend'
+      responses:
+        "200":
+          description: Response
+          schema:
+            $ref: '#/definitions/schema.BackendResponse'
+      summary: Install backends to LocalAI.
+  /backends/available:
+    get:
+      responses:
+        "200":
+          description: Response
+          schema:
+            items:
+              $ref: '#/definitions/gallery.GalleryBackend'
+            type: array
+      summary: List all available Backends
+  /backends/delete/{name}:
+    post:
+      parameters:
+      - description: Backend name
+        in: path
+        name: name
+        required: true
+        type: string
+      responses:
+        "200":
+          description: Response
+          schema:
+            $ref: '#/definitions/schema.BackendResponse'
+      summary: delete backends from LocalAI.
+  /backends/galleries:
+    get:
+      responses:
+        "200":
+          description: Response
+          schema:
+            items:
+              $ref: '#/definitions/config.Gallery'
+            type: array
+      summary: List all Galleries
+  /backends/jobs:
+    get:
+      responses:
+        "200":
+          description: Response
+          schema:
+            additionalProperties:
+              $ref: '#/definitions/services.GalleryOpStatus'
+            type: object
+      summary: Returns all the jobs status progress
+  /backends/jobs/{uuid}:
+    get:
+      responses:
+        "200":
+          description: Response
+          schema:
+            $ref: '#/definitions/services.GalleryOpStatus'
+      summary: Returns the job status
   /metrics:
     get:
       parameters:
@@ -843,22 +894,6 @@ paths:
             $ref: '#/definitions/schema.GalleryResponse'
       summary: delete models to LocalAI.
   /models/galleries:
-    delete:
-      parameters:
-      - description: Gallery details
-        in: body
-        name: request
-        required: true
-        schema:
-          $ref: '#/definitions/config.Gallery'
-      responses:
-        "200":
-          description: Response
-          schema:
-            items:
-              $ref: '#/definitions/config.Gallery'
-            type: array
-      summary: removes a gallery from LocalAI
     get:
       responses:
         "200":
@@ -868,22 +903,6 @@ paths:
               $ref: '#/definitions/config.Gallery'
             type: array
       summary: List all Galleries
-    post:
-      parameters:
-      - description: Gallery details
-        in: body
-        name: request
-        required: true
-        schema:
-          $ref: '#/definitions/config.Gallery'
-      responses:
-        "200":
-          description: Response
-          schema:
-            items:
-              $ref: '#/definitions/config.Gallery'
-            type: array
-      summary: Adds a gallery in LocalAI
   /models/jobs:
     get:
       responses:
@@ -941,62 +960,6 @@ paths:
           schema:
             type: string
       summary: Generates audio from the input text.
-  /v1/assistants:
-    get:
-      parameters:
-      - description: Limit the number of assistants returned
-        in: query
-        name: limit
-        type: integer
-      - description: Order of assistants returned
-        in: query
-        name: order
-        type: string
-      - description: Return assistants created after the given ID
-        in: query
-        name: after
-        type: string
-      - description: Return assistants created before the given ID
-        in: query
-        name: before
-        type: string
-      responses:
-        "200":
-          description: Response
-          schema:
-            items:
-              $ref: '#/definitions/openai.Assistant'
-            type: array
-      summary: List available assistents
-    post:
-      parameters:
-      - description: query params
-        in: body
-        name: request
-        required: true
-        schema:
-          $ref: '#/definitions/openai.AssistantRequest'
-      responses:
-        "200":
-          description: Response
-          schema:
-            $ref: '#/definitions/openai.Assistant'
-      summary: Create an assistant with a model and instructions.
-  /v1/assistants/{assistant_id}:
-    delete:
-      responses:
-        "200":
-          description: Response
-          schema:
-            $ref: '#/definitions/schema.DeleteAssistantResponse'
-      summary: Delete assistents
-    get:
-      responses:
-        "200":
-          description: Response
-          schema:
-            $ref: '#/definitions/openai.Assistant'
-      summary: Get assistent data
   /v1/audio/speech:
     post:
       consumes:
@@ -1069,6 +1032,21 @@ paths:
           schema:
             $ref: '#/definitions/schema.OpenAIResponse'
       summary: Generate completions for a given prompt and model.
+  /v1/detection:
+    post:
+      parameters:
+      - description: query params
+        in: body
+        name: request
+        required: true
+        schema:
+          $ref: '#/definitions/schema.DetectionRequest'
+      responses:
+        "200":
+          description: Response
+          schema:
+            $ref: '#/definitions/schema.DetectionResponse'
+      summary: Detects objects in the input image.
   /v1/edits:
     post:
       parameters:
@@ -1100,37 +1078,6 @@ paths:
             $ref: '#/definitions/schema.OpenAIResponse'
       summary: Get a vector representation of a given input that can be easily consumed
         by machine learning models and algorithms.
-  /v1/files:
-    get:
-      responses:
-        "200":
-          description: Response
-          schema:
-            $ref: '#/definitions/schema.ListFiles'
-      summary: List files.
-  /v1/files/{file_id}:
-    delete:
-      responses:
-        "200":
-          description: Response
-          schema:
-            $ref: '#/definitions/openai.DeleteStatus'
-      summary: Delete a file.
-    get:
-      responses:
-        "200":
-          description: Response
-          schema:
-            $ref: '#/definitions/schema.File'
-      summary: Returns information about a specific file.
-  /v1/files/{file_id}/content:
-    get:
-      responses:
-        "200":
-          description: file
-          schema:
-            type: string
-      summary: Returns information about a specific file.
   /v1/images/generations:
     post:
       parameters: