WIP

.github/workflows/backend.yml

@@ -197,6 +197,18 @@ jobs:
             backend: "rerankers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-rerankers'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "rerankers"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -209,6 +221,18 @@ jobs:
             backend: "llama-cpp"
             dockerfile: "./backend/Dockerfile.llama-cpp"
             context: "./"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-llama-cpp'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "llama-cpp"
+            dockerfile: "./backend/Dockerfile.llama-cpp"
+            context: "./"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -221,6 +245,18 @@ jobs:
             backend: "vllm"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-vllm'
+            runs-on: 'arc-runner-set'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "vllm"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -233,6 +269,18 @@ jobs:
             backend: "transformers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-transformers'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "transformers"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -245,7 +293,19 @@ jobs:
             backend: "diffusers"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
-          # CUDA 12 additional backends
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-diffusers'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "diffusers"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
+          # CUDA additional backends
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -258,6 +318,18 @@ jobs:
             backend: "kokoro"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-kokoro'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "kokoro"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -270,6 +342,18 @@ jobs:
             backend: "faster-whisper"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-faster-whisper'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "faster-whisper"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -282,6 +366,18 @@ jobs:
             backend: "coqui"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-coqui'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "coqui"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -294,6 +390,18 @@ jobs:
             backend: "bark"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-bark'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "bark"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"
@@ -306,6 +414,18 @@ jobs:
             backend: "chatterbox"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-chatterbox'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "chatterbox"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           # hipblas builds
           - build-type: 'hipblas'
             cuda-major-version: ""
@@ -625,6 +745,18 @@ jobs:
             backend: "stablediffusion-ggml"
             dockerfile: "./backend/Dockerfile.golang"
             context: "./"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13-stablediffusion-ggml'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "stablediffusion-ggml"
+            dockerfile: "./backend/Dockerfile.golang"
+            context: "./"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -710,6 +842,18 @@ jobs:
             backend: "whisper"
             dockerfile: "./backend/Dockerfile.golang"
             context: "./"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-12-whisper'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "whisper"
+            dockerfile: "./backend/Dockerfile.golang"
+            context: "./"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -846,6 +990,18 @@ jobs:
             backend: "rfdetr"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-12-rfdetr'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "rfdetr"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"
@@ -907,6 +1063,18 @@ jobs:
             backend: "exllama2"
             dockerfile: "./backend/Dockerfile.python"
             context: "./backend"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-12-exllama2'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            backend: "exllama2"
+            dockerfile: "./backend/Dockerfile.python"
+            context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "11"
             cuda-minor-version: "7"

.github/workflows/image-pr.yml

@@ -34,6 +34,15 @@ jobs:
       fail-fast: false
       matrix:
         include:
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'false'
+            tag-suffix: '-gpu-nvidia-cuda-13'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            makeflags: "--jobs=3 --output-sync=target"
           - build-type: 'cublas'
             cuda-major-version: "12"
             cuda-minor-version: "0"

.github/workflows/image.yml

@@ -100,6 +100,17 @@ jobs:
             skip-drivers: 'false'
             makeflags: "--jobs=4 --output-sync=target"
             aio: "-aio-gpu-nvidia-cuda-12"
+          - build-type: 'cublas'
+            cuda-major-version: "13"
+            cuda-minor-version: "0"
+            platforms: 'linux/amd64'
+            tag-latest: 'auto'
+            tag-suffix: '-gpu-nvidia-cuda-13'
+            runs-on: 'ubuntu-latest'
+            base-image: "ubuntu:22.04"
+            skip-drivers: 'false'
+            makeflags: "--jobs=4 --output-sync=target"
+            aio: "-aio-gpu-nvidia-cuda-13"
           - build-type: 'vulkan'
             platforms: 'linux/amd64'
             tag-latest: 'auto'

.github/workflows/localaibot_automerge.yml

@@ -6,8 +6,7 @@ permissions:
   contents: write
   pull-requests: write
   packages: read
-  issues: write # for Homebrew/actions/post-comment
-  actions: write # to dispatch publish workflow
+
 jobs:
   dependabot:
     runs-on: ubuntu-latest

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=f432d8d83e7407073634c5e4fd81a3d23a10827f
+LLAMA_VERSION?=8ff206097c2bf3ca1c7aa95f9d6db779fc7bdd68
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/go/whisper/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=44fa2f647cf2a6953493b21ab83b50d5f5dbc483
+WHISPER_CPP_VERSION?=edea8a9c3cf0eb7676dcdb604991eb2f95c3d984
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
 

backend/python/diffusers/backend.py

@@ -66,20 +66,11 @@ from diffusers.schedulers import (
 )
 
 def is_float(s):
-    """Check if a string can be converted to float."""
     try:
         float(s)
         return True
     except ValueError:
         return False
-def is_int(s):
-    """Check if a string can be converted to int."""
-    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
@@ -186,11 +177,10 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 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)
-                elif value.lower() in ["true", "false"]:
-                    value = value.lower() == "true"
+                    if value.is_integer():
+                        value = int(value)
+                    else:
+                        value = float(value)
                 self.options[key] = value
 
             # From options, extract if present "torch_dtype" and set it to the appropriate type

backend/python/mlx-audio/backend.py

@@ -20,21 +20,6 @@ import soundfile as sf
 import numpy as np
 import uuid
 
-def is_float(s):
-    """Check if a string can be converted to float."""
-    try:
-        float(s)
-        return True
-    except ValueError:
-        return False
-def is_int(s):
-    """Check if a string can be converted to int."""
-    try:
-        int(s)
-        return True
-    except ValueError:
-        return False
-
 _ONE_DAY_IN_SECONDS = 60 * 60 * 24
 
 # If MAX_WORKERS are specified in the environment use it, otherwise default to 1
@@ -47,6 +32,14 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
     This backend provides TTS (Text-to-Speech) functionality using MLX-Audio.
     """
 
+    def _is_float(self, s):
+        """Check if a string can be converted to float."""
+        try:
+            float(s)
+            return True
+        except ValueError:
+            return False
+
     def Health(self, request, context):
         """
         Returns a health check message.
@@ -87,10 +80,11 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 key, value = opt.split(":", 1)  # Split only on first colon to handle values with colons
                 
                 # Convert numeric values to appropriate types
-                if is_float(value):
-                    value = float(value)
-                elif is_int(value):
-                    value = int(value)
+                if self._is_float(value):
+                    if float(value).is_integer():
+                        value = int(value)
+                    else:
+                        value = float(value)
                 elif value.lower() in ["true", "false"]:
                     value = value.lower() == "true"
                     

backend/python/mlx-vlm/backend.py

@@ -21,21 +21,6 @@ import io
 from PIL import Image
 import tempfile
 
-def is_float(s):
-    """Check if a string can be converted to float."""
-    try:
-        float(s)
-        return True
-    except ValueError:
-        return False
-def is_int(s):
-    """Check if a string can be converted to int."""
-    try:
-        int(s)
-        return True
-    except ValueError:
-        return False
-
 _ONE_DAY_IN_SECONDS = 60 * 60 * 24
 
 # If MAX_WORKERS are specified in the environment use it, otherwise default to 1
@@ -47,6 +32,14 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
     A gRPC servicer that implements the Backend service defined in backend.proto.
     """
 
+    def _is_float(self, s):
+        """Check if a string can be converted to float."""
+        try:
+            float(s)
+            return True
+        except ValueError:
+            return False
+
     def Health(self, request, context):
         """
         Returns a health check message.
@@ -86,10 +79,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                     continue
                 key, value = opt.split(":", 1)  # Split only on first colon to handle values with colons
                 
-                if is_float(value):
-                    value = float(value)
-                elif is_int(value):
-                    value = int(value)
+                # Convert numeric values to appropriate types
+                if self._is_float(value):
+                    if float(value).is_integer():
+                        value = int(value)
+                    else:
+                        value = float(value)
                 elif value.lower() in ["true", "false"]:
                     value = value.lower() == "true"
                     

backend/python/mlx/backend.py

@@ -24,27 +24,20 @@ _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'))
 
-def is_float(s):
-    """Check if a string can be converted to float."""
-    try:
-        float(s)
-        return True
-    except ValueError:
-        return False
-def is_int(s):
-    """Check if a string can be converted to int."""
-    try:
-        int(s)
-        return True
-    except ValueError:
-        return False
-
 # Implement the BackendServicer class with the service methods
 class BackendServicer(backend_pb2_grpc.BackendServicer):
     """
     A gRPC servicer that implements the Backend service defined in backend.proto.
     """
 
+    def _is_float(self, s):
+        """Check if a string can be converted to float."""
+        try:
+            float(s)
+            return True
+        except ValueError:
+            return False
+
     def Health(self, request, context):
         """
         Returns a health check message.
@@ -85,10 +78,11 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                 key, value = opt.split(":", 1)  # Split only on first colon to handle values with colons
                 
                 # Convert numeric values to appropriate types
-                if is_float(value):
-                    value = float(value)
-                elif is_int(value):
-                    value = int(value)
+                if self._is_float(value):
+                    if float(value).is_integer():
+                        value = int(value)
+                    else:
+                        value = float(value)
                 elif value.lower() in ["true", "false"]:
                     value = value.lower() == "true"
                     

docs/data/version.json

@@ -1,3 +1,3 @@
 {
-  "version": "v3.5.3"
+  "version": "v3.5.0"
 }

gallery/index.yaml

@@ -2638,39 +2638,6 @@
     - filename: Alibaba-NLP_Tongyi-DeepResearch-30B-A3B-Q4_K_M.gguf
       sha256: 1afefb3b369ea2de191f24fe8ea22cbbb7b412357902f27bd81d693dde35c2d9
       uri: huggingface://bartowski/Alibaba-NLP_Tongyi-DeepResearch-30B-A3B-GGUF/Alibaba-NLP_Tongyi-DeepResearch-30B-A3B-Q4_K_M.gguf
-- !!merge <<: *qwen3
-  name: "impish_qwen_14b-1m"
-  icon: https://huggingface.co/SicariusSicariiStuff/Impish_QWEN_14B-1M/resolve/main/Images/Impish_Qwen_14B.png
-  urls:
-    - https://huggingface.co/SicariusSicariiStuff/Impish_QWEN_14B-1M
-    - https://huggingface.co/mradermacher/Impish_QWEN_14B-1M-GGUF
-  description: |
-    Supreme context One million tokens to play with.
-    Strong Roleplay internet RP format lovers will appriciate it, medium size paragraphs.
-    Qwen smarts built-in, but naughty and playful Maybe it's even too naughty.
-    VERY compliant with low censorship.
-    VERY high IFeval for a 14B RP model: 78.68.
-  overrides:
-    parameters:
-      model: Impish_QWEN_14B-1M.Q4_K_M.gguf
-  files:
-    - filename: Impish_QWEN_14B-1M.Q4_K_M.gguf
-      sha256: d326f2b8f05814ea3943c82498f0cd3cde64859cf03f532855c87fb94b0da79e
-      uri: huggingface://mradermacher/Impish_QWEN_14B-1M-GGUF/Impish_QWEN_14B-1M.Q4_K_M.gguf
-- !!merge <<: *qwen3
-  name: "aquif-3.5-a4b-think"
-  urls:
-    - https://huggingface.co/aquif-ai/aquif-3.5-A4B-Think
-    - https://huggingface.co/QuantFactory/aquif-3.5-A4B-Think-GGUF
-  description: |
-    The aquif-3.5 series is the successor to aquif-3, featuring a simplified naming scheme, expanded Mixture of Experts (MoE) options, and across-the-board performance improvements. This release streamlines model selection while delivering enhanced capabilities across reasoning, multilingual support, and general intelligence tasks.
-  overrides:
-    parameters:
-      model: aquif-3.5-A4B-Think.Q4_K_M.gguf
-  files:
-    - filename: aquif-3.5-A4B-Think.Q4_K_M.gguf
-      sha256: 1650b72ae1acf12b45a702f2ff5f47205552e494f0d910e81cbe40dfba55a6b9
-      uri: huggingface://QuantFactory/aquif-3.5-A4B-Think-GGUF/aquif-3.5-A4B-Think.Q4_K_M.gguf
 - &gemma3
   url: "github:mudler/LocalAI/gallery/gemma.yaml@master"
   name: "gemma-3-27b-it"
@@ -15208,27 +15175,6 @@
     - filename: Impish_Longtail_12B-Q4_K_M.gguf
       sha256: 2cf0cacb65d71cfc5b4255f3273ad245bbcb11956a0f9e3aaa0e739df57c90df
       uri: huggingface://SicariusSicariiStuff/Impish_Longtail_12B_GGUF/Impish_Longtail_12B-Q4_K_M.gguf
-- !!merge <<: *mistral03
-  name: "mistralai_magistral-small-2509"
-  urls:
-    - https://huggingface.co/mistralai/Magistral-Small-2509
-    - https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF
-  description: |
-    Magistral Small 1.2
-    Building upon Mistral Small 3.2 (2506), with added reasoning capabilities, undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters.
-
-    Magistral Small can be deployed locally, fitting within a single RTX 4090 or a 32GB RAM MacBook once quantized.
-
-    Learn more about Magistral in our blog post.
-
-    The model was presented in the paper Magistral.
-  overrides:
-    parameters:
-      model: mistralai_Magistral-Small-2509-Q4_K_M.gguf
-  files:
-    - filename: mistralai_Magistral-Small-2509-Q4_K_M.gguf
-      sha256: 1d638bc931de30d29fc73ad439206ff185f76666a096e7ad723866a20f78728d
-      uri: huggingface://bartowski/mistralai_Magistral-Small-2509-GGUF/mistralai_Magistral-Small-2509-Q4_K_M.gguf
 - &mudler
   url: "github:mudler/LocalAI/gallery/mudler.yaml@master" ### START mudler's LocalAI specific-models
   name: "LocalAI-llama3-8b-function-call-v0.2"