docs: ⬆️ update docs version mudler/LocalAI (#6315)

⬆️ Update docs version mudler/LocalAI

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

.github/workflows/backend.yml

@@ -89,7 +89,7 @@ jobs:
             context: "./backend"
           - build-type: 'l4t'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/arm64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-l4t-diffusers'
@@ -187,7 +187,7 @@ jobs:
           # CUDA 12 builds
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-rerankers'
@@ -199,7 +199,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-llama-cpp'
@@ -211,7 +211,7 @@ jobs:
             context: "./"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-vllm'
@@ -223,7 +223,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-transformers'
@@ -235,7 +235,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-diffusers'
@@ -248,7 +248,7 @@ jobs:
           # CUDA 12 additional backends
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-kokoro'
@@ -260,7 +260,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-faster-whisper'
@@ -272,7 +272,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-coqui'
@@ -284,7 +284,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-bark'
@@ -296,7 +296,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-chatterbox'
@@ -578,7 +578,7 @@ jobs:
             context: "./"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/arm64'
             skip-drivers: 'true'
             tag-latest: 'auto'
@@ -615,7 +615,7 @@ jobs:
             context: "./"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-stablediffusion-ggml'
@@ -675,7 +675,7 @@ jobs:
             context: "./"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/arm64'
             skip-drivers: 'true'
             tag-latest: 'auto'
@@ -700,7 +700,7 @@ jobs:
             context: "./"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-whisper'
@@ -760,7 +760,7 @@ jobs:
             context: "./"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/arm64'
             skip-drivers: 'true'
             tag-latest: 'auto'
@@ -836,7 +836,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-rfdetr'
@@ -872,7 +872,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/arm64'
             skip-drivers: 'true'
             tag-latest: 'auto'
@@ -897,7 +897,7 @@ jobs:
             context: "./backend"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12-exllama2'

.github/workflows/image-pr.yml

@@ -36,7 +36,7 @@ jobs:
         include:
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'false'
             tag-suffix: '-gpu-nvidia-cuda-12'

.github/workflows/image.yml

@@ -91,7 +91,7 @@ jobs:
             aio: "-aio-gpu-nvidia-cuda-11"
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/amd64'
             tag-latest: 'auto'
             tag-suffix: '-gpu-nvidia-cuda-12'
@@ -144,7 +144,7 @@ jobs:
         include:
           - build-type: 'cublas'
             cuda-major-version: "12"
-            cuda-minor-version: "8"
+            cuda-minor-version: "0"
             platforms: 'linux/arm64'
             tag-latest: 'auto'
             tag-suffix: '-nvidia-l4t-arm64'

.github/workflows/localaibot_automerge.yml

@@ -6,7 +6,8 @@ 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

Dockerfile

@@ -18,7 +18,7 @@ FROM requirements AS requirements-drivers
 
 ARG BUILD_TYPE
 ARG CUDA_MAJOR_VERSION=12
-ARG CUDA_MINOR_VERSION=8
+ARG CUDA_MINOR_VERSION=0
 ARG SKIP_DRIVERS=false
 ARG TARGETARCH
 ARG TARGETVARIANT

Makefile

@@ -170,7 +170,7 @@ prepare-e2e:
 	mkdir -p $(TEST_DIR)
 	cp -rfv $(abspath ./tests/e2e-fixtures)/gpu.yaml $(TEST_DIR)/gpu.yaml
 	test -e $(TEST_DIR)/ggllm-test-model.bin || wget -q https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGUF/resolve/main/codellama-7b-instruct.Q2_K.gguf -O $(TEST_DIR)/ggllm-test-model.bin
-	docker build --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=8 -t localai-tests .
+	docker build --build-arg IMAGE_TYPE=core --build-arg BUILD_TYPE=$(BUILD_TYPE) --build-arg CUDA_MAJOR_VERSION=12 --build-arg CUDA_MINOR_VERSION=0 -t localai-tests .
 
 run-e2e-image:
 	ls -liah $(abspath ./tests/e2e-fixtures)

backend/README.md

@@ -111,7 +111,7 @@ docker build -f backend/Dockerfile.python \
   --build-arg BACKEND=transformers \
   --build-arg BUILD_TYPE=cublas12 \
   --build-arg CUDA_MAJOR_VERSION=12 \
-  --build-arg CUDA_MINOR_VERSION=8 \
+  --build-arg CUDA_MINOR_VERSION=0 \
   -t localai-backend-transformers .
 
 # Build Go backend

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=8ff206097c2bf3ca1c7aa95f9d6db779fc7bdd68
+LLAMA_VERSION?=f432d8d83e7407073634c5e4fd81a3d23a10827f
 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?=edea8a9c3cf0eb7676dcdb604991eb2f95c3d984
+WHISPER_CPP_VERSION?=44fa2f647cf2a6953493b21ab83b50d5f5dbc483
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
 

backend/python/diffusers/backend.py

@@ -66,11 +66,20 @@ 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
@@ -177,10 +186,11 @@ 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):
-                    if value.is_integer():
-                        value = int(value)
-                    else:
-                        value = float(value)
+                    value = float(value)
+                elif is_int(value):
+                    value = int(value)
+                elif value.lower() in ["true", "false"]:
+                    value = value.lower() == "true"
                 self.options[key] = value
 
             # From options, extract if present "torch_dtype" and set it to the appropriate type

backend/python/mlx-audio/backend.py

@@ -20,6 +20,21 @@ 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
@@ -32,14 +47,6 @@ 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.
@@ -80,11 +87,10 @@ 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 self._is_float(value):
-                    if float(value).is_integer():
-                        value = int(value)
-                    else:
-                        value = float(value)
+                if is_float(value):
+                    value = float(value)
+                elif is_int(value):
+                    value = int(value)
                 elif value.lower() in ["true", "false"]:
                     value = value.lower() == "true"
                     

backend/python/mlx-vlm/backend.py

@@ -21,6 +21,21 @@ 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
@@ -32,14 +47,6 @@ 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.
@@ -79,12 +86,10 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                     continue
                 key, value = opt.split(":", 1)  # Split only on first colon to handle values with colons
                 
-                # Convert numeric values to appropriate types
-                if self._is_float(value):
-                    if float(value).is_integer():
-                        value = int(value)
-                    else:
-                        value = float(value)
+                if is_float(value):
+                    value = float(value)
+                elif is_int(value):
+                    value = int(value)
                 elif value.lower() in ["true", "false"]:
                     value = value.lower() == "true"
                     

backend/python/mlx/backend.py

@@ -24,20 +24,27 @@ _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.
@@ -78,11 +85,10 @@ 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 self._is_float(value):
-                    if float(value).is_integer():
-                        value = int(value)
-                    else:
-                        value = float(value)
+                if is_float(value):
+                    value = float(value)
+                elif is_int(value):
+                    value = int(value)
                 elif value.lower() in ["true", "false"]:
                     value = value.lower() == "true"
                     

docs/data/version.json

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

gallery/index.yaml

@@ -2638,6 +2638,39 @@
     - 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"
@@ -15175,6 +15208,27 @@
     - 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"