[pull] master from mudler:master

.docker/llama-cpp-build-target.sh

@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+arch=${1:?target architecture is required}
+build_type=${2-}
+
+# GPU arm64 base images do not consistently provide the gcc-14 toolchain needed
+# to compile ggml's armv9.2 CPU variants. Keep their portable fallback until the
+# builder images can supply that compiler.
+if [ "$arch" = "arm64" ] && [ -n "$build_type" ]; then
+  echo llama-cpp-fallback
+else
+  echo llama-cpp-cpu-all
+fi

.docker/llama-cpp-compile.sh

@@ -18,10 +18,12 @@ if [[ -n "${CUDA_DOCKER_ARCH:-}" ]]; then
 fi
 
 cd /LocalAI/backend/cpp/llama-cpp
-if [ -z "${BUILD_TYPE:-}" ]; then
-  # Pure CPU image (BUILD_TYPE empty): one build with ggml CPU_ALL_VARIANTS replaces the
-  # per-microarch binaries (x86: avx/avx2/avx512/fallback; arm64: armv8.x/armv9.x). ggml
-  # dlopens the best libggml-cpu-*.so at runtime by probing host CPU features.
+BUILD_TARGET=$(/LocalAI/.docker/llama-cpp-build-target.sh "${TARGETARCH}" "${BUILD_TYPE:-}")
+if [ "$BUILD_TARGET" = "llama-cpp-cpu-all" ]; then
+  # One build with ggml CPU_ALL_VARIANTS replaces the per-microarch binaries (x86:
+  # avx/avx2/avx512/fallback; arm64: armv8.x/armv9.x). BUILD_TYPE remains in the
+  # environment, so GPU builds retain their accelerator backend while ggml dlopens the
+  # best CPU library when work is offloaded to the host.
   #
   # arm64: the CPU_ALL_VARIANTS table includes armv9.2 SME variants whose -march=...+sme is
   # rejected by the Ubuntu 24.04 default gcc-13. gcc-14 accepts it, so build the arm64
@@ -35,14 +37,8 @@ if [ -z "${BUILD_TYPE:-}" ]; then
     apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
     export CC=gcc-14 CXX=g++-14
   fi
-  make llama-cpp-cpu-all
-else
-  # GPU build (cublas/hipblas/sycl/vulkan/...): the accelerator does the compute, so a
-  # single fallback CPU build is enough - no per-microarch CPU variants needed. (This also
-  # keeps the heavy GPU backend compile from also building the whole CPU variant matrix,
-  # and avoids the gcc-14 apt step on GPU base images such as nvidia l4t.)
-  make llama-cpp-fallback
 fi
+make "$BUILD_TARGET"
 make llama-cpp-grpc
 make llama-cpp-rpc-server
 

backend/cpp/bonsai/Makefile

@@ -1,7 +1,7 @@
 
 # Pinned to the HEAD of the `prism` branch on https://github.com/PrismML-Eng/llama.cpp.
 # Auto-bumped nightly by .github/workflows/bump_deps.yaml.
-BONSAI_VERSION?=7529fdaaf99ffdc5ca71ace9c7409a56b27ad92f
+BONSAI_VERSION?=4dd165625bb6c020285eec8b342af25cf60233dd
 LLAMA_REPO?=https://github.com/PrismML-Eng/llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/run.sh

@@ -12,10 +12,10 @@ grep -e "flags" /proc/cpuinfo | head -1
 
 BINARY=llama-cpp-fallback
 
-# CPU images (x86, arm64, darwin) ship a single llama-cpp-cpu-all built with ggml
+# CPU images and x86 GPU images ship a single llama-cpp-cpu-all built with ggml
 # CPU_ALL_VARIANTS: ggml's backend registry dlopens the best libggml-cpu-*.so for this
-# host, so no shell-side AVX probing. GPU images (cublas/sycl/vulkan/hipblas) ship only
-# llama-cpp-fallback (the accelerator does the compute), so fall back to it when absent.
+# host, so no shell-side AVX probing. GPU arm64 images still ship llama-cpp-fallback
+# until their builder toolchains support ggml's complete arm variant matrix.
 if [ -e "$CURDIR"/llama-cpp-cpu-all ]; then
 	BINARY=llama-cpp-cpu-all
 fi
@@ -76,4 +76,4 @@ echo "Using binary: $BINARY"
 exec "$CURDIR"/$BINARY "$@"
 
 # We should never reach this point, however just in case we do, run fallback
-exec "$CURDIR"/llama-cpp-fallback "$@"
+exec "$CURDIR"/llama-cpp-fallback "$@"

backend/cpp/turboquant/Makefile

@@ -1,7 +1,7 @@
 
 # Pinned to the HEAD of feature/turboquant-kv-cache on https://github.com/TheTom/llama-cpp-turboquant.
 # Auto-bumped nightly by .github/workflows/bump_deps.yaml.
-TURBOQUANT_VERSION?=c26cbdffcf6fc9b7430cd6b117757e9a3f70b7ea
+TURBOQUANT_VERSION?=8a891f4b566efdbd3cea92fafee3227a0a267683
 LLAMA_REPO?=https://github.com/TheTom/llama-cpp-turboquant
 
 CMAKE_ARGS?=

core/gallery/importers/mlx.go

@@ -3,6 +3,7 @@ package importers
 import (
 	"encoding/json"
 	"path/filepath"
+	"slices"
 	"strings"
 
 	"github.com/mudler/LocalAI/core/config"
@@ -31,7 +32,7 @@ func (i *MLXImporter) Match(details Details) bool {
 	}
 
 	b, ok := preferencesMap["backend"].(string)
-	if ok && b == "mlx" || b == "mlx-vlm" {
+	if ok && slices.Contains([]string{"mlx", "mlx-vlm", "mlx-audio"}, b) {
 		return true
 	}
 
@@ -71,27 +72,40 @@ func (i *MLXImporter) Import(details Details) (gallery.ModelConfig, error) {
 	// (issue #10269). Send them to the mlx-vlm backend, which applies the
 	// processor-aware chat template.
 	backend := "mlx"
-	if details.HuggingFace != nil && details.HuggingFace.PipelineTag == "image-text-to-text" {
-		backend = "mlx-vlm"
+	usecases := []string{config.UsecaseChat}
+	useTokenizerTemplate := true
+	if details.HuggingFace != nil {
+		switch details.HuggingFace.PipelineTag {
+		case "image-text-to-text":
+			backend = "mlx-vlm"
+		case "text-to-speech":
+			backend = "mlx-audio"
+			usecases = []string{config.UsecaseTTS}
+			useTokenizerTemplate = false
+		}
 	}
 	// An explicit backend preference always wins.
 	b, ok := preferencesMap["backend"].(string)
 	if ok {
 		backend = b
+		if backend == "mlx-audio" {
+			usecases = []string{config.UsecaseTTS}
+			useTokenizerTemplate = false
+		}
 	}
 
 	modelConfig := config.ModelConfig{
 		Name:                name,
 		Description:         description,
-		KnownUsecaseStrings: []string{config.UsecaseChat},
+		KnownUsecaseStrings: usecases,
 		Backend:             backend,
 		PredictionOptions: schema.PredictionOptions{
 			BasicModelRequest: schema.BasicModelRequest{
 				Model: LocalModelPath(details.URI),
 			},
 		},
 		TemplateConfig: config.TemplateConfig{
-			UseTokenizerTemplate: true,
+			UseTokenizerTemplate: useTokenizerTemplate,
 		},
 	}
 

core/gallery/importers/mlx_test.go

@@ -48,6 +48,16 @@ var _ = Describe("MLXImporter", func() {
 			Expect(result).To(BeTrue())
 		})
 
+		It("should match when backend preference is mlx-audio", func() {
+			preferences := json.RawMessage(`{"backend": "mlx-audio"}`)
+			details := importers.Details{
+				URI:         "https://example.com/model",
+				Preferences: preferences,
+			}
+
+			Expect(importer.Match(details)).To(BeTrue())
+		})
+
 		It("should not match when URI does not contain mlx-community/ and no backend preference", func() {
 			details := importers.Details{
 				URI: "https://huggingface.co/other-org/test-model",
@@ -123,6 +133,21 @@ var _ = Describe("MLXImporter", func() {
 			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: mlx-vlm"))
 		})
 
+		It("should configure explicit mlx-audio imports for text-to-speech", func() {
+			preferences := json.RawMessage(`{"backend": "mlx-audio"}`)
+			details := importers.Details{
+				URI:         "https://huggingface.co/mlx-community/Kokoro-82M-4bit",
+				Preferences: preferences,
+			}
+
+			modelConfig, err := importer.Import(details)
+
+			Expect(err).ToNot(HaveOccurred())
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: mlx-audio"))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("- tts"))
+			Expect(modelConfig.ConfigFile).ToNot(ContainSubstring("use_tokenizer_template: true"))
+		})
+
 		It("should auto-route vision-language models to the mlx-vlm backend", func() {
 			// gemma-4 E4B and similar VLMs declare pipeline_tag
 			// "image-text-to-text" on HuggingFace. The text-only mlx-lm
@@ -143,6 +168,23 @@ var _ = Describe("MLXImporter", func() {
 			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: mlx-vlm"))
 		})
 
+		It("should auto-route text-to-speech models to the mlx-audio backend", func() {
+			details := importers.Details{
+				URI: "https://huggingface.co/mlx-community/Kokoro-82M-4bit",
+				HuggingFace: &hfapi.ModelDetails{
+					ModelID:     "mlx-community/Kokoro-82M-4bit",
+					PipelineTag: "text-to-speech",
+				},
+			}
+
+			modelConfig, err := importer.Import(details)
+
+			Expect(err).ToNot(HaveOccurred())
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: mlx-audio"))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("- tts"))
+			Expect(modelConfig.ConfigFile).ToNot(ContainSubstring("use_tokenizer_template: true"))
+		})
+
 		It("should keep text-only models on the plain mlx backend", func() {
 			details := importers.Details{
 				URI: "https://huggingface.co/mlx-community/Llama-3.2-1B-Instruct-4bit",

core/http/endpoints/localai/backend.go

@@ -38,6 +38,7 @@ var knownPrefOnlyBackends = []schema.KnownBackend{
 	{Name: "whisperx", Modality: "asr", AutoDetect: false, Description: "WhisperX transcription (preference-only)"},
 	{Name: "crispasr", Modality: "asr", AutoDetect: false, Description: "CrispASR multi-architecture transcription (preference-only)"},
 	// TTS
+	{Name: "mlx-audio", Modality: "tts", AutoDetect: false, Description: "MLX-Audio text-to-speech models (auto-detected; pref-only fallback)"},
 	{Name: "kokoros", Modality: "tts", AutoDetect: false, Description: "Kokoros TTS (preference-only)"},
 	{Name: "qwen-tts", Modality: "tts", AutoDetect: false, Description: "Qwen TTS (preference-only)"},
 	{Name: "qwen3-tts-cpp", Modality: "tts", AutoDetect: false, Description: "Qwen3 TTS C++ (preference-only)"},

core/http/endpoints/localai/backend_test.go

@@ -152,6 +152,7 @@ var _ = Describe("Backend Endpoints", func() {
 			expectPrefOnly("tinygrad", "text")
 			expectPrefOnly("trl", "text")
 			expectPrefOnly("mlx-vlm", "text")
+			expectPrefOnly("mlx-audio", "tts")
 			expectPrefOnly("whisperx", "asr")
 			expectPrefOnly("crispasr", "asr")
 			expectPrefOnly("kokoros", "tts")

docs/content/getting-started/models.md

@@ -80,6 +80,12 @@ The WebUI provides a powerful model import interface that supports both simple a
    - Custom preferences
 5. Click "Import Model" to start the import process
 
+Repositories under `mlx-community` are imported with the native MLX backend.
+LocalAI uses Hugging Face's pipeline metadata to select `mlx-vlm` for
+vision-language models and `mlx-audio` for text-to-speech models; other MLX
+repositories use `mlx`. An explicit backend selection in the import form always
+overrides this automatic routing.
+
 ### Advanced Import Mode
 
 For full control over model configuration: