fix(backends): darwin/metal support across purego Go backends

The parakeet-cpp fix in the previous commit was an instance of a bug
shared by nearly every purego/dlopen Go backend: the dlopen target was
hardcoded to a .so name and run.sh exported only LD_LIBRARY_PATH, so the
backend panicked at startup on macOS/Apple-Metal nodes (dyld needs the
.dylib name and DYLD_LIBRARY_PATH). voxtral was the only backend handling
this correctly.

Apply the same four-layer fix (mirroring backend/go/voxtral) to the
remaining affected backends:

  whisper, sherpa-onnx, ced, stablediffusion-ggml, vibevoice-cpp,
  qwen3-tts-cpp, omnivoice-cpp, crispasr, acestep-cpp, locate-anything-cpp,
  depth-anything-cpp, rfdetr-cpp, sam3-cpp, localvqe

Per backend:
- main.go (sherpa-onnx: backend.go, two libraries): default the dlopen
  target to the .dylib on darwin (runtime.GOOS), .so elsewhere; the
  existing <BACKEND>_LIBRARY env override still wins.
- run.sh: on Darwin set DYLD_LIBRARY_PATH and point <BACKEND>_LIBRARY at
  the packaged .dylib; keep LD_LIBRARY_PATH + the Linux CPU-variant
  (avx/avx2/avx512) selection unchanged in the else branch.
- package.sh: also bundle the .dylib and stop hard-failing when no .so is
  present (the macOS case).
- Makefile: also stage the built .dylib.

Notes:
- stablediffusion-ggml and acestep-cpp build their lib as a CMake MODULE,
  which emits .so (not .dylib) on macOS; run.sh prefers .dylib and falls
  back to .so so both layouts work.
- sherpa-onnx was already partly darwin-aware (Makefile/package.sh); only
  run.sh and the two dlopen defaults needed fixing.

Linux behavior is unchanged. Verified gofmt-clean and
`CGO_ENABLED=0 go build` for every backend.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

.docker/llama-cpp-compile.sh

@@ -17,25 +17,19 @@ if [[ -n "${CUDA_DOCKER_ARCH:-}" ]]; then
   rm -rf /LocalAI/backend/cpp/llama-cpp-*-build
 fi
 
-cd /LocalAI/backend/cpp/llama-cpp
-if [ "${BUILD_TYPE}" = "hipblas" ]; then
-  # ROCm: the GPU does the compute, so a single fallback CPU build is enough.
+if [ "${TARGETARCH}" = "arm64" ] || [ "${BUILD_TYPE}" = "hipblas" ]; then
+  cd /LocalAI/backend/cpp/llama-cpp
   make llama-cpp-fallback
+  make llama-cpp-grpc
+  make llama-cpp-rpc-server
 else
-  # arm64: ggml's CPU_ALL_VARIANTS table includes armv9.2 SME variants whose
-  # -march=...+sme is rejected by the Ubuntu 24.04 default gcc-13. gcc-14 accepts it, so
-  # build the arm64 variants with gcc-14 (the host never *selects* SME unless it has it,
-  # but every variant must still compile).
-  if [ "${TARGETARCH}" = "arm64" ]; then
-    apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
-    export CC=gcc-14 CXX=g++-14
-  fi
-  # x86 and arm64: 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.
-  make llama-cpp-cpu-all
+  cd /LocalAI/backend/cpp/llama-cpp
+  make llama-cpp-avx
+  make llama-cpp-avx2
+  make llama-cpp-avx512
+  make llama-cpp-fallback
+  make llama-cpp-grpc
+  make llama-cpp-rpc-server
 fi
-make llama-cpp-grpc
-make llama-cpp-rpc-server
 
 ccache -s || true

.docker/turboquant-compile.sh

@@ -19,19 +19,17 @@ fi
 
 cd /LocalAI/backend/cpp/turboquant
 
-if [ "${BUILD_TYPE}" = "hipblas" ]; then
-  # ROCm: single fallback CPU build (GPU does the compute).
+if [ "${TARGETARCH}" = "arm64" ] || [ "${BUILD_TYPE}" = "hipblas" ]; then
   make turboquant-fallback
+  make turboquant-grpc
+  make turboquant-rpc-server
 else
-  # arm64: the CPU_ALL_VARIANTS armv9.2 SME variants need gcc-14 (gcc-13 rejects +sme).
-  if [ "${TARGETARCH}" = "arm64" ]; then
-    apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
-    export CC=gcc-14 CXX=g++-14
-  fi
-  # x86 and arm64: one ggml CPU_ALL_VARIANTS build replaces the per-microarch binaries.
-  make turboquant-cpu-all
+  make turboquant-avx
+  make turboquant-avx2
+  make turboquant-avx512
+  make turboquant-fallback
+  make turboquant-grpc
+  make turboquant-rpc-server
 fi
-make turboquant-grpc
-make turboquant-rpc-server
 
 ccache -s || true

backend/cpp/llama-cpp/CMakeLists.txt

@@ -50,13 +50,8 @@ add_custom_command(
         "${hw_proto}"
       DEPENDS "${hw_proto}")
 
-# hw_grpc_proto: force STATIC. Under the CPU_ALL_VARIANTS build BUILD_SHARED_LIBS=ON
-# (ggml/llama become shared), which would otherwise make this glue library a DSO. As a
-# DSO it references the hidden-visibility symbols in the static libprotobuf.a, which the
-# linker cannot satisfy ("hidden symbol ... in libprotobuf.a is referenced by DSO").
-# Keeping it STATIC links protobuf/gRPC directly into the grpc-server executable while
-# only ggml/llama stay shared. No effect on the static variants (already BUILD_SHARED_LIBS=OFF).
-add_library(hw_grpc_proto STATIC
+# hw_grpc_proto
+add_library(hw_grpc_proto
   ${hw_grpc_srcs}
   ${hw_grpc_hdrs}
   ${hw_proto_srcs}

backend/cpp/llama-cpp/Makefile

@@ -10,16 +10,8 @@ TARGET?=--target grpc-server
 JOBS?=$(shell nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 1)
 ARCH?=$(shell uname -m)
 
-# Shared libs default to OFF: we link static gRPC and the avx/avx2/avx512/fallback
-# variants are fully static. The CPU_ALL_VARIANTS build flips SHARED_LIBS=ON (ggml/llama
-# become shared so the dynamic CPU backends work; gRPC stays static via its imported
-# targets). SHARED_LIBS is a make variable, not an appended -D, so it survives the
-# recursive sub-make into the VARIANT build dir (which re-parses this Makefile) instead
-# of being re-clobbered by a second -DBUILD_SHARED_LIBS=OFF. EXTRA_CMAKE_ARGS is the hook
-# the CPU_ALL_VARIANTS target uses to inject -DGGML_BACKEND_DL/-DGGML_CPU_ALL_VARIANTS.
-SHARED_LIBS?=OFF
-EXTRA_CMAKE_ARGS?=
-CMAKE_ARGS+=-DBUILD_SHARED_LIBS=$(SHARED_LIBS) -DLLAMA_CURL=OFF $(EXTRA_CMAKE_ARGS)
+# Disable Shared libs as we are linking on static gRPC and we can't mix shared and static
+CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF -DLLAMA_CURL=OFF
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
 ifeq ($(NATIVE),false)
@@ -128,30 +120,6 @@ llama-cpp-fallback: llama.cpp
 	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) VARIANT="llama-cpp-fallback-build" build-llama-cpp-grpc-server
 	cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-fallback-build/grpc-server llama-cpp-fallback
 
-# Single-build CPU backend using ggml's CPU_ALL_VARIANTS. Produces ONE grpc-server
-# plus a set of dlopen-able libggml-cpu-*.so (sandybridge/haswell/skylakex/...) that
-# ggml's backend registry selects from at runtime by probing host CPU features.
-# Replaces the avx/avx2/avx512/fallback multi-binary build on x86.
-#
-# CPU_ALL_VARIANTS requires GGML_BACKEND_DL, which requires BUILD_SHARED_LIBS=ON, so we
-# pass SHARED_LIBS=ON and the DL flags as make variables (NOT pre-expanded into the
-# CMAKE_ARGS env string): command-line make variables propagate through every recursive
-# sub-make, so the deepest VARIANT-dir build computes BUILD_SHARED_LIBS=ON consistently.
-# Only ggml/llama go shared - gRPC is found via its static imported targets, so the
-# grpc-server binary keeps static gRPC and only dynamically links ggml.
-#
-# TARGET adds "ggml": the per-microarch backends are runtime-dlopened, not link deps of
-# grpc-server, so they only build because each is an add_dependencies() of the ggml target.
-llama-cpp-cpu-all: llama.cpp
-	cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build
-	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build purge
-	$(info ${GREEN}I llama-cpp build info:cpu-all-variants${RESET})
-	$(MAKE) SHARED_LIBS=ON EXTRA_CMAKE_ARGS="-DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON" TARGET="--target grpc-server --target ggml" VARIANT="llama-cpp-cpu-all-build" build-llama-cpp-grpc-server
-	cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build/grpc-server llama-cpp-cpu-all
-	rm -rf ggml-shared-libs && mkdir -p ggml-shared-libs
-	find $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build/llama.cpp/build \( -name '*.so*' -o -name '*.dylib' \) -exec cp -av {} ggml-shared-libs/ \;
-	@echo "Collected ggml shared backends:" && ls -la ggml-shared-libs/
-
 llama-cpp-grpc: llama.cpp
 	cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build purge

backend/cpp/llama-cpp/package.sh

@@ -14,22 +14,6 @@ mkdir -p $CURDIR/package/lib
 cp -avrf $CURDIR/llama-cpp-* $CURDIR/package/
 cp -rfv $CURDIR/run.sh $CURDIR/package/
 
-# Bundle the ggml shared backends produced by the CPU_ALL_VARIANTS build (libggml-base.so,
-# libggml.so, libllama.so and the per-microarch libggml-cpu-*.so), all into package/lib.
-#
-# Two distinct resolution mechanisms both land here:
-#   - NEEDED deps (libggml-base/libggml/libllama): resolved by the dynamic linker via the
-#     LD_LIBRARY_PATH=$CURDIR/lib that run.sh exports.
-#   - The per-microarch libggml-cpu-*.so are NOT linked; ggml *discovers* them at runtime by
-#     scanning the executable's own directory (readlink /proc/self/exe). run.sh launches via
-#     the bundled $CURDIR/lib/ld.so, so /proc/self/exe -> .../lib/ld.so and ggml scans lib/.
-#     That is why the variants must sit in lib/ (next to ld.so), not just on the link path.
-# No-op on builds (arm64/darwin) that don't produce the all-variants set.
-if [ -d "$CURDIR/ggml-shared-libs" ]; then
-    echo "Bundling ggml shared backends (CPU_ALL_VARIANTS)..."
-    cp -avf $CURDIR/ggml-shared-libs/*.so* $CURDIR/package/lib/
-fi
-
 # Detect architecture and copy appropriate libraries
 if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
     # x86_64 architecture

backend/cpp/llama-cpp/run.sh

@@ -12,11 +12,26 @@ grep -e "flags" /proc/cpuinfo | head -1
 
 BINARY=llama-cpp-fallback
 
-# x86 ships 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.
-# arm64/darwin builds ship only llama-cpp-fallback, so fall back to it when cpu-all absent.
-if [ -e $CURDIR/llama-cpp-cpu-all ]; then
-	BINARY=llama-cpp-cpu-all
+if grep -q -e "\savx\s" /proc/cpuinfo ; then
+	echo "CPU:    AVX    found OK"
+	if [ -e $CURDIR/llama-cpp-avx ]; then
+		BINARY=llama-cpp-avx
+	fi
+fi
+
+if grep -q -e "\savx2\s" /proc/cpuinfo ; then
+	echo "CPU:    AVX2   found OK"
+	if [ -e $CURDIR/llama-cpp-avx2 ]; then
+		BINARY=llama-cpp-avx2
+	fi
+fi
+
+# Check avx 512
+if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
+	echo "CPU:    AVX512F found OK"
+	if [ -e $CURDIR/llama-cpp-avx512 ]; then
+		BINARY=llama-cpp-avx512
+	fi
 fi
 
 if [ -n "$LLAMACPP_GRPC_SERVERS" ]; then

backend/cpp/turboquant/Makefile

@@ -65,29 +65,6 @@ turboquant-avx:
 turboquant-fallback:
 	$(call turboquant-build,fallback,-DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off,--target grpc-server)
 
-# Single-build CPU backend via ggml CPU_ALL_VARIANTS (mirrors llama-cpp-cpu-all).
-# turboquant reuses backend/cpp/llama-cpp's CMakeLists.txt (hw_grpc_proto STATIC) and
-# Makefile (SHARED_LIBS make-var + EXTRA_CMAKE_ARGS), so this passes the same overrides
-# through to the copied build: SHARED_LIBS=ON, the DL flags, and --target ggml (which
-# pulls in the per-microarch libggml-cpu-*.so via ggml's add_dependencies). The .so set
-# is collected for package.sh to bundle into package/lib.
-turboquant-cpu-all:
-	rm -rf $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build
-	cp -rf $(LLAMA_CPP_DIR) $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build
-	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build purge
-	bash $(CURRENT_MAKEFILE_DIR)/patch-grpc-server.sh $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/grpc-server.cpp
-	$(info $(GREEN)I turboquant build info:cpu-all-variants$(RESET))
-	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(TURBOQUANT_VERSION) \
-	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build llama.cpp
-	bash $(CURRENT_MAKEFILE_DIR)/apply-patches.sh $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/llama.cpp $(PATCHES_DIR)
-	SHARED_LIBS=ON EXTRA_CMAKE_ARGS="-DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON" TARGET="--target grpc-server --target ggml" \
-	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(TURBOQUANT_VERSION) \
-	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build grpc-server
-	cp -rfv $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/grpc-server turboquant-cpu-all
-	rm -rf ggml-shared-libs && mkdir -p ggml-shared-libs
-	find $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/llama.cpp/build \( -name '*.so*' -o -name '*.dylib' \) -exec cp -av {} ggml-shared-libs/ \;
-	@echo "Collected ggml shared backends:" && ls -la ggml-shared-libs/
-
 turboquant-grpc:
 	$(call turboquant-build,grpc,-DGGML_RPC=ON -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off,--target grpc-server --target rpc-server)
 

backend/cpp/turboquant/package.sh

@@ -14,15 +14,6 @@ mkdir -p $CURDIR/package/lib
 cp -avrf $CURDIR/turboquant-* $CURDIR/package/
 cp -rfv $CURDIR/run.sh $CURDIR/package/
 
-# Bundle the ggml shared backends from the CPU_ALL_VARIANTS build into package/lib. ggml
-# discovers the per-microarch libggml-cpu-*.so by scanning the executable directory, which
-# (via the bundled lib/ld.so that run.sh launches through) resolves to lib/. See the
-# matching comment in backend/cpp/llama-cpp/package.sh. No-op on the fallback/ROCm builds.
-if [ -d "$CURDIR/ggml-shared-libs" ]; then
-    echo "Bundling ggml shared backends (CPU_ALL_VARIANTS)..."
-    cp -avf $CURDIR/ggml-shared-libs/*.so* $CURDIR/package/lib/
-fi
-
 # Detect architecture and copy appropriate libraries
 if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
     # x86_64 architecture

backend/cpp/turboquant/run.sh

@@ -12,11 +12,26 @@ grep -e "flags" /proc/cpuinfo | head -1
 
 BINARY=turboquant-fallback
 
-# x86/arm64 ship a single turboquant-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
-# probing. ROCm ships only turboquant-fallback, so fall back to it when cpu-all is absent.
-if [ -e $CURDIR/turboquant-cpu-all ]; then
-	BINARY=turboquant-cpu-all
+if grep -q -e "\savx\s" /proc/cpuinfo ; then
+	echo "CPU:    AVX    found OK"
+	if [ -e $CURDIR/turboquant-avx ]; then
+		BINARY=turboquant-avx
+	fi
+fi
+
+if grep -q -e "\savx2\s" /proc/cpuinfo ; then
+	echo "CPU:    AVX2   found OK"
+	if [ -e $CURDIR/turboquant-avx2 ]; then
+		BINARY=turboquant-avx2
+	fi
+fi
+
+# Check avx 512
+if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
+	echo "CPU:    AVX512F found OK"
+	if [ -e $CURDIR/turboquant-avx512 ]; then
+		BINARY=turboquant-avx512
+	fi
 fi
 
 if [ -n "$LLAMACPP_GRPC_SERVERS" ]; then

backend/go/acestep-cpp/Makefile

@@ -117,7 +117,8 @@ libgoacestepcpp-custom: CMakeLists.txt cpp/goacestepcpp.cpp cpp/goacestepcpp.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target goacestepcpp && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgoacestepcpp.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/libgoacestepcpp.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/libgoacestepcpp.dylib ./$(SO_TARGET) 2>/dev/null)
 
 test: acestep-cpp
 	@echo "Running acestep-cpp tests..."

backend/go/acestep-cpp/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,7 +23,11 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("ACESTEP_LIBRARY")
 	if libName == "" {
-		libName = "./libgoacestepcpp-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./libgoacestepcpp-fallback.dylib"
+		} else {
+			libName = "./libgoacestepcpp-fallback.so"
+		}
 	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/acestep-cpp/package.sh

@@ -13,6 +13,7 @@ mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/acestep-cpp $CURDIR/package/
 cp -fv $CURDIR/libgoacestepcpp-*.so $CURDIR/package/
+cp -fv $CURDIR/libgoacestepcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/acestep-cpp/run.sh

@@ -12,9 +12,19 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single library variant (Metal or Accelerate). The goacestepcpp
+	# target is built as a CMake MODULE, which emits a .dylib for a SHARED
+	# build but a .so for a MODULE build on Apple, so prefer .dylib and fall
+	# back to .so.
+	LIBRARY="$CURDIR/libgoacestepcpp-fallback.dylib"
+	if [ ! -e "$LIBRARY" ]; then
+		LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
+	fi
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgoacestepcpp-avx.so ]; then
@@ -36,9 +46,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libgoacestepcpp-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export ACESTEP_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/ced/Makefile

@@ -57,6 +57,7 @@ libced.so: sources/ced.cpp
 	cmake -B sources/ced.cpp/build-shared -S sources/ced.cpp $(CMAKE_ARGS)
 	cmake --build sources/ced.cpp/build-shared --config Release -j$(JOBS)
 	cp -fv sources/ced.cpp/build-shared/libced.so* ./ 2>/dev/null || true
+	cp -fv sources/ced.cpp/build-shared/libced.dylib ./ 2>/dev/null || true
 	cp -fv sources/ced.cpp/include/ced_capi.h ./
 
 ced-grpc: libced.so main.go goced.go

backend/go/ced/main.go

@@ -12,6 +12,7 @@ import (
 	"flag"
 	"fmt"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -27,7 +28,11 @@ type libFunc struct {
 func main() {
 	libName := os.Getenv("CED_LIBRARY")
 	if libName == "" {
-		libName = "libced.so"
+		if runtime.GOOS == "darwin" {
+			libName = "libced.dylib"
+		} else {
+			libName = "libced.so"
+		}
 	}
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/ced/package.sh

@@ -15,10 +15,12 @@ mkdir -p "$CURDIR/package/lib"
 cp -avf "$CURDIR/ced-grpc" "$CURDIR/package/"
 cp -avf "$CURDIR/run.sh" "$CURDIR/package/"
 
-cp -avf "$CURDIR"/libced.so* "$CURDIR/package/lib/" 2>/dev/null || {
-	echo "ERROR: libced.so not found in $CURDIR, run 'make' first" >&2
+cp -avf "$CURDIR"/libced.so* "$CURDIR/package/lib/" 2>/dev/null || true
+cp -avf "$CURDIR"/libced.dylib "$CURDIR/package/lib/" 2>/dev/null || true
+if ! ls "$CURDIR"/package/lib/libced.* >/dev/null 2>&1; then
+	echo "ERROR: libced shared library not found in $CURDIR, run 'make' first" >&2
 	exit 1
-}
+fi
 
 if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
     echo "Detected x86_64 architecture, copying x86_64 libraries..."

backend/go/ced/run.sh

@@ -3,7 +3,12 @@ set -e
 
 CURDIR=$(dirname "$(realpath "$0")")
 
-export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
+if [ "$(uname)" = "Darwin" ]; then
+	export DYLD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${DYLD_LIBRARY_PATH:-}"
+	export CED_LIBRARY="$CURDIR/lib/libced.dylib"
+else
+	export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
+fi
 
 # If a self-contained ld.so was packaged, route through it so the packaged
 # libc / libstdc++ are used instead of the host's (matches the sibling backends).

backend/go/crispasr/Makefile

@@ -75,7 +75,8 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgocrispasr-avx.so libgocrispasr-avx2.so libgocrispasr-avx512.so libgocrispasr-fallback.so
 else
-	VARIANT_TARGETS = libgocrispasr-fallback.so
+	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
+	VARIANT_TARGETS = libgocrispasr-fallback.dylib
 endif
 
 crispasr: main.go gocrispasr.go $(VARIANT_TARGETS)
@@ -87,7 +88,7 @@ package: crispasr
 build: package
 
 clean: purge
-	rm -rf libgocrispasr*.so package sources/CrispASR crispasr
+	rm -rf libgocrispasr*.so libgocrispasr*.dylib package sources/CrispASR crispasr
 
 purge:
 	rm -rf build*
@@ -118,13 +119,21 @@ libgocrispasr-fallback.so: sources/CrispASR
 	SO_TARGET=libgocrispasr-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgocrispasr-custom
 	rm -rfv build*
 
+# Build fallback variant as a dylib (Darwin)
+libgocrispasr-fallback.dylib: sources/CrispASR
+	$(MAKE) purge
+	$(info ${GREEN}I crispasr build info:fallback (dylib)${RESET})
+	SO_TARGET=libgocrispasr-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgocrispasr-custom
+	rm -rfv build*
+
 libgocrispasr-custom: CMakeLists.txt cpp/crispasr_shim.cpp cpp/crispasr_shim.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgocrispasr.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/libgocrispasr.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/libgocrispasr.dylib ./$(SO_TARGET) 2>/dev/null)
 
 test: crispasr
 	CGO_ENABLED=0 $(GOCMD) test -v ./...

backend/go/crispasr/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,7 +22,11 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("CRISPASR_LIBRARY")
 	if libName == "" {
-		libName = "./libgocrispasr-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./libgocrispasr-fallback.dylib"
+		} else {
+			libName = "./libgocrispasr-fallback.so"
+		}
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/crispasr/package.sh

@@ -12,7 +12,8 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/crispasr $CURDIR/package/
-cp -fv $CURDIR/libgocrispasr-*.so $CURDIR/package/
+cp -fv $CURDIR/libgocrispasr-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgocrispasr-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/crispasr/run.sh

@@ -12,9 +12,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/libgocrispasr-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/libgocrispasr-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libgocrispasr-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgocrispasr-avx.so ]; then
@@ -36,9 +40,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libgocrispasr-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export CRISPASR_LIBRARY=$LIBRARY
 
 # Point piper's espeak-ng phonemizer at the bundled voice data. The variable

backend/go/depth-anything-cpp/Makefile

@@ -77,7 +77,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libdepthanythingcpp-avx.so libdepthanythingcpp-avx2.so libdepthanythingcpp-avx512.so libdepthanythingcpp-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = libdepthanythingcpp-fallback.so
+	VARIANT_TARGETS = libdepthanythingcpp-fallback.dylib
 endif
 
 depth-anything-cpp: main.go godepthanythingcpp.go $(VARIANT_TARGETS)
@@ -89,7 +89,7 @@ package: depth-anything-cpp
 build: package
 
 clean: purge
-	rm -rf libdepthanythingcpp*.so depth-anything-cpp package sources
+	rm -rf libdepthanythingcpp*.so libdepthanythingcpp*.dylib depth-anything-cpp package sources
 
 purge:
 	rm -rf build*
@@ -116,11 +116,19 @@ libdepthanythingcpp-avx512.so: sources/depth-anything.cpp
 endif
 
 # Build fallback variant (all platforms)
+ifeq ($(UNAME_S),Darwin)
+libdepthanythingcpp-fallback.dylib: sources/depth-anything.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I depth-anything-cpp build info:fallback${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libdepthanythingcpp-custom
+	rm -rfv build-$@
+else
 libdepthanythingcpp-fallback.so: sources/depth-anything.cpp
 	rm -rfv build-$@
 	$(info ${GREEN}I depth-anything-cpp build info:fallback${RESET})
 	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libdepthanythingcpp-custom
 	rm -rfv build-$@
+endif
 
 libdepthanythingcpp-custom: CMakeLists.txt
 	mkdir -p build-$(SO_TARGET) && \
@@ -128,7 +136,8 @@ libdepthanythingcpp-custom: CMakeLists.txt
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libdepthanything.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/libdepthanything.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/libdepthanything.dylib ./$(SO_TARGET) 2>/dev/null)
 
 all: depth-anything-cpp package
 

backend/go/depth-anything-cpp/main.go

@@ -9,6 +9,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -27,7 +28,11 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("DEPTHANYTHING_LIBRARY")
 	if libName == "" {
-		libName = "./libdepthanythingcpp-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./libdepthanythingcpp-fallback.dylib"
+		} else {
+			libName = "./libdepthanythingcpp-fallback.so"
+		}
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/depth-anything-cpp/package.sh

@@ -10,7 +10,8 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -avf $CURDIR/libdepthanythingcpp-*.so $CURDIR/package/
+cp -fv $CURDIR/libdepthanythingcpp-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libdepthanythingcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -avf $CURDIR/depth-anything-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/depth-anything-cpp/run.sh

@@ -12,9 +12,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/libdepthanythingcpp-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/libdepthanythingcpp-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libdepthanythingcpp-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libdepthanythingcpp-avx.so ]; then
@@ -36,9 +40,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libdepthanythingcpp-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export DEPTHANYTHING_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/localvqe/Makefile

@@ -67,8 +67,9 @@ $(LIB_SENTINEL): sources/LocalVQE
 	# that the loader picks at runtime. We must build every target — the
 	# default `--target localvqe_shared` drops these. CMAKE_LIBRARY_OUTPUT_DIRECTORY
 	# routes all of them into build/bin; copy them out next to the binary.
-	cp -P build/bin/liblocalvqe.so* . 2>/dev/null || cp -P build/liblocalvqe.so* .
+	cp -P build/bin/liblocalvqe.so* . 2>/dev/null || cp -P build/bin/liblocalvqe.dylib . 2>/dev/null || cp -P build/liblocalvqe.so* . 2>/dev/null || cp -P build/liblocalvqe.dylib .
 	cp -P build/bin/libggml*.so* . 2>/dev/null || true
+	cp -P build/bin/libggml*.dylib . 2>/dev/null || true
 	touch $(LIB_SENTINEL)
 
 liblocalvqe.so: $(LIB_SENTINEL)

backend/go/localvqe/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,7 +22,11 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("LOCALVQE_LIBRARY")
 	if libName == "" {
-		libName = "./liblocalvqe.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./liblocalvqe.dylib"
+		} else {
+			libName = "./liblocalvqe.so"
+		}
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/localvqe/package.sh

@@ -15,7 +15,9 @@ cp -avf $CURDIR/localvqe $CURDIR/package/
 # liblocalvqe.so* (with SOVERSION symlinks) and the libggml-*.so runtime
 # variants — LocalVQE picks the matching CPU variant at load time.
 cp -P $CURDIR/liblocalvqe.so* $CURDIR/package/ 2>/dev/null || true
+cp -P $CURDIR/liblocalvqe.dylib $CURDIR/package/ 2>/dev/null || true
 cp -P $CURDIR/libggml*.so* $CURDIR/package/ 2>/dev/null || true
+cp -P $CURDIR/libggml*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/localvqe/run.sh

@@ -10,8 +10,19 @@ CURDIR=$(dirname "$(realpath $0)")
 # exec'ing the binary.
 cd "$CURDIR"
 
-export LD_LIBRARY_PATH=$CURDIR:$CURDIR/lib:$LD_LIBRARY_PATH
-export LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.so
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: LocalVQE is built as a SHARED library, so dyld needs the .dylib +
+	# DYLD_LIBRARY_PATH. Prefer .dylib and fall back to .so just in case.
+	export DYLD_LIBRARY_PATH=$CURDIR:$CURDIR/lib:$DYLD_LIBRARY_PATH
+	LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.dylib
+	if [ ! -e "$LOCALVQE_LIBRARY" ]; then
+		LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.so
+	fi
+	export LOCALVQE_LIBRARY
+else
+	export LD_LIBRARY_PATH=$CURDIR:$CURDIR/lib:$LD_LIBRARY_PATH
+	export LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.so
+fi
 
 if [ -f $CURDIR/lib/ld.so ]; then
 	echo "Using lib/ld.so"

backend/go/locate-anything-cpp/Makefile

@@ -70,7 +70,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = liblocateanythingcpp-avx.so liblocateanythingcpp-avx2.so liblocateanythingcpp-avx512.so liblocateanythingcpp-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = liblocateanythingcpp-fallback.so
+	VARIANT_TARGETS = liblocateanythingcpp-fallback.dylib
 endif
 
 locate-anything-cpp: main.go golocateanythingcpp.go $(VARIANT_TARGETS)
@@ -82,7 +82,7 @@ package: locate-anything-cpp
 build: package
 
 clean: purge
-	rm -rf liblocateanythingcpp*.so locate-anything-cpp package sources
+	rm -rf liblocateanythingcpp*.so liblocateanythingcpp*.dylib locate-anything-cpp package sources
 
 purge:
 	rm -rf build*
@@ -109,11 +109,19 @@ liblocateanythingcpp-avx512.so: sources/locate-anything.cpp
 endif
 
 # Build fallback variant (all platforms)
+ifeq ($(UNAME_S),Darwin)
+liblocateanythingcpp-fallback.dylib: sources/locate-anything.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I locate-anything-cpp build info:fallback${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) liblocateanythingcpp-custom
+	rm -rfv build-$@
+else
 liblocateanythingcpp-fallback.so: sources/locate-anything.cpp
 	rm -rfv build-$@
 	$(info ${GREEN}I locate-anything-cpp build info:fallback${RESET})
 	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) liblocateanythingcpp-custom
 	rm -rfv build-$@
+endif
 
 liblocateanythingcpp-custom: CMakeLists.txt
 	mkdir -p build-$(SO_TARGET) && \
@@ -121,7 +129,8 @@ liblocateanythingcpp-custom: CMakeLists.txt
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	mv build-$(SO_TARGET)/liblocateanythingcpp.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/liblocateanythingcpp.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/liblocateanythingcpp.dylib ./$(SO_TARGET) 2>/dev/null)
 
 all: locate-anything-cpp package
 

backend/go/locate-anything-cpp/main.go

@@ -9,6 +9,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -27,7 +28,11 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("LOCATEANYTHING_LIBRARY")
 	if libName == "" {
-		libName = "./liblocateanythingcpp-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./liblocateanythingcpp-fallback.dylib"
+		} else {
+			libName = "./liblocateanythingcpp-fallback.so"
+		}
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/locate-anything-cpp/package.sh

@@ -10,7 +10,8 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -avf $CURDIR/liblocateanythingcpp-*.so $CURDIR/package/
+cp -fv $CURDIR/liblocateanythingcpp-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/liblocateanythingcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -avf $CURDIR/locate-anything-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/locate-anything-cpp/run.sh

@@ -12,9 +12,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/liblocateanythingcpp-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/liblocateanythingcpp-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/liblocateanythingcpp-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/liblocateanythingcpp-avx.so ]; then
@@ -36,9 +40,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/liblocateanythingcpp-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export LOCATEANYTHING_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/omnivoice-cpp/Makefile

@@ -65,7 +65,8 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgomnivoicecpp-avx.so libgomnivoicecpp-avx2.so libgomnivoicecpp-avx512.so libgomnivoicecpp-fallback.so
 else
-	VARIANT_TARGETS = libgomnivoicecpp-fallback.so
+	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
+	VARIANT_TARGETS = libgomnivoicecpp-fallback.dylib
 endif
 
 omnivoice-cpp: main.go gomnivoicecpp.go $(VARIANT_TARGETS)
@@ -77,7 +78,7 @@ package: omnivoice-cpp
 build: package
 
 clean: purge
-	rm -rf libgomnivoicecpp*.so package sources/omnivoice.cpp omnivoice-cpp
+	rm -rf libgomnivoicecpp*.so libgomnivoicecpp*.dylib package sources/omnivoice.cpp omnivoice-cpp
 
 purge:
 	rm -rf build*
@@ -106,13 +107,20 @@ libgomnivoicecpp-fallback.so: sources/omnivoice.cpp
 	SO_TARGET=libgomnivoicecpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomnivoicecpp-custom
 	rm -rf build-libgomnivoicecpp-fallback.so
 
+# Build fallback variant as a dylib (Darwin)
+libgomnivoicecpp-fallback.dylib: sources/omnivoice.cpp
+	$(info ${GREEN}I omnivoice-cpp build info:fallback (dylib)${RESET})
+	SO_TARGET=libgomnivoicecpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomnivoicecpp-custom
+	rm -rf build-libgomnivoicecpp-fallback.dylib
+
 libgomnivoicecpp-custom: CMakeLists.txt cpp/gomnivoicecpp.cpp cpp/gomnivoicecpp.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target gomnivoicecpp && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgomnivoicecpp.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/libgomnivoicecpp.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/libgomnivoicecpp.dylib ./$(SO_TARGET) 2>/dev/null)
 
 test: omnivoice-cpp
 	@echo "Running omnivoice-cpp tests..."

backend/go/omnivoice-cpp/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,7 +22,11 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("OMNIVOICE_LIBRARY")
 	if libName == "" {
-		libName = "./libgomnivoicecpp-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./libgomnivoicecpp-fallback.dylib"
+		} else {
+			libName = "./libgomnivoicecpp-fallback.so"
+		}
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/omnivoice-cpp/package.sh

@@ -12,7 +12,8 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/omnivoice-cpp $CURDIR/package/
-cp -fv $CURDIR/libgomnivoicecpp-*.so $CURDIR/package/
+cp -fv $CURDIR/libgomnivoicecpp-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgomnivoicecpp-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/omnivoice-cpp/run.sh

@@ -12,9 +12,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/libgomnivoicecpp-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/libgomnivoicecpp-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libgomnivoicecpp-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgomnivoicecpp-avx.so ]; then
@@ -36,9 +40,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libgomnivoicecpp-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export OMNIVOICE_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/parakeet-cpp/Makefile

@@ -74,6 +74,7 @@ libparakeet.so: sources/parakeet.cpp
 	cmake -B sources/parakeet.cpp/build-shared -S sources/parakeet.cpp $(CMAKE_ARGS)
 	cmake --build sources/parakeet.cpp/build-shared --config Release -j$(JOBS)
 	cp -fv sources/parakeet.cpp/build-shared/libparakeet.so* ./ 2>/dev/null || true
+	cp -fv sources/parakeet.cpp/build-shared/libparakeet.dylib ./ 2>/dev/null || true
 	cp -fv sources/parakeet.cpp/include/parakeet_capi.h ./
 
 parakeet-cpp-grpc: libparakeet.so main.go goparakeetcpp.go

backend/go/parakeet-cpp/main.go

@@ -2,15 +2,17 @@ package main
 
 // Started internally by LocalAI - one gRPC server per loaded model.
 //
-// Loads libparakeet.so via purego and registers the flat C-API entry
-// points declared in parakeet_capi.h. The library name can be overridden
-// with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY / VIBEVOICECPP_LIBRARY
-// convention in the sibling backends); the default looks for the .so next
-// to this binary.
+// Loads the parakeet shared library via purego and registers the flat
+// C-API entry points declared in parakeet_capi.h. The library name can be
+// overridden with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY /
+// VIBEVOICECPP_LIBRARY convention in the sibling backends); the default
+// looks next to this binary for libparakeet.so on Linux and
+// libparakeet.dylib on macOS.
 import (
 	"flag"
 	"fmt"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,7 +30,11 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("PARAKEET_LIBRARY")
 	if libName == "" {
-		libName = "libparakeet.so"
+		if runtime.GOOS == "darwin" {
+			libName = "libparakeet.dylib"
+		} else {
+			libName = "libparakeet.so"
+		}
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/parakeet-cpp/package.sh

@@ -16,12 +16,15 @@ mkdir -p "$CURDIR/package/lib"
 cp -avf "$CURDIR/parakeet-cpp-grpc" "$CURDIR/package/"
 cp -avf "$CURDIR/run.sh" "$CURDIR/package/"
 
-# libparakeet.so + any soname symlinks (libparakeet.so.X[.Y]). purego.Dlopen
-# resolves it via LD_LIBRARY_PATH, which run.sh points at lib/.
-cp -avf "$CURDIR"/libparakeet.so* "$CURDIR/package/lib/" 2>/dev/null || {
-	echo "ERROR: libparakeet.so not found in $CURDIR, run 'make' first" >&2
+# libparakeet shared lib + any soname symlinks. On Linux this is
+# libparakeet.so[.X.Y]; on macOS it is libparakeet.dylib. purego.Dlopen
+# resolves it via the *_LIBRARY_PATH that run.sh points at lib/.
+cp -avf "$CURDIR"/libparakeet.so* "$CURDIR/package/lib/" 2>/dev/null || true
+cp -avf "$CURDIR"/libparakeet.dylib "$CURDIR/package/lib/" 2>/dev/null || true
+if ! ls "$CURDIR"/package/lib/libparakeet.* >/dev/null 2>&1; then
+	echo "ERROR: libparakeet shared library not found in $CURDIR, run 'make' first" >&2
 	exit 1
-}
+fi
 
 # Detect architecture and copy the core runtime libs libparakeet.so links
 # against, plus the matching dynamic loader as lib/ld.so.
@@ -48,7 +51,7 @@ elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
     cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 "$CURDIR/package/lib/librt.so.1"
     cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 "$CURDIR/package/lib/libpthread.so.0"
 elif [ "$(uname -s)" = "Darwin" ]; then
-    echo "Detected Darwin"
+    echo "Detected Darwin — system frameworks linked dynamically, no bundled libs needed"
 else
     echo "Error: Could not detect architecture"
     exit 1

backend/go/parakeet-cpp/run.sh

@@ -3,11 +3,17 @@ set -e
 
 CURDIR=$(dirname "$(realpath "$0")")
 
-export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
+if [ "$(uname)" = "Darwin" ]; then
+	export DYLD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${DYLD_LIBRARY_PATH:-}"
+	export PARAKEET_LIBRARY="$CURDIR/lib/libparakeet.dylib"
+else
+	export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
+	export PARAKEET_LIBRARY="$CURDIR/lib/libparakeet.so"
+fi
 
 # If a self-contained ld.so was packaged, route through it so the
 # packaged libc / libstdc++ are used instead of the host's (matches the
-# whisper backend's runtime layout).
+# whisper backend's runtime layout). Linux only.
 if [ -f "$CURDIR/lib/ld.so" ]; then
 	echo "Using lib/ld.so"
 	exec "$CURDIR/lib/ld.so" "$CURDIR/parakeet-cpp-grpc" "$@"

backend/go/qwen3-tts-cpp/Makefile

@@ -65,8 +65,8 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgoqwen3ttscpp-avx.so libgoqwen3ttscpp-avx2.so libgoqwen3ttscpp-avx512.so libgoqwen3ttscpp-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = libgoqwen3ttscpp-fallback.so
+	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
+	VARIANT_TARGETS = libgoqwen3ttscpp-fallback.dylib
 endif
 
 qwen3-tts-cpp: main.go goqwen3ttscpp.go $(VARIANT_TARGETS)
@@ -78,7 +78,7 @@ package: qwen3-tts-cpp
 build: package
 
 clean: purge
-	rm -rf libgoqwen3ttscpp*.so package sources/qwentts.cpp qwen3-tts-cpp
+	rm -rf libgoqwen3ttscpp*.so libgoqwen3ttscpp*.dylib package sources/qwentts.cpp qwen3-tts-cpp
 
 purge:
 	rm -rf build*
@@ -110,13 +110,20 @@ libgoqwen3ttscpp-fallback.so: sources/qwentts.cpp
 	SO_TARGET=libgoqwen3ttscpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoqwen3ttscpp-custom
 	rm -rf build-libgoqwen3ttscpp-fallback.so
 
+# Build fallback variant as a dylib (Darwin)
+libgoqwen3ttscpp-fallback.dylib: sources/qwentts.cpp
+	$(info ${GREEN}I qwen3-tts-cpp build info:fallback (dylib)${RESET})
+	SO_TARGET=libgoqwen3ttscpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoqwen3ttscpp-custom
+	rm -rf build-libgoqwen3ttscpp-fallback.dylib
+
 libgoqwen3ttscpp-custom: CMakeLists.txt cpp/goqwen3ttscpp.cpp cpp/goqwen3ttscpp.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target goqwen3ttscpp && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgoqwen3ttscpp.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/libgoqwen3ttscpp.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/libgoqwen3ttscpp.dylib ./$(SO_TARGET) 2>/dev/null)
 
 test: qwen3-tts-cpp
 	@echo "Running qwen3-tts-cpp tests..."

backend/go/qwen3-tts-cpp/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,7 +22,11 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("QWEN3TTS_LIBRARY")
 	if libName == "" {
-		libName = "./libgoqwen3ttscpp-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./libgoqwen3ttscpp-fallback.dylib"
+		} else {
+			libName = "./libgoqwen3ttscpp-fallback.so"
+		}
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/qwen3-tts-cpp/package.sh

@@ -12,7 +12,8 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/qwen3-tts-cpp $CURDIR/package/
-cp -fv $CURDIR/libgoqwen3ttscpp-*.so $CURDIR/package/
+cp -fv $CURDIR/libgoqwen3ttscpp-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgoqwen3ttscpp-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/qwen3-tts-cpp/run.sh

@@ -12,9 +12,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/libgoqwen3ttscpp-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/libgoqwen3ttscpp-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libgoqwen3ttscpp-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgoqwen3ttscpp-avx.so ]; then
@@ -36,9 +40,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libgoqwen3ttscpp-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export QWEN3TTS_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/rfdetr-cpp/Makefile

@@ -71,7 +71,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = librfdetrcpp-avx.so librfdetrcpp-avx2.so librfdetrcpp-avx512.so librfdetrcpp-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = librfdetrcpp-fallback.so
+	VARIANT_TARGETS = librfdetrcpp-fallback.dylib
 endif
 
 rfdetr-cpp: main.go gorfdetrcpp.go $(VARIANT_TARGETS)
@@ -83,7 +83,7 @@ package: rfdetr-cpp
 build: package
 
 clean: purge
-	rm -rf librfdetrcpp*.so rfdetr-cpp package sources
+	rm -rf librfdetrcpp*.so librfdetrcpp*.dylib rfdetr-cpp package sources
 
 purge:
 	rm -rf build*
@@ -110,11 +110,19 @@ librfdetrcpp-avx512.so: sources/rt-detr.cpp
 endif
 
 # Build fallback variant (all platforms)
+ifeq ($(UNAME_S),Darwin)
+librfdetrcpp-fallback.dylib: sources/rt-detr.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I rfdetr-cpp build info:fallback${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
+	rm -rfv build-$@
+else
 librfdetrcpp-fallback.so: sources/rt-detr.cpp
 	rm -rfv build-$@
 	$(info ${GREEN}I rfdetr-cpp build info:fallback${RESET})
 	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
 	rm -rfv build-$@
+endif
 
 librfdetrcpp-custom: CMakeLists.txt
 	mkdir -p build-$(SO_TARGET) && \
@@ -122,7 +130,8 @@ librfdetrcpp-custom: CMakeLists.txt
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	mv build-$(SO_TARGET)/librfdetrcpp.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/librfdetrcpp.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/librfdetrcpp.dylib ./$(SO_TARGET) 2>/dev/null)
 
 all: rfdetr-cpp package
 

backend/go/rfdetr-cpp/main.go

@@ -9,6 +9,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -27,7 +28,11 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("RFDETR_LIBRARY")
 	if libName == "" {
-		libName = "./librfdetrcpp-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./librfdetrcpp-fallback.dylib"
+		} else {
+			libName = "./librfdetrcpp-fallback.so"
+		}
 	}
 
 	rfdetrLib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/rfdetr-cpp/package.sh

@@ -10,7 +10,8 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -avf $CURDIR/librfdetrcpp-*.so $CURDIR/package/
+cp -fv $CURDIR/librfdetrcpp-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/librfdetrcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -avf $CURDIR/rfdetr-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/rfdetr-cpp/run.sh

@@ -12,9 +12,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/librfdetrcpp-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/librfdetrcpp-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/librfdetrcpp-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/librfdetrcpp-avx.so ]; then
@@ -36,9 +40,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/librfdetrcpp-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export RFDETR_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/sam3-cpp/Makefile

@@ -66,7 +66,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgosam3-avx.so libgosam3-avx2.so libgosam3-avx512.so libgosam3-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = libgosam3-fallback.so
+	VARIANT_TARGETS = libgosam3-fallback.dylib
 endif
 
 sam3-cpp: main.go gosam3.go $(VARIANT_TARGETS)
@@ -78,7 +78,7 @@ package: sam3-cpp
 build: package
 
 clean: purge
-	rm -rf libgosam3*.so sam3-cpp package sources
+	rm -rf libgosam3*.so libgosam3*.dylib sam3-cpp package sources
 
 purge:
 	rm -rf build*
@@ -105,11 +105,19 @@ libgosam3-avx512.so: sources/sam3.cpp
 endif
 
 # Build fallback variant (all platforms)
+ifeq ($(UNAME_S),Darwin)
+libgosam3-fallback.dylib: sources/sam3.cpp
+	$(MAKE) purge
+	$(info ${GREEN}I sam3-cpp build info:fallback${RESET})
+	SO_TARGET=libgosam3-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgosam3-custom
+	rm -rfv build*
+else
 libgosam3-fallback.so: sources/sam3.cpp
 	$(MAKE) purge
 	$(info ${GREEN}I sam3-cpp build info:fallback${RESET})
 	SO_TARGET=libgosam3-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgosam3-custom
 	rm -rfv build*
+endif
 
 libgosam3-custom: CMakeLists.txt cpp/gosam3.cpp cpp/gosam3.h
 	mkdir -p build-$(SO_TARGET) && \
@@ -117,6 +125,7 @@ libgosam3-custom: CMakeLists.txt cpp/gosam3.cpp cpp/gosam3.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgosam3.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/libgosam3.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/libgosam3.dylib ./$(SO_TARGET) 2>/dev/null)
 
 all: sam3-cpp package

backend/go/sam3-cpp/main.go

@@ -3,6 +3,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,7 +22,11 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("SAM3_LIBRARY")
 	if libName == "" {
-		libName = "./libgosam3-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./libgosam3-fallback.dylib"
+		} else {
+			libName = "./libgosam3-fallback.so"
+		}
 	}
 
 	gosamLib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/sam3-cpp/package.sh

@@ -10,7 +10,8 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -avf $CURDIR/libgosam3-*.so $CURDIR/package/
+cp -fv $CURDIR/libgosam3-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgosam3-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -avf $CURDIR/sam3-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/sam3-cpp/run.sh

@@ -12,9 +12,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/libgosam3-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/libgosam3-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libgosam3-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgosam3-avx.so ]; then
@@ -36,9 +40,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libgosam3-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export SAM3_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/sherpa-onnx/backend.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"runtime"
 	"strconv"
 	"strings"
 	"sync"
@@ -238,11 +239,19 @@ func loadSherpaLibs() error {
 func loadSherpaLibsOnce() error {
 	shimLib := os.Getenv("SHERPA_SHIM_LIBRARY")
 	if shimLib == "" {
-		shimLib = "libsherpa-shim.so"
+		if runtime.GOOS == "darwin" {
+			shimLib = "libsherpa-shim.dylib"
+		} else {
+			shimLib = "libsherpa-shim.so"
+		}
 	}
 	capiLib := os.Getenv("SHERPA_ONNX_LIBRARY")
 	if capiLib == "" {
-		capiLib = "libsherpa-onnx-c-api.so"
+		if runtime.GOOS == "darwin" {
+			capiLib = "libsherpa-onnx-c-api.dylib"
+		} else {
+			capiLib = "libsherpa-onnx-c-api.so"
+		}
 	}
 
 	shim, err := purego.Dlopen(shimLib, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/sherpa-onnx/run.sh

@@ -3,7 +3,13 @@ set -ex
 
 CURDIR=$(dirname "$(realpath $0)")
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+if [ "$(uname)" = "Darwin" ]; then
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+	export SHERPA_SHIM_LIBRARY=$CURDIR/lib/libsherpa-shim.dylib
+	export SHERPA_ONNX_LIBRARY=$CURDIR/lib/libsherpa-onnx-c-api.dylib
+else
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+fi
 
 if [ -f $CURDIR/lib/ld.so ]; then
 	echo "Using lib/ld.so"

backend/go/stablediffusion-ggml/Makefile

@@ -131,6 +131,7 @@ libgosd-custom: CMakeLists.txt cpp/gosd.cpp cpp/gosd.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgosd.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/libgosd.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/libgosd.dylib ./$(SO_TARGET) 2>/dev/null)
 
 all: stablediffusion-ggml package

backend/go/stablediffusion-ggml/main.go

@@ -3,6 +3,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,7 +22,11 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("SD_LIBRARY")
 	if libName == "" {
-		libName = "./libgosd-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./libgosd-fallback.dylib"
+		} else {
+			libName = "./libgosd-fallback.so"
+		}
 	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/stablediffusion-ggml/package.sh

@@ -12,6 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/libgosd-*.so $CURDIR/package/
+cp -fv $CURDIR/libgosd-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -avf $CURDIR/stablediffusion-ggml $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/stablediffusion-ggml/run.sh

@@ -12,9 +12,18 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/libgosd-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single library variant (Metal or Accelerate). The gosd target is
+	# built as a CMake MODULE, which emits a .dylib for a SHARED build but a
+	# .so for a MODULE build on Apple, so prefer .dylib and fall back to .so.
+	LIBRARY="$CURDIR/libgosd-fallback.dylib"
+	if [ ! -e "$LIBRARY" ]; then
+		LIBRARY="$CURDIR/libgosd-fallback.so"
+	fi
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libgosd-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgosd-avx.so ]; then
@@ -36,9 +45,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libgosd-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export SD_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/vibevoice-cpp/Makefile

@@ -70,8 +70,8 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgovibevoicecpp-avx.so libgovibevoicecpp-avx2.so libgovibevoicecpp-avx512.so libgovibevoicecpp-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = libgovibevoicecpp-fallback.so
+	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
+	VARIANT_TARGETS = libgovibevoicecpp-fallback.dylib
 endif
 
 vibevoice-cpp: main.go govibevoicecpp.go $(VARIANT_TARGETS)
@@ -83,7 +83,7 @@ package: vibevoice-cpp
 build: package
 
 clean: purge
-	rm -rf libgovibevoicecpp*.so package sources/vibevoice.cpp vibevoice-cpp
+	rm -rf libgovibevoicecpp*.so libgovibevoicecpp*.dylib package sources/vibevoice.cpp vibevoice-cpp
 
 purge:
 	rm -rf build*
@@ -119,13 +119,21 @@ libgovibevoicecpp-fallback.so: sources/vibevoice.cpp
 	SO_TARGET=libgovibevoicecpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgovibevoicecpp-custom
 	rm -rfv build*
 
+# Build fallback variant as a dylib (Darwin)
+libgovibevoicecpp-fallback.dylib: sources/vibevoice.cpp
+	$(MAKE) purge
+	$(info ${GREEN}I vibevoice-cpp build info:fallback (dylib)${RESET})
+	SO_TARGET=libgovibevoicecpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgovibevoicecpp-custom
+	rm -rfv build*
+
 libgovibevoicecpp-custom: CMakeLists.txt cpp/govibevoicecpp.cpp cpp/govibevoicecpp.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target govibevoicecpp && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgovibevoicecpp.so ./$(SO_TARGET)
+	(mv build-$(SO_TARGET)/libgovibevoicecpp.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/libgovibevoicecpp.dylib ./$(SO_TARGET) 2>/dev/null)
 
 test: vibevoice-cpp
 	@echo "Running vibevoice-cpp tests..."

backend/go/vibevoice-cpp/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -21,7 +22,11 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("VIBEVOICECPP_LIBRARY")
 	if libName == "" {
-		libName = "./libgovibevoicecpp-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./libgovibevoicecpp-fallback.dylib"
+		} else {
+			libName = "./libgovibevoicecpp-fallback.so"
+		}
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/vibevoice-cpp/package.sh

@@ -12,7 +12,8 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/vibevoice-cpp $CURDIR/package/
-cp -fv $CURDIR/libgovibevoicecpp-*.so $CURDIR/package/
+cp -fv $CURDIR/libgovibevoicecpp-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgovibevoicecpp-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/vibevoice-cpp/run.sh

@@ -11,9 +11,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/libgovibevoicecpp-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/libgovibevoicecpp-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libgovibevoicecpp-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgovibevoicecpp-avx.so ]; then
@@ -34,9 +38,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libgovibevoicecpp-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export VIBEVOICECPP_LIBRARY=$LIBRARY
 
 if [ -f $CURDIR/lib/ld.so ]; then

backend/go/whisper/Makefile

@@ -117,6 +117,7 @@ libgowhisper-custom: CMakeLists.txt cpp/gowhisper.cpp cpp/gowhisper.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgowhisper.so ./$(SO_TARGET)
+	mv build-$(SO_TARGET)/libgowhisper.so ./$(SO_TARGET) 2>/dev/null || \
+		mv build-$(SO_TARGET)/libgowhisper.dylib ./$(SO_TARGET:.so=.dylib)
 
 all: whisper package

backend/go/whisper/main.go

@@ -4,6 +4,7 @@ package main
 import (
 	"flag"
 	"os"
+	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,7 +23,11 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("WHISPER_LIBRARY")
 	if libName == "" {
-		libName = "./libgowhisper-fallback.so"
+		if runtime.GOOS == "darwin" {
+			libName = "./libgowhisper-fallback.dylib"
+		} else {
+			libName = "./libgowhisper-fallback.so"
+		}
 	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/whisper/package.sh

@@ -12,7 +12,8 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/whisper $CURDIR/package/
-cp -fv $CURDIR/libgowhisper-*.so $CURDIR/package/
+cp -fv $CURDIR/libgowhisper-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgowhisper-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/whisper/run.sh

@@ -12,9 +12,13 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-LIBRARY="$CURDIR/libgowhisper-fallback.so"
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/libgowhisper-fallback.dylib"
+	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libgowhisper-fallback.so"
 
-if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgowhisper-avx.so ]; then
@@ -36,9 +40,10 @@ if [ "$(uname)" != "Darwin" ]; then
 			LIBRARY="$CURDIR/libgowhisper-avx512.so"
 		fi
 	fi
+
+	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
-export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export WHISPER_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

core/http/endpoints/openai/realtime_model.go

@@ -432,7 +432,7 @@ func loadSoundDetectionConfig(pipeline *config.Pipeline, cl *config.ModelConfigL
 	if pipeline.SoundDetection == "" {
 		return nil, nil
 	}
-	cfg, err := loadPipelineSubModel(cl, pipeline.SoundDetection, ml.ModelPath)
+	cfg, err := cl.LoadModelConfigFileByName(pipeline.SoundDetection, ml.ModelPath)
 	if err != nil {
 		return nil, fmt.Errorf("failed to load sound detection config: %w", err)
 	}
@@ -443,7 +443,7 @@ func loadSoundDetectionConfig(pipeline *config.Pipeline, cl *config.ModelConfigL
 }
 
 func newTranscriptionOnlyModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) (Model, *config.ModelConfig, error) {
-	cfgVAD, err := loadPipelineSubModel(cl, pipeline.VAD, ml.ModelPath)
+	cfgVAD, err := cl.LoadModelConfigFileByName(pipeline.VAD, ml.ModelPath)
 	if err != nil {
 
 		return nil, nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -453,7 +453,7 @@ func newTranscriptionOnlyModel(pipeline *config.Pipeline, cl *config.ModelConfig
 		return nil, nil, fmt.Errorf("failed to validate config: %w", err)
 	}
 
-	cfgSST, err := loadPipelineSubModel(cl, pipeline.Transcription, ml.ModelPath)
+	cfgSST, err := cl.LoadModelConfigFileByName(pipeline.Transcription, ml.ModelPath)
 	if err != nil {
 
 		return nil, nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -542,30 +542,11 @@ func buildRealtimeRoutingContext(a *application.Application, sessionID string) *
 	}
 }
 
-// loadPipelineSubModel loads a pipeline sub-model config by name and follows a
-// single alias hop, so a pipeline that references an alias (e.g. `llm: default`)
-// gets the alias target's full config (Backend, Model, ...) rather than the
-// alias stub with an empty Backend. Without this the alias survives unresolved
-// into model loading and fails downstream — notably in distributed mode with
-// "backend name is empty". Mirrors the top-level alias resolution in
-// core/http/middleware/request.go.
-func loadPipelineSubModel(cl *config.ModelConfigLoader, name, modelPath string) (*config.ModelConfig, error) {
-	cfg, err := cl.LoadModelConfigFileByName(name, modelPath)
-	if err != nil {
-		return nil, err
-	}
-	resolved, _, err := cl.ResolveAlias(cfg)
-	if err != nil {
-		return nil, err
-	}
-	return resolved, nil
-}
-
 // returns and loads either a wrapped model or a model that support audio-to-audio
 func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig, evaluator *templates.Evaluator, routing *RealtimeRoutingContext) (Model, error) {
 	xlog.Debug("Creating new model pipeline model", "pipeline", pipeline)
 
-	cfgVAD, err := loadPipelineSubModel(cl, pipeline.VAD, ml.ModelPath)
+	cfgVAD, err := cl.LoadModelConfigFileByName(pipeline.VAD, ml.ModelPath)
 	if err != nil {
 
 		return nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -576,7 +557,7 @@ func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model
 	}
 
 	// TODO: Do we always need a transcription model? It can be disabled. Note that any-to-any instruction following models don't transcribe as such, so if transcription is required it is a separate process
-	cfgSST, err := loadPipelineSubModel(cl, pipeline.Transcription, ml.ModelPath)
+	cfgSST, err := cl.LoadModelConfigFileByName(pipeline.Transcription, ml.ModelPath)
 	if err != nil {
 
 		return nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -608,7 +589,7 @@ func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model
 	xlog.Debug("Loading a wrapped model")
 
 	// Otherwise we want to return a wrapped model, which is a "virtual" model that re-uses other models to perform operations
-	cfgLLM, err := loadPipelineSubModel(cl, pipeline.LLM, ml.ModelPath)
+	cfgLLM, err := cl.LoadModelConfigFileByName(pipeline.LLM, ml.ModelPath)
 	if err != nil {
 
 		return nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -623,7 +604,7 @@ func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model
 	applyPipelineReasoning(cfgLLM, *pipeline)
 	applyPipelineThinking(cfgLLM, *pipeline)
 
-	cfgTTS, err := loadPipelineSubModel(cl, pipeline.TTS, ml.ModelPath)
+	cfgTTS, err := cl.LoadModelConfigFileByName(pipeline.TTS, ml.ModelPath)
 	if err != nil {
 
 		return nil, fmt.Errorf("failed to load backend config: %w", err)

core/http/endpoints/openai/realtime_model_alias_test.go

@@ -1,52 +0,0 @@
-package openai
-
-import (
-	"os"
-	"path/filepath"
-
-	. "github.com/onsi/ginkgo/v2"
-	. "github.com/onsi/gomega"
-
-	"github.com/mudler/LocalAI/core/config"
-)
-
-// loadPipelineSubModel must resolve a pipeline sub-model that references an
-// alias (e.g. `llm: default`) one hop to the alias target's full config — so
-// the effective backend is the target's backend, not the empty backend of the
-// alias stub. This mirrors the top-level alias resolution done in
-// core/http/middleware/request.go, which the realtime pipeline previously
-// skipped (failing in distributed mode with "backend name is empty").
-var _ = Describe("loadPipelineSubModel", func() {
-	It("resolves a sub-model alias one hop to the target's config", func() {
-		tmpDir := GinkgoT().TempDir()
-
-		// A real model config with a concrete backend.
-		realLLM := `name: real-llm
-backend: llama-cpp
-parameters:
-  model: real-llm.gguf
-`
-		Expect(os.WriteFile(filepath.Join(tmpDir, "real-llm.yaml"), []byte(realLLM), 0644)).To(Succeed())
-
-		// An alias pointing at the real model.
-		aliasCfg := `name: default
-alias: real-llm
-`
-		Expect(os.WriteFile(filepath.Join(tmpDir, "default.yaml"), []byte(aliasCfg), 0644)).To(Succeed())
-
-		cl := config.NewModelConfigLoader(tmpDir)
-		Expect(cl.LoadModelConfigsFromPath(tmpDir)).To(Succeed())
-
-		// Resolving the alias must follow the hop to the target's full config.
-		resolved, err := loadPipelineSubModel(cl, "default", tmpDir)
-		Expect(err).NotTo(HaveOccurred())
-		Expect(resolved.IsAlias()).To(BeFalse())
-		Expect(resolved.Backend).To(Equal("llama-cpp"))
-
-		// A non-alias name must load unchanged.
-		direct, err := loadPipelineSubModel(cl, "real-llm", tmpDir)
-		Expect(err).NotTo(HaveOccurred())
-		Expect(direct.Backend).To(Equal("llama-cpp"))
-		Expect(direct.Name).To(Equal("real-llm"))
-	})
-})

core/http/react-ui/public/locales/id/admin.json

@@ -45,7 +45,7 @@
   },
   "scheduling": {
     "title": "Penjadwalan",
-    "subtitle": "Aturan penempatan model dan replika di seluruh kluster"
+    "subtitle": "Aturan penempatan model dan replika di seluruh klaster"
   },
   "p2p": {
     "title": "Komputasi AI Terdistribusi",
@@ -86,4 +86,4 @@
     "title": "Penjelajah",
     "subtitle": "Jelajahi file dan konfigurasi"
   }
-}
+}

core/http/react-ui/public/locales/id/chat.json

@@ -72,7 +72,7 @@
   "actions": {
     "copy": "Salin",
     "regenerate": "Hasilkan ulang",
-    "jumpToLatest": "Lompat ke terbaru"
+    "jumpToLatest": "Jump to latest"
   },
   "streaming": {
     "transferring": "Mentransfer model...",
@@ -115,4 +115,4 @@
     "clearAll": "Hapus semua",
     "deleteAllTitle": "Hapus semua percakapan"
   }
-}
+}

core/http/react-ui/public/locales/id/common.json

@@ -1,8 +1,8 @@
 {
   "unsaved": {
-    "title": "Buang perubahan yang belum disimpan?",
-    "message": "Anda memiliki perubahan yang belum disimpan. Perubahan tersebut akan hilang jika Anda meninggalkan halaman ini.",
-    "leave": "Tinggalkan Halaman"
+    "title": "Discard unsaved changes?",
+    "message": "You have unsaved changes that will be lost if you leave this page.",
+    "leave": "Leave"
   },
   "actions": {
     "save": "Simpan",

core/http/react-ui/public/locales/id/home.json

@@ -7,15 +7,15 @@
   "resourceGpu": "GPU",
   "resourceRam": "RAM",
   "greeting": {
-    "morning": "Selamat pagi",
-    "afternoon": "Selamat siang",
-    "evening": "Selamat malam",
-    "night": "Selamat lembur"
+    "morning": "Good morning",
+    "afternoon": "Good afternoon",
+    "evening": "Good evening",
+    "night": "Working late"
   },
   "statusLine": {
-    "modelsLoaded_one": "{{count}} model dimuat",
-    "modelsLoaded_other": "{{count}} model dimuat",
-    "noModelsLoaded": "Tidak ada model yang dimuat",
+    "modelsLoaded_one": "{{count}} model loaded",
+    "modelsLoaded_other": "{{count}} models loaded",
+    "noModelsLoaded": "No models loaded",
     "nodes_one": "{{count}} node",
     "nodes_other": "{{count}} nodes"
   },
@@ -79,14 +79,14 @@
   },
   "connect": {
     "title": "Satu endpoint, semua API",
-    "subtitle": "LocalAI menyediakan API miliknya sendiri yang lengkap — pembuatan gambar & video, depth, deteksi objek, reranking, audio, pengenalan wajah & suara, serta suara realtime melalui WebRTC dan WebSocket. Selain itu, lapisan kompatibilitas drop-in membuat aplikasi apa pun yang dibuat untuk OpenAI, Anthropic, Ollama, atau OpenAI Responses bekerja tanpa perubahan.",
+    "subtitle": "LocalAI menyediakan API miliknya sendiri yang lengkap — pembuatan gambar & video, depth, deteksi objek, reranking, audio, pengenalan wajah & suara, serta suara realtime melalui WebRTC dan WebSocket. Di atas itu, lapisan kompatibilitas drop-in membuat aplikasi apa pun yang dibuat untuk OpenAI, Anthropic, Ollama, atau OpenAI Responses bekerja tanpa perubahan.",
     "nativeTitle": "API native",
     "compatTitle": "Kompatibilitas drop-in",
     "apiReference": "Referensi API lengkap",
     "copy": "Salin",
     "copied": "Disalin",
-    "browse": "Jelajahi API",
-    "hide": "Sembunyikan endpoint",
-    "dismiss": "Abaikan"
+    "browse": "Browse the API",
+    "hide": "Hide endpoints",
+    "dismiss": "Dismiss"
   }
 }

core/http/react-ui/public/locales/id/media.json

@@ -5,7 +5,7 @@
       "video": "Video",
       "tts": "TTS",
       "sound": "Suara",
-      "transform": "Transformasi"
+      "transform": "Transform"
     }
   },
   "image": {
@@ -30,7 +30,7 @@
       "refImagesAdded_other": "{{count}} gambar ditambahkan"
     },
     "actions": {
-      "view": "Lihat",
+      "view": "View",
       "generate": "Hasilkan",
       "generating": "Menghasilkan..."
     },
@@ -153,4 +153,4 @@
     "clearConfirm": "Hapus",
     "cleared": "Riwayat dihapus"
   }
-}
+}

core/http/react-ui/public/locales/id/nav.json

@@ -19,11 +19,11 @@
     "operate": "Operasikan"
   },
   "operate": {
-    "inference": "Inferensi",
-    "cluster": "Kluster",
-    "observability": "Observabilitas",
-    "access": "Akses",
-    "system": "Sistem"
+    "inference": "Inference",
+    "cluster": "Cluster",
+    "observability": "Observability",
+    "access": "Access",
+    "system": "System"
   },
   "items": {
     "home": "Beranda",
@@ -64,7 +64,7 @@
     "copyright": "© 2023-{{year}} {{author}}"
   },
   "console": {
-    "automation": "Automasi",
+    "automation": "Otomasi",
     "training": "Pelatihan"
   }
 }

scripts/build/llama-cpp-darwin.sh

@@ -6,11 +6,10 @@ IMAGE_NAME="${IMAGE_NAME:-localai/llama-cpp-darwin}"
 
 pushd backend/cpp/llama-cpp
 
-# Single build via ggml CPU_ALL_VARIANTS: one binary plus the per-microarch Apple/arm
-# dylibs (apple_m1/m2_m3/m4, armv8.x) that ggml selects at runtime. GGML_METAL stays ON
-# and --target ggml also builds ggml-metal (via add_dependencies), so the Metal GPU
-# backend is still produced as a loadable libggml-metal.dylib.
-make llama-cpp-cpu-all && \
+# make llama-cpp-avx && \
+# make llama-cpp-avx2 && \
+# make llama-cpp-avx512 && \
+make llama-cpp-fallback && \
 make llama-cpp-grpc && \
 make llama-cpp-rpc-server
 
@@ -20,24 +19,13 @@ mkdir -p build/darwin
 mkdir -p backend-images
 mkdir -p build/darwin/lib
 
-cp -rf backend/cpp/llama-cpp/llama-cpp-cpu-all build/darwin/
+# cp -rf backend/cpp/llama-cpp/llama-cpp-avx build/darwin/
+# cp -rf backend/cpp/llama-cpp/llama-cpp-avx2 build/darwin/
+# cp -rf backend/cpp/llama-cpp/llama-cpp-avx512 build/darwin/
+cp -rf backend/cpp/llama-cpp/llama-cpp-fallback build/darwin/
 cp -rf backend/cpp/llama-cpp/llama-cpp-grpc build/darwin/
 cp -rf backend/cpp/llama-cpp/llama-cpp-rpc-server build/darwin/
 
-# Distribute the shared ggml/llama libraries from the CPU_ALL_VARIANTS build. Unlike the
-# old fully-static fallback build, these have @rpath install names, so the otool loop below
-# (which only copies deps that exist on disk) will not pick them up. The split is by suffix:
-#  - ggml emits its loadable backends (per-microarch CPU variants, metal, blas) with a .so
-#    suffix EVEN ON DARWIN. These go in the package ROOT next to the binary, because darwin
-#    run.sh execs the binary directly (no bundled ld.so) so ggml's executable-directory
-#    scan looks there.
-#  - the core libraries (libggml-base/libggml/libllama/libllama-common/libmtmd) use the
-#    platform .dylib suffix and are NEEDED deps; they go in lib/, resolved at load time via
-#    the DYLD_LIBRARY_PATH=lib that run.sh exports. -a preserves the version symlinks.
-SHLIBS=backend/cpp/llama-cpp/ggml-shared-libs
-cp -a $SHLIBS/*.so build/darwin/
-cp -a $SHLIBS/*.dylib build/darwin/lib/
-
 # Set default additional libs only for Darwin on M chips (arm64)
 if [[ "$(uname -s)" == "Darwin" && "$(uname -m)" == "arm64" ]]; then
     ADDITIONAL_LIBS=${ADDITIONAL_LIBS:-$(ls /opt/homebrew/Cellar/protobuf/**/lib/libutf8_validity*.dylib 2>/dev/null)}