Add experimental MLX backend and engine with imagegen support (#13648)

* WIP - MLX backend with gemma3

* MLX: add cmake and go tag build toggles

To build the new MLX backend code:
  cmake --preset MLX
  cmake --build --preset MLX --parallel
  cmake --install build --component MLX
  go build -tags mlx .

Note: the main.go entrypoint for the MLX engine will change in a follow up commit.

* add experimental image generation runtime

* add experimental image generation runtime

* MLX: wire up cuda build for linux

* MLX: get dependencies correct and dedup

This is still too large for a unified github artifact, but is now "correct" for the mlx_cuda_v13
directory.

* fix relative link bug in dedup

* Add darwin build and readme

* add go build tag for mlx dependent code and wire up build_darwin.sh

* lint cleanup

* macos: build mlx for x86

This will be CPU only.

* cuda build instructions and fix drift from mlx bump

* stale comment

* Delete agent helper doc

* Clean up readme.md

* Revise README for tokenizer clarity and details

Updated README to clarify tokenizer functionality and removed correctness section.

---------

Co-authored-by: jmorganca <jmorganca@gmail.com>

scripts/build_darwin.sh

@@ -42,18 +42,39 @@ shift $(( $OPTIND - 1 ))
 _build_darwin() {
     for ARCH in $ARCHS; do
         status "Building darwin $ARCH"
-        INSTALL_PREFIX=dist/darwin-$ARCH/
-        GOOS=darwin GOARCH=$ARCH CGO_ENABLED=1 go build -o $INSTALL_PREFIX .
+        INSTALL_PREFIX=dist/darwin-$ARCH/        
 
         if [ "$ARCH" = "amd64" ]; then
             status "Building darwin $ARCH dynamic backends"
-            cmake -B build/darwin-$ARCH \
+            BUILD_DIR=build/darwin-$ARCH
+            cmake -B $BUILD_DIR \
                 -DCMAKE_OSX_ARCHITECTURES=x86_64 \
-                -DCMAKE_OSX_DEPLOYMENT_TARGET=11.3 \
+                -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
+                -DCMAKE_INSTALL_PREFIX=$INSTALL_PREFIX \
+                -DMLX_ENGINE=ON \
+                -DMLX_ENABLE_X64_MAC=ON \
+                -DOLLAMA_RUNNER_DIR=./
+            cmake --build $BUILD_DIR --target ggml-cpu -j
+            cmake --build $BUILD_DIR --target mlx mlxc -j
+            cmake --install $BUILD_DIR --component CPU
+            cmake --install $BUILD_DIR --component MLX
+            # Override CGO flags to point to the amd64 build directory
+            MLX_CGO_CFLAGS="-O3 -I$(pwd)/$BUILD_DIR/_deps/mlx-c-src -mmacosx-version-min=14.0"
+            MLX_CGO_LDFLAGS="-L$(pwd)/$BUILD_DIR/lib/ollama -lmlxc -lmlx -Wl,-rpath,@executable_path -lc++ -framework Accelerate -mmacosx-version-min=14.0"
+        else
+            BUILD_DIR=build
+            cmake --preset MLX \
+                -DOLLAMA_RUNNER_DIR=./ \
+                -DCMAKE_OSX_DEPLOYMENT_TARGET=14.0 \
                 -DCMAKE_INSTALL_PREFIX=$INSTALL_PREFIX
-            cmake --build build/darwin-$ARCH --target ggml-cpu -j
-            cmake --install build/darwin-$ARCH --component CPU
+            cmake --build --preset MLX --parallel
+            cmake --install $BUILD_DIR --component MLX
+            # Use default CGO flags from mlx.go for arm64
+            MLX_CGO_CFLAGS="-O3 -I$(pwd)/$BUILD_DIR/_deps/mlx-c-src -mmacosx-version-min=14.0"
+            MLX_CGO_LDFLAGS="-L$(pwd)/$BUILD_DIR/lib/ollama -lmlxc -lmlx -Wl,-rpath,@executable_path -lc++ -framework Metal -framework Foundation -framework Accelerate -mmacosx-version-min=14.0"
         fi
+        GOOS=darwin GOARCH=$ARCH CGO_ENABLED=1 CGO_CFLAGS="$MLX_CGO_CFLAGS" CGO_LDFLAGS="$MLX_CGO_LDFLAGS" go build -tags mlx -o $INSTALL_PREFIX/imagegen ./x/imagegen/cmd/engine
+        GOOS=darwin GOARCH=$ARCH CGO_ENABLED=1 go build -o $INSTALL_PREFIX .
     done
 }
 
@@ -61,10 +82,12 @@ _sign_darwin() {
     status "Creating universal binary..."
     mkdir -p dist/darwin
     lipo -create -output dist/darwin/ollama dist/darwin-*/ollama
+    lipo -create -output dist/darwin/imagegen dist/darwin-*/imagegen
     chmod +x dist/darwin/ollama
+    chmod +x dist/darwin/imagegen
 
     if [ -n "$APPLE_IDENTITY" ]; then
-        for F in dist/darwin/ollama dist/darwin-amd64/lib/ollama/*; do
+        for F in dist/darwin/ollama dist/darwin-*/lib/ollama/* dist/darwin/imagegen; do
             codesign -f --timestamp -s "$APPLE_IDENTITY" --identifier ai.ollama.ollama --options=runtime $F
         done
 
@@ -131,17 +154,23 @@ _build_macapp() {
     mkdir -p dist/Ollama.app/Contents/Resources
     if [ -d dist/darwin-amd64 ]; then
         lipo -create -output dist/Ollama.app/Contents/Resources/ollama dist/darwin-amd64/ollama dist/darwin-arm64/ollama
-        cp dist/darwin-amd64/lib/ollama/*.so dist/darwin-amd64/lib/ollama/*.dylib dist/Ollama.app/Contents/Resources/
+        lipo -create -output dist/Ollama.app/Contents/Resources/imagegen dist/darwin-amd64/imagegen dist/darwin-arm64/imagegen
+        for F in dist/darwin-amd64/lib/ollama/*mlx*.dylib ; do
+            lipo -create -output dist/darwin/$(basename $F) $F dist/darwin-arm64/lib/ollama/$(basename $F)
+        done
+        cp dist/darwin-*/lib/ollama/*.so dist/darwin-*/lib/ollama/*.dylib dist/Ollama.app/Contents/Resources/
+        cp dist/darwin/*.dylib dist/Ollama.app/Contents/Resources/
     else
         cp -a dist/darwin/ollama dist/Ollama.app/Contents/Resources/ollama
         cp dist/darwin/*.so dist/darwin/*.dylib dist/Ollama.app/Contents/Resources/
     fi
+    cp -a dist/darwin/imagegen dist/Ollama.app/Contents/Resources/imagegen
     chmod a+x dist/Ollama.app/Contents/Resources/ollama
 
     # Sign
     if [ -n "$APPLE_IDENTITY" ]; then
         codesign -f --timestamp -s "$APPLE_IDENTITY" --identifier ai.ollama.ollama --options=runtime dist/Ollama.app/Contents/Resources/ollama
-        for lib in dist/Ollama.app/Contents/Resources/*.so dist/Ollama.app/Contents/Resources/*.dylib ; do
+        for lib in dist/Ollama.app/Contents/Resources/*.so dist/Ollama.app/Contents/Resources/*.dylib dist/Ollama.app/Contents/Resources/imagegen ; do
             codesign -f --timestamp -s "$APPLE_IDENTITY" --identifier ai.ollama.ollama --options=runtime ${lib}
         done
         codesign -f --timestamp -s "$APPLE_IDENTITY" --identifier com.electron.ollama --deep --options=runtime dist/Ollama.app
@@ -149,7 +178,7 @@ _build_macapp() {
 
     rm -f dist/Ollama-darwin.zip
     ditto -c -k --keepParent dist/Ollama.app dist/Ollama-darwin.zip
-    (cd dist/Ollama.app/Contents/Resources/; tar -cf - ollama *.so *.dylib) | gzip -9vc > dist/ollama-darwin.tgz
+    (cd dist/Ollama.app/Contents/Resources/; tar -cf - ollama imagegen *.so *.dylib) | gzip -9vc > dist/ollama-darwin.tgz
 
     # Notarize and Staple
     if [ -n "$APPLE_IDENTITY" ]; then

scripts/build_linux.sh

@@ -48,6 +48,55 @@ if echo $PLATFORM | grep "amd64" > /dev/null; then
         .
 fi
 
+# Deduplicate CUDA libraries across mlx_* and cuda_* directories
+deduplicate_cuda_libs() {
+    local base_dir="$1"
+    echo "Deduplicating CUDA libraries in ${base_dir}..."
+
+    # Find all mlx_cuda_* directories
+    for mlx_dir in "${base_dir}"/lib/ollama/mlx_cuda_*; do
+        [ -d "${mlx_dir}" ] || continue
+
+        # Extract CUDA version (e.g., v12, v13)
+        cuda_version=$(basename "${mlx_dir}" | sed 's/mlx_cuda_//')
+        cuda_dir="${base_dir}/lib/ollama/cuda_${cuda_version}"
+
+        # Skip if corresponding cuda_* directory doesn't exist
+        [ -d "${cuda_dir}" ] || continue
+
+        echo "  Checking ${mlx_dir} against ${cuda_dir}..."
+
+        # Find all .so* files in mlx directory
+        find "${mlx_dir}" -type f -name "*.so*" | while read mlx_file; do
+            filename=$(basename "${mlx_file}")
+            cuda_file="${cuda_dir}/${filename}"
+
+            # Skip if file doesn't exist in cuda directory
+            [ -f "${cuda_file}" ] || continue
+
+            # Compare checksums
+            mlx_sum=$(sha256sum "${mlx_file}" | awk '{print $1}')
+            cuda_sum=$(sha256sum "${cuda_file}" | awk '{print $1}')
+
+            if [ "${mlx_sum}" = "${cuda_sum}" ]; then
+                echo "    Deduplicating ${filename}"
+                # Calculate relative path from mlx_dir to cuda_dir
+                rel_path="../cuda_${cuda_version}/${filename}"
+                rm -f "${mlx_file}"
+                ln -s "${rel_path}" "${mlx_file}"
+            fi
+        done
+    done
+}
+
+# Run deduplication for each platform output directory
+if echo $PLATFORM | grep "," > /dev/null ; then
+    deduplicate_cuda_libs "./dist/linux_amd64"
+    deduplicate_cuda_libs "./dist/linux_arm64"
+elif echo $PLATFORM | grep "amd64\|arm64" > /dev/null ; then
+    deduplicate_cuda_libs "./dist"
+fi
+
 # buildx behavior changes for single vs. multiplatform
 echo "Compressing linux tar bundles..."
 if echo $PLATFORM | grep "," > /dev/null ; then