diff --git a/README.md b/README.md
index 137c1ba..f51cfd3 100644
--- a/README.md
+++ b/README.md
@@ -38,10 +38,12 @@ run-pipeline.sh            → Run finetune → merge/convert → run in sequenc
 
 `setup.sh` will:
 1. Create a Python virtual environment and install Python dependencies
-2. Clone [llama.cpp](https://github.com/ggml-org/llama.cpp)
-3. Build llama.cpp with your selected GPU backend
+2. Clone [llama.cpp](https://github.com/ggml-org/llama.cpp) or symlink an existing build
+3. Build llama.cpp with your selected GPU backend (skip if using existing)
 4. Install llama-cpp-python bindings with matching backend flags
 
+**Using an existing llama.cpp build:** Choose option 2 and provide the absolute path to your existing build. Setup will create a symlink at `./llama.cpp`.
+
 ### Backend Selection
 
 | Choice | Backend | Requirements |
diff --git a/setup.sh b/setup.sh
index b4222db..a2b3007 100755
--- a/setup.sh
+++ b/setup.sh
@@ -11,7 +11,7 @@ python -m venv venv
 source venv/bin/activate
 pip install -r requirements.txt
 
-# Prompt for backend
+# Select backend for llama-cpp-python binding
 echo ""
 echo "Select llama.cpp backend:"
 echo "  1) CUDA (NVIDIA GPU)"
@@ -21,59 +21,77 @@ echo "  4) CPU only"
 echo ""
 read -p "Enter choice (1-4): " BACKEND
 
-# Clone llama.cpp
+# Ask if fresh build or existing
 echo ""
-echo "Cloning llama.cpp..."
-if [ ! -d "llama.cpp" ]; then
+echo "Would you like to:"
+echo "  1) Clone and build a fresh copy of llama.cpp"
+echo "  2) Use an existing llama.cpp build (symlink)"
+echo ""
+read -p "Enter choice (1-2): " BUILD_CHOICE
+
+if [ "$BUILD_CHOICE" = "1" ]; then
+    echo ""
+    echo "Cloning llama.cpp..."
     git clone https://github.com/ggml-org/llama.cpp.git
+
+    # Build llama.cpp with correct flags
+    echo ""
+    echo "Building llama.cpp..."
+    cd llama.cpp
+
+    BUILD_FAILED=0
+
+    case $BACKEND in
+        1)
+            echo "Building with CUDA support..."
+            cmake -B build -DGGML_CUDA=ON || BUILD_FAILED=1
+            [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
+            ;;
+        2)
+            echo "Building with ROCm support..."
+            HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
+                cmake -S . -B build -DGGML_HIP=ON -DGPU_TARGETS=gfx1030 -DCMAKE_BUILD_TYPE=Release || BUILD_FAILED=1
+            [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
+            ;;
+        3)
+            echo "Building with Vulkan support..."
+            cmake -B build -DGGML_VULKAN=1 || BUILD_FAILED=1
+            [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
+            ;;
+        4)
+            echo "Building CPU-only..."
+            cmake -B build || BUILD_FAILED=1
+            [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
+            ;;
+        *)
+            echo "Invalid choice. Building CPU-only."
+            cmake -B build || BUILD_FAILED=1
+            [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
+            ;;
+    esac
+
+    cd ..
 else
-    echo "llama.cpp already exists, skipping clone."
+    read -p "Enter absolute path to existing llama.cpp build: " LLAMA_CPP_PATH
+
+    # Validate path
+    if [ ! -d "$LLAMA_CPP_PATH" ]; then
+        echo "Error: Directory $LLAMA_CPP_PATH does not exist."
+        exit 1
+    fi
+
+    # Resolve to absolute path
+    LLAMA_CPP_PATH=$(realpath "$LLAMA_CPP_PATH")
+
+    echo ""
+    echo "Creating symlink: ./llama.cpp -> $LLAMA_CPP_PATH"
+    ln -sfn "$LLAMA_CPP_PATH" llama.cpp
 fi
 
-# Build llama.cpp with correct flags
-echo ""
-echo "Building llama.cpp..."
-cd llama.cpp
-
-BUILD_FAILED=0
-
-case $BACKEND in
-    1)
-        echo "Building with CUDA support..."
-        cmake -B build -DGGML_CUDA=ON || BUILD_FAILED=1
-        [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
-        ;;
-    2)
-        echo "Building with ROCm support..."
-        HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
-            cmake -S . -B build -DGGML_HIP=ON -DGPU_TARGETS=gfx1030 -DCMAKE_BUILD_TYPE=Release || BUILD_FAILED=1
-        [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
-        ;;
-    3)
-        echo "Building with Vulkan support..."
-        cmake -B build -DGGML_VULKAN=1 || BUILD_FAILED=1
-        [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
-        ;;
-    4)
-        echo "Building CPU-only..."
-        cmake -B build || BUILD_FAILED=1
-        [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
-        ;;
-    *)
-        echo "Invalid choice. Building CPU-only."
-        cmake -B build || BUILD_FAILED=1
-        [ $BUILD_FAILED -eq 0 ] && cmake --build build --config Release -j$(nproc) || BUILD_FAILED=1
-        ;;
-esac
-
-cd ..
-
 # Install llama-cpp-python in main venv
 echo ""
 echo "Installing llama-cpp-python..."
 
-source venv/bin/activate
-
 case $BACKEND in
     1) CMAKE_ARGS="-DGGML_CUDA=on" ;;
     2) CMAKE_ARGS="-DGGML_HIP=on" ;;
@@ -81,6 +99,7 @@ case $BACKEND in
     *) CMAKE_ARGS="" ;;
 esac
 
+source venv/bin/activate
 eval "CMAKE_ARGS=\"$CMAKE_ARGS\" pip install llama-cpp-python"
 
 # Create convertgguf_venv for llama.cpp Python tools
@@ -94,7 +113,7 @@ echo ""
 echo "Setup complete! Configure the scripts and run:"
 echo "  bash run-pipeline.sh"
 
-if [ $BUILD_FAILED -ne 0 ]; then
+if [ -n "$BUILD_FAILED" ] && [ $BUILD_FAILED -ne 0 ]; then
     echo ""
     echo "Build failed. See the build guide for help:"
     echo "  https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md"