Oracle/Unsloth-Finetune-Template
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add option to use existing llama.cpp build

Browse source
This commit is contained in:
Oracle 2026-06-02 16:39:02 +02:00
parent 80a91e278e
commit 1f4e9e119c
Signed by: Oracle
SSH key fingerprint: SHA256:x4/RtnjUyuHkdvmwNDsWSfcfF1V5PNr3OpriZqOvCX8
2 changed files with 69 additions and 48 deletions
Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -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 |

111
setup.sh
View file

@ -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"