mirror of
https://github.com/mudler/LocalAI.git
synced 2024-06-07 19:40:48 +00:00
128694213f
* wip: llama.cpp c++ gRPC server Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * make it work, attach it to the build process Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * update deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: add protobuf dep Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * try fix protobuf on cmake * cmake: workarounds Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * add packages * cmake: use fixed version of grpc Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * cmake(grpc): install locally * install grpc Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * install required deps for grpc on debian bullseye Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * debug * debug * Fixups * no need to install cmake manually Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: fixup macOS * use brew whenever possible Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * macOS fixups * debug * fix container build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * workaround * try mac https://stackoverflow.com/questions/23905661/on-mac-g-clang-fails-to-search-usr-local-include-and-usr-local-lib-by-def * Disable temp. arm64 docker image builds --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
44 lines
1.7 KiB
Makefile
44 lines
1.7 KiB
Makefile
|
|
LLAMA_VERSION?=24ba3d829e31a6eda3fa1723f692608c2fa3adda
|
|
|
|
CMAKE_ARGS?=
|
|
BUILD_TYPE?=
|
|
|
|
# If build type is cublas, then we set -DLLAMA_CUBLAS=ON to CMAKE_ARGS automatically
|
|
ifeq ($(BUILD_TYPE),cublas)
|
|
CMAKE_ARGS+=-DLLAMA_CUBLAS=ON
|
|
# If build type is openblas then we set -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
|
|
# to CMAKE_ARGS automatically
|
|
else ifeq ($(BUILD_TYPE),openblas)
|
|
CMAKE_ARGS+=-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
|
|
# If build type is clblast (openCL) we set -DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
|
|
else ifeq ($(BUILD_TYPE),clblast)
|
|
CMAKE_ARGS+=-DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
|
|
# If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++
|
|
else ifeq ($(BUILD_TYPE),hipblas)
|
|
CMAKE_ARGS+=-DLLAMA_HIPBLAS=ON
|
|
endif
|
|
|
|
llama.cpp:
|
|
git clone --recurse-submodules https://github.com/ggerganov/llama.cpp llama.cpp
|
|
cd llama.cpp && git checkout -b build $(LLAMA_VERSION) && git submodule update --init --recursive --depth 1
|
|
|
|
llama.cpp/examples/grpc-server:
|
|
mkdir -p llama.cpp/examples/grpc-server
|
|
cp -r $(abspath ./)/CMakeLists.txt llama.cpp/examples/grpc-server/
|
|
cp -r $(abspath ./)/grpc-server.cpp llama.cpp/examples/grpc-server/
|
|
echo "add_subdirectory(grpc-server)" >> llama.cpp/examples/CMakeLists.txt
|
|
|
|
rebuild:
|
|
cp -rfv $(abspath ./)/CMakeLists.txt llama.cpp/examples/grpc-server/
|
|
cp -rfv $(abspath ./)/grpc-server.cpp llama.cpp/examples/grpc-server/
|
|
rm -rf grpc-server
|
|
$(MAKE) grpc-server
|
|
|
|
clean:
|
|
rm -rf llama.cpp
|
|
rm -rf grpc-server
|
|
|
|
grpc-server: llama.cpp llama.cpp/examples/grpc-server
|
|
cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release
|
|
cp llama.cpp/build/bin/grpc-server .
|