LocalAI/backend/cpp/llama/Makefile
Ettore Di Giacinto 530bec9c64
feat(llama.cpp): do not specify backends to autoload and add llama.cpp variants (#2232)
* feat(initializer): do not specify backends to autoload

We can simply try to autoload the backends extracted in the asset dir.
This will allow to build variants of the same backend (for e.g. with different instructions sets),
so to have a single binary for all the variants.

Signed-off-by: mudler <mudler@localai.io>

* refactor(prepare): refactor out llama.cpp prepare steps

Make it so are idempotent and that we can re-build

Signed-off-by: mudler <mudler@localai.io>

* [TEST] feat(build): build noavx version along

Signed-off-by: mudler <mudler@localai.io>

* build: make build parallel

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* build: do not override CMAKE_ARGS

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* build: add fallback variant

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(huggingface-langchain): fail if no token is set

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(huggingface-langchain): rename

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: do not autoload local-store

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix: give priority between the listed backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: mudler <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-04 17:56:12 +02:00

69 lines
2.3 KiB
Makefile

LLAMA_VERSION?=
CMAKE_ARGS?=
BUILD_TYPE?=
ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
# 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 clblas (openCL) we set -DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
else ifeq ($(BUILD_TYPE),clblas)
CMAKE_ARGS+=-DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
# If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++
else ifeq ($(BUILD_TYPE),hipblas)
CMAKE_ARGS+=-DLLAMA_HIPBLAS=ON
# If it's OSX, DO NOT embed the metal library - -DLLAMA_METAL_EMBED_LIBRARY=ON requires further investigation
# But if it's OSX without metal, disable it here
else ifeq ($(OS),darwin)
ifneq ($(BUILD_TYPE),metal)
CMAKE_ARGS+=-DLLAMA_METAL=OFF
endif
endif
ifeq ($(BUILD_TYPE),sycl_f16)
CMAKE_ARGS+=-DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON
endif
ifeq ($(BUILD_TYPE),sycl_f32)
CMAKE_ARGS+=-DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
endif
llama.cpp:
git clone --recurse-submodules https://github.com/ggerganov/llama.cpp llama.cpp
if [ -z "$(LLAMA_VERSION)" ]; then \
exit 1; \
fi
cd llama.cpp && git checkout -b build $(LLAMA_VERSION) && git submodule update --init --recursive --depth 1
llama.cpp/examples/grpc-server: llama.cpp
mkdir -p llama.cpp/examples/grpc-server
bash prepare.sh
rebuild:
bash prepare.sh
rm -rf grpc-server
$(MAKE) grpc-server
purge:
rm -rf llama.cpp/build
rm -rf llama.cpp/examples/grpc-server
rm -rf grpc-server
clean: purge
rm -rf llama.cpp
grpc-server: llama.cpp llama.cpp/examples/grpc-server
@echo "Building grpc-server with $(BUILD_TYPE) build type and $(CMAKE_ARGS)"
ifneq (,$(findstring sycl,$(BUILD_TYPE)))
bash -c "source $(ONEAPI_VARS); \
cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release"
else
cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release
endif
cp llama.cpp/build/bin/grpc-server .