mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-06-12 02:38:19 -04:00
Code Issues Packages Projects Releases Wiki Activity

WIP

Browse Source
This commit is contained in:
Ettore Di Giacinto
2025-07-23 21:18:47 +02:00
parent 5f7ece3e94
commit 3f52776a1c
4 changed files with 23 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/cpp/llama-cpp/CMakeLists.txt
View File

@@ -17,6 +17,8 @@ if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
include_directories("${HOMEBREW_DEFAULT_PREFIX}/include")
endif()
set(Protobuf_USE_STATIC_LIBS OFF)
set(gRPC_USE_STATIC_LIBS OFF)
find_package(absl CONFIG REQUIRED)
find_package(Protobuf CONFIG REQUIRED)
find_package(gRPC CONFIG REQUIRED)

35
backend/cpp/llama-cpp/Makefile
View File

@@ -9,7 +9,7 @@ ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
TARGET?=--target grpc-server
# Disable Shared libs as we are linking on static gRPC and we can't mix shared and static
CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF -DLLAMA_CURL=OFF
CMAKE_ARGS+=-DBUILD_SHARED_LIBS=ON -DLLAMA_CURL=OFF -DGGML_CPU_ALL_VARIANTS=ON -DGGML_BACKEND_DL=ON
CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
ifeq ($(NATIVE),false)
@@ -89,33 +89,12 @@ else
LLAMA_VERSION=$(LLAMA_VERSION) $(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../$(VARIANT) grpc-server
endif
llama-cpp-avx2: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx2-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx2-build purge
$(info ${GREEN}I llama-cpp build info:avx2${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-cpp-avx2-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx2-build/grpc-server llama-cpp-avx2
llama-cpp-avx512: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx512-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx512-build purge
$(info ${GREEN}I llama-cpp build info:avx512${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-cpp-avx512-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx512-build/grpc-server llama-cpp-avx512
llama-cpp-avx: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx-build purge
$(info ${GREEN}I llama-cpp build info:avx${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off" $(MAKE) VARIANT="llama-cpp-avx-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-avx-build/grpc-server llama-cpp-avx
llama-cpp-fallback: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-fallback-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-fallback-build purge
$(info ${GREEN}I llama-cpp build info:fallback${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off" $(MAKE) VARIANT="llama-cpp-fallback-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-fallback-build/grpc-server llama-cpp-fallback
llama-cpp: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-build
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-build purge
$(info ${GREEN}I llama-cpp build info:${RESET})
CMAKE_ARGS="$(CMAKE_ARGS)" $(MAKE) VARIANT="llama-cpp-build" build-llama-cpp-grpc-server
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-build/grpc-server llama-cpp
llama-cpp-grpc: llama.cpp
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build

32
backend/cpp/llama-cpp/run.sh
View File

@@ -6,34 +6,9 @@ CURDIR=$(dirname "$(realpath $0)")
cd /
echo "CPU info:"
grep -e "model\sname" /proc/cpuinfo | head -1
grep -e "flags" /proc/cpuinfo | head -1
BINARY=llama-cpp-fallback
if grep -q -e "\savx\s" /proc/cpuinfo ; then
echo "CPU: AVX found OK"
if [ -e $CURDIR/llama-cpp-avx ]; then
BINARY=llama-cpp-avx
fi
fi
if grep -q -e "\savx2\s" /proc/cpuinfo ; then
echo "CPU: AVX2 found OK"
if [ -e $CURDIR/llama-cpp-avx2 ]; then
BINARY=llama-cpp-avx2
fi
fi
# Check avx 512
if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
echo "CPU: AVX512F found OK"
if [ -e $CURDIR/llama-cpp-avx512 ]; then
BINARY=llama-cpp-avx512
fi
fi
BINARY=llama-cpp
## P2P/GRPC mode
if [ -n "$LLAMACPP_GRPC_SERVERS" ]; then
if [ -e $CURDIR/llama-cpp-grpc ]; then
BINARY=llama-cpp-grpc
@@ -56,6 +31,3 @@ fi
echo "Using binary: $BINARY"
exec $CURDIR/$BINARY "$@"
# In case we fail execing, just run fallback
exec $CURDIR/llama-cpp-fallback "$@"