mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-25 09:09:07 -04:00
e47c58656f
Replace the per-microarch avx/avx2/avx512/fallback multi-binary build on
x86 with a single grpc-server plus the dlopen-able libggml-cpu-*.so set
that ggml's backend registry selects at runtime by probing host CPU
features. One build instead of four, broader microarch coverage (adds
alderlake AVX-VNNI, zen4 AVX512-BF16, sapphirerapids AMX), and the
shell-side /proc/cpuinfo probing in run.sh goes away.
Build/link notes:
- CPU_ALL_VARIANTS requires GGML_BACKEND_DL + BUILD_SHARED_LIBS=ON, so
ggml/llama become shared objects. SHARED_LIBS is now a make variable
(default OFF) so the override survives the recursive sub-make into the
VARIANT build dir instead of being re-clobbered by the base flags.
- The cpu-all target also builds "--target ggml": the per-microarch
backends are runtime-dlopened, not link deps, so they only compile via
ggml's add_dependencies().
- hw_grpc_proto is pinned STATIC. Under BUILD_SHARED_LIBS=ON it would
otherwise become a DSO referencing hidden-visibility symbols in the
static libprotobuf.a, which fails to link ("hidden symbol ... is
referenced by DSO"). Keeping it static links gRPC/protobuf into the
executable while only ggml/llama stay shared, so no PIC or base-image
change is required.
- package.sh bundles the libggml-*.so set into package/lib; ggml finds
them by scanning the bundled ld.so directory (/proc/self/exe), which
run.sh launches from.
Scope: x86 only. arm64/darwin keep the single fallback build. The
ik-llama-cpp / turboquant forks and the other ggml C++ backends are
unchanged; the same recipe applies but is out of scope here.
Validated with a full docker build plus a live inference smoke test:
the model loads, ggml selects the AVX512_BF16 variant on a Zen-class
host, and tokens generate correctly.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]
203 lines
9.5 KiB
Makefile
203 lines
9.5 KiB
Makefile
|
|
LLAMA_VERSION?=be4a6a63eb2b848e19c277bdcf2bd399e8af76d9
|
|
LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
|
|
|
|
CMAKE_ARGS?=
|
|
BUILD_TYPE?=
|
|
NATIVE?=false
|
|
ONEAPI_VARS?=/opt/intel/oneapi/setvars.sh
|
|
TARGET?=--target grpc-server
|
|
JOBS?=$(shell nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 1)
|
|
ARCH?=$(shell uname -m)
|
|
|
|
# Shared libs default to OFF: we link static gRPC and the avx/avx2/avx512/fallback
|
|
# variants are fully static. The CPU_ALL_VARIANTS build flips SHARED_LIBS=ON (ggml/llama
|
|
# become shared so the dynamic CPU backends work; gRPC stays static via its imported
|
|
# targets). SHARED_LIBS is a make variable, not an appended -D, so it survives the
|
|
# recursive sub-make into the VARIANT build dir (which re-parses this Makefile) instead
|
|
# of being re-clobbered by a second -DBUILD_SHARED_LIBS=OFF. EXTRA_CMAKE_ARGS is the hook
|
|
# the CPU_ALL_VARIANTS target uses to inject -DGGML_BACKEND_DL/-DGGML_CPU_ALL_VARIANTS.
|
|
SHARED_LIBS?=OFF
|
|
EXTRA_CMAKE_ARGS?=
|
|
CMAKE_ARGS+=-DBUILD_SHARED_LIBS=$(SHARED_LIBS) -DLLAMA_CURL=OFF $(EXTRA_CMAKE_ARGS)
|
|
|
|
CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
|
|
ifeq ($(NATIVE),false)
|
|
CMAKE_ARGS+=-DGGML_NATIVE=OFF -DLLAMA_OPENSSL=OFF
|
|
endif
|
|
# If build type is cublas, then we set -DGGML_CUDA=ON to CMAKE_ARGS automatically
|
|
ifeq ($(BUILD_TYPE),cublas)
|
|
CMAKE_ARGS+=-DGGML_CUDA=ON
|
|
# If build type is openblas then we set -DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
|
|
# to CMAKE_ARGS automatically
|
|
else ifeq ($(BUILD_TYPE),openblas)
|
|
CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
|
|
# If build type is clblas (openCL) we set -DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
|
|
else ifeq ($(BUILD_TYPE),clblas)
|
|
CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
|
|
# If it's hipblas we do have also to set CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++
|
|
else ifeq ($(BUILD_TYPE),hipblas)
|
|
ROCM_HOME ?= /opt/rocm
|
|
ROCM_PATH ?= /opt/rocm
|
|
export CXX=$(ROCM_HOME)/llvm/bin/clang++
|
|
export CC=$(ROCM_HOME)/llvm/bin/clang
|
|
AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201
|
|
ifeq ($(strip $(AMDGPU_TARGETS)),)
|
|
$(error AMDGPU_TARGETS is empty — set it to a comma-separated list of gfx targets e.g. gfx1100,gfx1101)
|
|
endif
|
|
CMAKE_ARGS+=-DGGML_HIP=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
|
|
else ifeq ($(BUILD_TYPE),vulkan)
|
|
CMAKE_ARGS+=-DGGML_VULKAN=1
|
|
else ifeq ($(OS),Darwin)
|
|
ifeq ($(BUILD_TYPE),)
|
|
BUILD_TYPE=metal
|
|
endif
|
|
ifneq ($(BUILD_TYPE),metal)
|
|
CMAKE_ARGS+=-DGGML_METAL=OFF
|
|
else
|
|
CMAKE_ARGS+=-DGGML_METAL=ON
|
|
CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
|
|
CMAKE_ARGS+=-DGGML_METAL_USE_BF16=ON
|
|
CMAKE_ARGS+=-DGGML_OPENMP=OFF
|
|
endif
|
|
TARGET+=--target ggml-metal
|
|
endif
|
|
|
|
ifeq ($(BUILD_TYPE),sycl_f16)
|
|
CMAKE_ARGS+=-DGGML_SYCL=ON \
|
|
-DCMAKE_C_COMPILER=icx \
|
|
-DCMAKE_CXX_COMPILER=icpx \
|
|
-DCMAKE_CXX_FLAGS="-fsycl" \
|
|
-DGGML_SYCL_F16=ON
|
|
endif
|
|
|
|
ifeq ($(BUILD_TYPE),sycl_f32)
|
|
CMAKE_ARGS+=-DGGML_SYCL=ON \
|
|
-DCMAKE_C_COMPILER=icx \
|
|
-DCMAKE_CXX_COMPILER=icpx \
|
|
-DCMAKE_CXX_FLAGS="-fsycl"
|
|
endif
|
|
|
|
INSTALLED_PACKAGES=$(CURDIR)/../grpc/installed_packages
|
|
INSTALLED_LIB_CMAKE=$(INSTALLED_PACKAGES)/lib/cmake
|
|
ADDED_CMAKE_ARGS=-Dabsl_DIR=${INSTALLED_LIB_CMAKE}/absl \
|
|
-DProtobuf_DIR=${INSTALLED_LIB_CMAKE}/protobuf \
|
|
-Dutf8_range_DIR=${INSTALLED_LIB_CMAKE}/utf8_range \
|
|
-DgRPC_DIR=${INSTALLED_LIB_CMAKE}/grpc \
|
|
-DCMAKE_CXX_STANDARD_INCLUDE_DIRECTORIES=${INSTALLED_PACKAGES}/include
|
|
build-llama-cpp-grpc-server:
|
|
# Conditionally build grpc for the llama backend to use if needed
|
|
ifdef BUILD_GRPC_FOR_BACKEND_LLAMA
|
|
$(MAKE) -C ../../grpc build
|
|
_PROTOBUF_PROTOC=${INSTALLED_PACKAGES}/bin/proto \
|
|
_GRPC_CPP_PLUGIN_EXECUTABLE=${INSTALLED_PACKAGES}/bin/grpc_cpp_plugin \
|
|
PATH="${INSTALLED_PACKAGES}/bin:${PATH}" \
|
|
CMAKE_ARGS="${CMAKE_ARGS} ${ADDED_CMAKE_ARGS}" \
|
|
LLAMA_VERSION=$(LLAMA_VERSION) \
|
|
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../$(VARIANT) grpc-server
|
|
else
|
|
echo "BUILD_GRPC_FOR_BACKEND_LLAMA is not defined."
|
|
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 -DGGML_BMI2=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 -DGGML_BMI2=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
|
|
|
|
# Single-build CPU backend using ggml's CPU_ALL_VARIANTS. Produces ONE grpc-server
|
|
# plus a set of dlopen-able libggml-cpu-*.so (sandybridge/haswell/skylakex/...) that
|
|
# ggml's backend registry selects from at runtime by probing host CPU features.
|
|
# Replaces the avx/avx2/avx512/fallback multi-binary build on x86.
|
|
#
|
|
# CPU_ALL_VARIANTS requires GGML_BACKEND_DL, which requires BUILD_SHARED_LIBS=ON, so we
|
|
# pass SHARED_LIBS=ON and the DL flags as make variables (NOT pre-expanded into the
|
|
# CMAKE_ARGS env string): command-line make variables propagate through every recursive
|
|
# sub-make, so the deepest VARIANT-dir build computes BUILD_SHARED_LIBS=ON consistently.
|
|
# Only ggml/llama go shared - gRPC is found via its static imported targets, so the
|
|
# grpc-server binary keeps static gRPC and only dynamically links ggml.
|
|
#
|
|
# TARGET adds "ggml": the per-microarch backends are runtime-dlopened, not link deps of
|
|
# grpc-server, so they only build because each is an add_dependencies() of the ggml target.
|
|
llama-cpp-cpu-all: llama.cpp
|
|
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build
|
|
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build purge
|
|
$(info ${GREEN}I llama-cpp build info:cpu-all-variants${RESET})
|
|
$(MAKE) SHARED_LIBS=ON EXTRA_CMAKE_ARGS="-DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON" TARGET="--target grpc-server --target ggml" VARIANT="llama-cpp-cpu-all-build" build-llama-cpp-grpc-server
|
|
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build/grpc-server llama-cpp-cpu-all
|
|
rm -rf ggml-shared-libs && mkdir -p ggml-shared-libs
|
|
find $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build/llama.cpp/build -name '*.so*' -exec cp -av {} ggml-shared-libs/ \;
|
|
@echo "Collected ggml shared backends:" && ls -la ggml-shared-libs/
|
|
|
|
llama-cpp-grpc: llama.cpp
|
|
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build
|
|
$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build purge
|
|
$(info ${GREEN}I llama-cpp build info:grpc${RESET})
|
|
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_RPC=ON -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" TARGET="--target grpc-server --target rpc-server" $(MAKE) VARIANT="llama-cpp-grpc-build" build-llama-cpp-grpc-server
|
|
cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build/grpc-server llama-cpp-grpc
|
|
|
|
llama-cpp-rpc-server: llama-cpp-grpc
|
|
cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build/llama.cpp/build/bin/rpc-server llama-cpp-rpc-server
|
|
|
|
llama.cpp:
|
|
mkdir -p llama.cpp
|
|
cd llama.cpp && \
|
|
git init && \
|
|
git remote add origin $(LLAMA_REPO) && \
|
|
git fetch --all --tags && \
|
|
git checkout -b build $(LLAMA_VERSION) && \
|
|
git submodule update --init --recursive --depth 1 --single-branch
|
|
|
|
llama.cpp/tools/grpc-server: llama.cpp
|
|
mkdir -p llama.cpp/tools/grpc-server
|
|
bash prepare.sh
|
|
|
|
rebuild:
|
|
bash prepare.sh
|
|
rm -rf grpc-server
|
|
$(MAKE) grpc-server
|
|
|
|
package:
|
|
bash package.sh
|
|
|
|
purge:
|
|
rm -rf llama.cpp/build
|
|
rm -rf llama.cpp/tools/grpc-server
|
|
rm -rf grpc-server
|
|
|
|
clean: purge
|
|
rm -rf llama.cpp
|
|
|
|
grpc-server: llama.cpp llama.cpp/tools/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 -j $(JOBS) $(TARGET)"
|
|
else
|
|
+cd llama.cpp && mkdir -p build && cd build && cmake .. $(CMAKE_ARGS) && cmake --build . --config Release -j $(JOBS) $(TARGET)
|
|
endif
|
|
cp llama.cpp/build/bin/grpc-server .
|