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]
90 lines
3.5 KiB
CMake
90 lines
3.5 KiB
CMake
set(TARGET grpc-server)
|
|
set(CMAKE_CXX_STANDARD 17)
|
|
cmake_minimum_required(VERSION 3.15)
|
|
set(TARGET grpc-server)
|
|
set(_PROTOBUF_LIBPROTOBUF libprotobuf)
|
|
set(_REFLECTION grpc++_reflection)
|
|
|
|
if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
|
|
# Set correct Homebrew install folder for Apple Silicon and Intel Macs
|
|
if (CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "arm64")
|
|
set(HOMEBREW_DEFAULT_PREFIX "/opt/homebrew")
|
|
else()
|
|
set(HOMEBREW_DEFAULT_PREFIX "/usr/local")
|
|
endif()
|
|
|
|
link_directories("${HOMEBREW_DEFAULT_PREFIX}/lib")
|
|
include_directories("${HOMEBREW_DEFAULT_PREFIX}/include")
|
|
endif()
|
|
|
|
find_package(absl CONFIG REQUIRED)
|
|
find_package(Protobuf CONFIG REQUIRED)
|
|
find_package(gRPC CONFIG REQUIRED)
|
|
|
|
find_program(_PROTOBUF_PROTOC protoc)
|
|
set(_GRPC_GRPCPP grpc++)
|
|
find_program(_GRPC_CPP_PLUGIN_EXECUTABLE grpc_cpp_plugin)
|
|
|
|
include_directories(${CMAKE_CURRENT_BINARY_DIR})
|
|
include_directories(${Protobuf_INCLUDE_DIRS})
|
|
|
|
message(STATUS "Using protobuf version ${Protobuf_VERSION} | Protobuf_INCLUDE_DIRS: ${Protobuf_INCLUDE_DIRS} | CMAKE_CURRENT_BINARY_DIR: ${CMAKE_CURRENT_BINARY_DIR}")
|
|
|
|
# Proto file
|
|
get_filename_component(hw_proto "../../../../../../backend/backend.proto" ABSOLUTE)
|
|
get_filename_component(hw_proto_path "${hw_proto}" PATH)
|
|
|
|
# Generated sources
|
|
set(hw_proto_srcs "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.cc")
|
|
set(hw_proto_hdrs "${CMAKE_CURRENT_BINARY_DIR}/backend.pb.h")
|
|
set(hw_grpc_srcs "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.cc")
|
|
set(hw_grpc_hdrs "${CMAKE_CURRENT_BINARY_DIR}/backend.grpc.pb.h")
|
|
|
|
add_custom_command(
|
|
OUTPUT "${hw_proto_srcs}" "${hw_proto_hdrs}" "${hw_grpc_srcs}" "${hw_grpc_hdrs}"
|
|
COMMAND ${_PROTOBUF_PROTOC}
|
|
ARGS --grpc_out "${CMAKE_CURRENT_BINARY_DIR}"
|
|
--cpp_out "${CMAKE_CURRENT_BINARY_DIR}"
|
|
-I "${hw_proto_path}"
|
|
--plugin=protoc-gen-grpc="${_GRPC_CPP_PLUGIN_EXECUTABLE}"
|
|
"${hw_proto}"
|
|
DEPENDS "${hw_proto}")
|
|
|
|
# hw_grpc_proto: force STATIC. Under the CPU_ALL_VARIANTS build BUILD_SHARED_LIBS=ON
|
|
# (ggml/llama become shared), which would otherwise make this glue library a DSO. As a
|
|
# DSO it references the hidden-visibility symbols in the static libprotobuf.a, which the
|
|
# linker cannot satisfy ("hidden symbol ... in libprotobuf.a is referenced by DSO").
|
|
# Keeping it STATIC links protobuf/gRPC directly into the grpc-server executable while
|
|
# only ggml/llama stay shared. No effect on the static variants (already BUILD_SHARED_LIBS=OFF).
|
|
add_library(hw_grpc_proto STATIC
|
|
${hw_grpc_srcs}
|
|
${hw_grpc_hdrs}
|
|
${hw_proto_srcs}
|
|
${hw_proto_hdrs} )
|
|
|
|
add_executable(${TARGET} grpc-server.cpp json.hpp httplib.h)
|
|
|
|
target_include_directories(${TARGET} PRIVATE ../llava)
|
|
target_include_directories(${TARGET} PRIVATE ${CMAKE_SOURCE_DIR})
|
|
|
|
# Upstream llama.cpp renamed the `common` helpers library to `llama-common`.
|
|
# Forks that branched before the rename (e.g. llama-cpp-turboquant) still
|
|
# expose it as `common`. Detect which one is present so the same CMakeLists
|
|
# drives both builds — otherwise an unresolved name silently degrades to a
|
|
# plain `-l` flag and the PUBLIC include dir (where common.h lives) is lost.
|
|
if (TARGET llama-common)
|
|
set(_LLAMA_COMMON_TARGET llama-common)
|
|
else()
|
|
set(_LLAMA_COMMON_TARGET common)
|
|
endif()
|
|
|
|
target_link_libraries(${TARGET} PRIVATE ${_LLAMA_COMMON_TARGET} llama mtmd ${CMAKE_THREAD_LIBS_INIT} absl::flags hw_grpc_proto
|
|
absl::flags_parse
|
|
gRPC::${_REFLECTION}
|
|
gRPC::${_GRPC_GRPCPP}
|
|
protobuf::${_PROTOBUF_LIBPROTOBUF})
|
|
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
|
if(TARGET BUILD_INFO)
|
|
add_dependencies(${TARGET} BUILD_INFO)
|
|
endif()
|