LocalAI/backend/cpp/llama/CMakeLists.txt
Ettore Di Giacinto 6d5bde860b
Some checks are pending
Explorer deployment / build-linux (push) Waiting to run
GPU tests / ubuntu-latest (1.21.x) (push) Waiting to run
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Waiting to run
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, extras, latest-gpu-hipblas-extras, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -hipblas-extras) (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, latest-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, extras, latest-gpu-intel-f16-extras, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-… (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, extras, latest-gpu-intel-f32-extras, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-… (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, extras, latest-gpu-nvidia-cuda-11-extras, latest-aio-gpu-nvidia-cuda-11, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11-extras) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, extras, latest-gpu-nvidia-cuda-12-extras, latest-aio-gpu-nvidia-cuda-12, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12-extras) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, core, latest-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, core, latest-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32) (push) Waiting to run
build container images / core-image-build (-aio-cpu, ubuntu:22.04, , true, core, latest-cpu, latest-aio-cpu, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, arc-runner-set, false, auto, ) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, true, core, latest-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, true, core, latest-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, vulkan, true, core, latest-gpu-vulkan, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan) (push) Waiting to run
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, core, latest-nvidia-l4t-arm64, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64) (push) Waiting to run
Security Scan / tests (push) Waiting to run
Tests extras backends / tests-transformers (push) Waiting to run
Tests extras backends / tests-rerankers (push) Waiting to run
Tests extras backends / tests-diffusers (push) Waiting to run
Tests extras backends / tests-coqui (push) Waiting to run
tests / tests-linux (1.21.x) (push) Waiting to run
tests / tests-aio-container (push) Waiting to run
tests / tests-apple (1.21.x) (push) Waiting to run
feat(llama.cpp): upgrade and use libmtmd (#5379)
* WIP

* wip

* wip

* Make it compile

* Update json.hpp

* this shouldn't be private for now

* Add logs

* Reset auto detected template

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

* Re-enable grammars

* This seems to be broken - 360a9c98e1 (diff-a18a8e64e12a01167d8e98fc)[…]cccf0d4eed09d76d879L2998-L3207

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

* Placeholder

* Simplify image loading

* use completion type

* disable streaming

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

* correctly return timings

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

* Remove some debug logging

* Adapt tests

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

* Keep header

* embedding: do not use oai type

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

* Sync from server.cpp

* Use utils and json directly from llama.cpp

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

* Sync with upstream

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

* fix: copy json.hpp from the correct location

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

* fix: add httplib

* sync llama.cpp

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

* Embeddiongs: set OAICOMPAT_TYPE_EMBEDDING

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

* feat: sync with server.cpp by including it

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

* make it darwin-compatible

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2025-05-17 16:02:53 +02:00

90 lines
No EOL
3.2 KiB
CMake

## XXX: In some versions of CMake clip wasn't being built before llama.
## This is an hack for now, but it should be fixed in the future.
# set(TARGET myclip)
# add_library(${TARGET} clip.cpp clip.h clip-impl.h llava.cpp llava.h)
# install(TARGETS ${TARGET} LIBRARY)
# target_include_directories(myclip PUBLIC .)
# target_include_directories(myclip PUBLIC ../..)
# target_include_directories(myclip PUBLIC ../../common)
# target_link_libraries(${TARGET} PRIVATE common ggml llama ${CMAKE_THREAD_LIBS_INIT})
# target_compile_features(${TARGET} PRIVATE cxx_std_11)
# if (NOT MSVC)
# target_compile_options(${TARGET} PRIVATE -Wno-cast-qual) # stb_image.h
# endif()
# END CLIP hack
set(TARGET grpc-server)
set(CMAKE_CXX_STANDARD 17)
cmake_minimum_required(VERSION 3.15)
set(TARGET grpc-server)
set(_PROTOBUF_LIBPROTOBUF libprotobuf)
set(_REFLECTION grpc++_reflection)
if (${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
add_library(hw_grpc_proto
${hw_grpc_srcs}
${hw_grpc_hdrs}
${hw_proto_srcs}
${hw_proto_hdrs} )
add_executable(${TARGET} grpc-server.cpp utils.hpp json.hpp httplib.h)
target_include_directories(${TARGET} PRIVATE ../llava)
target_include_directories(${TARGET} PRIVATE ${CMAKE_SOURCE_DIR})
target_link_libraries(${TARGET} PRIVATE common 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()