hf_text-generation-inference/backends/trtllm/CMakeLists.txt

72 lines
3.4 KiB
CMake

cmake_minimum_required(VERSION 3.20)
if (NOT DEFINED CMAKE_CXX_COMPILER_LAUNCHER AND CMAKE_BUILD_TYPE STREQUAL "Debug")
find_program(CCACHE_EXECUTABLE "ccache")
if (CCACHE_EXECUTABLE)
message(STATUS "Using ccache")
set(CMAKE_CXX_COMPILER_LAUNCHER "${CCACHE_EXECUTABLE}" CACHE PATH "Path to ccache" FORCE)
endif ()
endif ()
project(tgi-trtllm-backend VERSION 1.0.0)
set(CMAKE_CXX_STANDARD 20)
include(FetchContent)
include(ExternalProject)
option(TGI_TRTLLM_BACKEND_BUILD_TESTS "Enable building the unittests suite" OFF)
option(TGI_TRTLLM_BACKEND_BUILD_EXAMPLES "Enable building the examples suite" OFF)
set(TGI_TRTLLM_BACKEND_TARGET_CUDA_ARCH_LIST "89-real" CACHE STRING "List of CUDA architectures to support")
set(TGI_TRTLLM_BACKEND_TRT_ROOT "/usr/local/tensorrt" CACHE STRING "Path where TensorRT libraries and headers are located")
set(TGI_TRTLLM_BACKEND_TRT_INCLUDE_DIR "${TGI_TRTLLM_BACKEND_TRT_ROOT}/include" CACHE STRING "Path where TensorRT headers are located")
set(TGI_TRTLLM_BACKEND_TRT_LIB_DIR "${TGI_TRTLLM_BACKEND_TRT_ROOT}/lib" CACHE STRING "Path where TensorRT libraries are located")
# We are using nvidia-ml to query at runtime device information to enable some architecture-specific features
find_package(CUDAToolkit 12.5 REQUIRED COMPONENTS CUDA::cudart CUDA::nvml)
#### External dependencies ####
include(cmake/fmt.cmake)
include(cmake/json.cmake)
include(cmake/spdlog.cmake)
include(cmake/trtllm.cmake)
# Let's build TRTLLM as part of CMake
add_subdirectory("${trtllm_SOURCE_DIR}/cpp" "${trtllm_SOURCE_DIR}/..")
# Tell CMake to need try to override the RPATH for executorWorker as it has not information on how to do so
set_target_properties(executorWorker PROPERTIES SKIP_BUILD_RPATH TRUE)
# TGI TRTLLM Backend definition
add_library(tgi_trtllm_backend_impl STATIC include/backend.h lib/backend.cpp include/hardware.h)
include_directories(${TGI_TRTLLM_BACKEND_TRT_INCLUDE_DIR})
target_include_directories(tgi_trtllm_backend_impl PRIVATE
$<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
$<INSTALL_INTERFACE:include>
)
target_include_directories(tgi_trtllm_backend_impl PUBLIC "${trtllm_SOURCE_DIR}/cpp/include")
target_link_libraries(tgi_trtllm_backend_impl PRIVATE tensorrt_llm nvinfer_plugin_tensorrt_llm tensorrt_llm_nvrtc_wrapper CUDA::cudart CUDA::nvml)
target_link_libraries(tgi_trtllm_backend_impl PUBLIC nlohmann_json::nlohmann_json spdlog::spdlog fmt::fmt)
# This install all the artifacts in CMAKE_INSTALL_PREFIX under include/ lib/ bin/ to make easy to link / find it back
install(TARGETS tgi_trtllm_backend_impl tensorrt_llm nvinfer_plugin_tensorrt_llm decoder_attention executorWorker)
install(FILES ${TRTLLM_NVRTC_WRAPPER_LIBRARY_PATH} ${TRTLLM_EXECUTOR_STATIC_LIBRARY_PATH} TYPE LIB)
#### Unit Tests ####
if (${TGI_TRTLLM_BACKEND_BUILD_TESTS})
message(STATUS "Building tests")
FetchContent_Declare(
Catch2
GIT_REPOSITORY https://github.com/catchorg/Catch2
GIT_TAG v3.6.0
)
FetchContent_MakeAvailable(Catch2)
# add_executable(tgi_trtllm_backend_tests tests/infer_test.cpp)
# target_link_libraries(tgi_trtllm_backend_tests PRIVATE tgi_trtllm_backend_impl Catch2::Catch2WithMain nlohmann_json::nlohmann_json spdlog::spdlog fmt::fmt CUDA::cudart CUDA::nvml)
list(APPEND CMAKE_MODULE_PATH ${catch2_SOURCE_DIR}/extras)
include(CTest)
include(Catch)
# catch_discover_tests(tgi_trtllm_backend_tests)
endif ()