Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add some more information in CMakeLists.txt to correctly install executorWorker

This commit is contained in:
Morgan Funtowicz 2024-07-22 08:43:10 +00:00
parent d5464d2f80
commit 84153702d2
3 changed files with 13 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.dockerignore
View File

@ -2,4 +2,5 @@ aml
target target
server/transformers server/transformers
server/flash-attention server/flash-attention
cmake-build* cmake-build-debug/
cmake-build-release/

16
backends/trtllm/CMakeLists.txt
View File

@ -13,15 +13,20 @@ set(TGI_TRTLLM_BACKEND_TRT_ROOT "/usr/local/tensorrt" CACHE STRING "Path where T
set(TGI_TRTLLM_BACKEND_TRT_INCLUDE_DIR "${TGI_TRTLLM_BACKEND_TRT_ROOT}/include" CACHE STRING "Path where TensorRT headers are located") set(TGI_TRTLLM_BACKEND_TRT_INCLUDE_DIR "${TGI_TRTLLM_BACKEND_TRT_ROOT}/include" CACHE STRING "Path where TensorRT headers are located")
set(TGI_TRTLLM_BACKEND_TRT_LIB_DIR "${TGI_TRTLLM_BACKEND_TRT_ROOT}/lib" CACHE STRING "Path where TensorRT libraries are located") set(TGI_TRTLLM_BACKEND_TRT_LIB_DIR "${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 REQUIRED COMPONENTS CUDA::nvml)
#### External dependencies #### #### External dependencies ####
include(cmake/fmt.cmake) include(cmake/fmt.cmake)
include(cmake/json.cmake) include(cmake/json.cmake)
include(cmake/spdlog.cmake) include(cmake/spdlog.cmake)
include(cmake/trtllm.cmake) include(cmake/trtllm.cmake)
# Let's build TRTLLM as part of CMake
add_subdirectory("${trtllm_SOURCE_DIR}/cpp" "${trtllm_SOURCE_DIR}/..") add_subdirectory("${trtllm_SOURCE_DIR}/cpp" "${trtllm_SOURCE_DIR}/..")
find_package(CUDAToolkit REQUIRED COMPONENTS CUDA::nvml) # 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 # TGI TRTLLM Backend definition
add_library(tgi_trtllm_backend_impl STATIC include/backend.h lib/backend.cpp) add_library(tgi_trtllm_backend_impl STATIC include/backend.h lib/backend.cpp)
@ -31,7 +36,7 @@ target_include_directories(tgi_trtllm_backend_impl PRIVATE
$<INSTALL_INTERFACE:include> $<INSTALL_INTERFACE:include>
) )
target_include_directories(tgi_trtllm_backend_impl PUBLIC "${trtllm_SOURCE_DIR}/cpp/include") target_include_directories(tgi_trtllm_backend_impl PUBLIC "${trtllm_SOURCE_DIR}/cpp/include")
target_link_libraries(tgi_trtllm_backend_impl PRIVATE tensorrt_llm nvinfer_plugin_tensorrt_llm CUDA::nvml) target_link_libraries(tgi_trtllm_backend_impl PRIVATE tensorrt_llm nvinfer_plugin_tensorrt_llm tensorrt_llm_nvrtc_wrapper CUDA::nvml)
target_link_libraries(tgi_trtllm_backend_impl PUBLIC nlohmann_json::nlohmann_json spdlog::spdlog fmt::fmt) target_link_libraries(tgi_trtllm_backend_impl PUBLIC nlohmann_json::nlohmann_json spdlog::spdlog fmt::fmt)
if (${TGI_TRTLLM_BACKEND_BUILD_EXAMPLES}) if (${TGI_TRTLLM_BACKEND_BUILD_EXAMPLES})
@ -40,9 +45,8 @@ if (${TGI_TRTLLM_BACKEND_BUILD_EXAMPLES})
target_link_libraries(tgi_trtllm_backend_example PUBLIC nlohmann_json::nlohmann_json spdlog::spdlog fmt::fmt) target_link_libraries(tgi_trtllm_backend_example PUBLIC nlohmann_json::nlohmann_json spdlog::spdlog fmt::fmt)
endif () endif ()
# TODO: need to find why we can't install fmt (include not found...) # 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 spdlog fmt) install(TARGETS tgi_trtllm_backend_impl tensorrt_llm nvinfer_plugin_tensorrt_llm executorWorker)
install(TARGETS tgi_trtllm_backend_impl tensorrt_llm nvinfer_plugin_tensorrt_llm)
#### Unit Tests #### #### Unit Tests ####
if (${TGI_TRTLLM_BACKEND_BUILD_TESTS}) if (${TGI_TRTLLM_BACKEND_BUILD_TESTS})
@ -61,4 +65,4 @@ if (${TGI_TRTLLM_BACKEND_BUILD_TESTS})
include(CTest) include(CTest)
include(Catch) include(Catch)
catch_discover_tests(tgi_trtllm_backend_tests) catch_discover_tests(tgi_trtllm_backend_tests)
endif () endif ()

1
backends/trtllm/cmake/trtllm.cmake
View File

@ -26,6 +26,7 @@ fetchcontent_declare(
GIT_SHALLOW FALSE GIT_SHALLOW FALSE
) )
fetchcontent_makeavailable(trtllm) fetchcontent_makeavailable(trtllm)
message(STATUS "Found TensorRT-LLM: ${trtllm_SOURCE_DIR}") message(STATUS "Found TensorRT-LLM: ${trtllm_SOURCE_DIR}")
execute_process(COMMAND git lfs install WORKING_DIRECTORY "${trtllm_SOURCE_DIR}/") execute_process(COMMAND git lfs install WORKING_DIRECTORY "${trtllm_SOURCE_DIR}/")
execute_process(COMMAND git lfs pull WORKING_DIRECTORY "${trtllm_SOURCE_DIR}/") execute_process(COMMAND git lfs pull WORKING_DIRECTORY "${trtllm_SOURCE_DIR}/")