huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-24 16:32:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(backend): tell cmake to build llama-common and link to it

Browse Source
This commit is contained in:
Morgan Funtowicz 2024-10-22 15:23:16 +02:00
parent 0911076320
commit 098c66920d
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
backends/llamacpp/CMakeLists.txt
View File

@ -6,6 +6,7 @@ set(CMAKE_CXX_STANDARD 23)
include(FetchContent)
set(LLAMA_CPP_TARGET_VERSION "b3837" CACHE STRING "Version of llama.cpp to build against")
set(LLAMA_BUILD_COMMON ON)
set(LLAMA_CPP_TARGET_CUDA_ARCHS "75-real;80-real;86-real;89-real;90-real" CACHE STRING "CUDA arch(s) to build")
option(LLAMA_CPP_BUILD_OFFLINE_RUNNER "Flag to build the standalone c++ backend runner")
option(LLAMA_CPP_BUILD_CUDA "Flag to build CUDA enabled inference through llama.cpp")
@ -28,7 +29,7 @@ fetchcontent_declare(
llama
# DOWNLOAD_EXTRACT_TIMESTAMP TRUE
GIT_REPOSITORY https://github.com/ggerganov/llama.cpp.git
GIT_TAG b3837
GIT_TAG b3958
GIT_SHALLOW FALSE
)
@ -41,7 +42,8 @@ target_link_libraries(tgi_llama_cpp_backend_impl PUBLIC fmt::fmt spdlog::spdlog
if (${LLAMA_CPP_BUILD_OFFLINE_RUNNER})
message(STATUS "Building llama.cpp offline runner")
add_executable(tgi_llama_cpp_offline_runner offline/main.cpp)
target_link_libraries(tgi_llama_cpp_offline_runner tgi_llama_cpp_backend_impl)
target_link_libraries(tgi_llama_cpp_offline_runner PUBLIC tgi_llama_cpp_backend_impl llama common)
endif ()