58d95cc9bd
This should resolve a number of memory leak and stability defects by allowing us to isolate llama.cpp in a separate process and shutdown when idle, and gracefully restart if it has problems. This also serves as a first step to be able to run multiple copies to support multiple models concurrently.
14 lines
No EOL
559 B
CMake
Vendored
14 lines
No EOL
559 B
CMake
Vendored
|
|
set(TARGET ollama_llama_server)
|
|
option(LLAMA_SERVER_VERBOSE "Build verbose logging option for Server" ON)
|
|
include_directories(${CMAKE_CURRENT_SOURCE_DIR})
|
|
add_executable(${TARGET} server.cpp utils.hpp json.hpp httplib.h)
|
|
install(TARGETS ${TARGET} RUNTIME)
|
|
target_compile_definitions(${TARGET} PRIVATE
|
|
SERVER_VERBOSE=$<BOOL:${LLAMA_SERVER_VERBOSE}>
|
|
)
|
|
target_link_libraries(${TARGET} PRIVATE common llava ${CMAKE_THREAD_LIBS_INIT})
|
|
if (WIN32)
|
|
TARGET_LINK_LIBRARIES(${TARGET} PRIVATE ws2_32)
|
|
endif()
|
|
target_compile_features(${TARGET} PRIVATE cxx_std_11) |