app : introduce the llama unified executable (#23296)

* app : introduce the llama unified executable

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Use serve for server

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Hide completion and bench, add help command

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Remove STATIC

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Use -impl targets instead of -lib

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* Revert "Remove STATIC"

This reverts commit cc44caccb9902b34a3531633edac911e5b3d65cd.

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

tools/cli/CMakeLists.txt

@@ -1,9 +1,19 @@
-set(TARGET llama-cli)
-add_executable(${TARGET} cli.cpp)
-target_link_libraries(${TARGET} PRIVATE server-context PUBLIC llama-common ${CMAKE_THREAD_LIBS_INIT})
-target_compile_features(${TARGET} PRIVATE cxx_std_17)
+# llama-cli-impl: CLI logic, reusable by app
 
-include_directories(../server)
+set(TARGET llama-cli-impl)
+
+add_library(${TARGET} STATIC cli.cpp)
+
+target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR} ../server)
+target_link_libraries(${TARGET} PUBLIC server-context llama-common ${CMAKE_THREAD_LIBS_INIT})
+
+# llama-cli executable
+
+set(TARGET llama-cli)
+
+add_executable(${TARGET} main.cpp)
+target_link_libraries(${TARGET} PRIVATE llama-cli-impl)
+target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)
     install(TARGETS ${TARGET} RUNTIME)

tools/cli/cli.cpp

@@ -342,7 +342,10 @@ static std::vector<std::pair<std::string, size_t>> auto_completion_callback(std:
 
 static constexpr size_t FILE_GLOB_MAX_RESULTS = 100;
 
-int main(int argc, char ** argv) {
+// satisfies -Wmissing-declarations
+int llama_cli(int argc, char ** argv);
+
+int llama_cli(int argc, char ** argv) {
     common_params params;
 
     params.verbosity = LOG_LEVEL_ERROR; // by default, less verbose logs

tools/cli/main.cpp

@@ -0,0 +1,5 @@
+int llama_cli(int argc, char ** argv);
+
+int main(int argc, char ** argv) {
+    return llama_cli(argc, argv);
+}