app : add batched-bench, fit-params, quantize & perplexity (#23459)

* app : add batched-bench, fit-params, quantize & perplexity

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

* Add missing main.cpp

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

* Add EOL

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

---------

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

tools/quantize/CMakeLists.txt

@@ -1,7 +1,18 @@
+# llama-quantize-impl: quantize logic, reusable by app
+
+set(TARGET llama-quantize-impl)
+
+add_library(${TARGET} STATIC quantize.cpp)
+
+target_include_directories(${TARGET} PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
+target_link_libraries(${TARGET} PUBLIC llama-common llama ${CMAKE_THREAD_LIBS_INIT})
+
+# llama-quantize executable
+
 set(TARGET llama-quantize)
-add_executable(${TARGET} quantize.cpp)
-target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
-target_include_directories(${TARGET} PRIVATE ../../common)
+
+add_executable(${TARGET} main.cpp)
+target_link_libraries(${TARGET} PRIVATE llama-quantize-impl)
 target_compile_features(${TARGET} PRIVATE cxx_std_17)
 
 if(LLAMA_TOOLS_INSTALL)

tools/quantize/main.cpp

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

tools/quantize/quantize.cpp

@@ -490,7 +490,10 @@ static bool parse_layer_prune(const char * data, std::vector<int> & prune_layers
     return true;
 }
 
-int main(int argc, char ** argv) {
+// satisfies -Wmissing-declarations
+int llama_quantize(int argc, char ** argv);
+
+int llama_quantize(int argc, char ** argv) {
     std::setlocale(LC_NUMERIC, "C");
     if (argc < 3) {
         usage(argv[0]);