Merge 'origin/master' into hipblas

Makefile

@@ -74,6 +74,15 @@ ifeq ($(UNAME_S),Haiku)
 	CXXFLAGS += -pthread
 endif
 
+ifdef LLAMA_GPROF
+	CFLAGS   += -pg
+	CXXFLAGS += -pg
+endif
+ifdef LLAMA_PERF
+	CFLAGS   += -DGGML_PERF
+	CXXFLAGS += -DGGML_PERF
+endif
+
 # Architecture specific
 # TODO: probably these flags need to be tweaked on some architectures
 #       feel free to update the Makefile for your architecture and send a pull request or issue
@@ -148,14 +157,6 @@ ggml-cuda.o: CXXFLAGS += $(addprefix --offload-arch=,$(GPU_TARGETS))
 ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
 	$(CXX) $(CXXFLAGS) -x hip -c -o $@ $<
 endif
-ifdef LLAMA_GPROF
-	CFLAGS   += -pg
-	CXXFLAGS += -pg
-endif
-ifdef LLAMA_PERF
-	CFLAGS   += -DGGML_PERF
-	CXXFLAGS += -DGGML_PERF
-endif
 ifneq ($(filter aarch64%,$(UNAME_M)),)
 	# Apple M1, M2, etc.
 	# Raspberry Pi 3, 4, Zero 2 (64-bit)

examples/CMakeLists.txt

@@ -36,4 +36,5 @@ else()
     add_subdirectory(embedding)
     add_subdirectory(save-load-state)
     add_subdirectory(benchmark)
+    add_subdirectory(baby-llama)
 endif()

examples/baby-llama/CMakeLists.txt

@@ -0,0 +1,4 @@
+set(TARGET baby-llama)
+add_executable(${TARGET} baby-llama.cpp)
+target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_compile_features(${TARGET} PRIVATE cxx_std_11)