cmake: revert CUDA arch default to 52, 61 if f16 (#1959)

CMakeLists.txt

@@ -250,6 +250,15 @@ if (LLAMA_CUBLAS)
             set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
         endif()
 
+    if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
+        if (LLAMA_CUDA_DMMV_F16)
+            set(CMAKE_CUDA_ARCHITECTURES "61") # needed for f16 CUDA intrinsics
+        else()
+            set(CMAKE_CUDA_ARCHITECTURES "52") # lowest CUDA 12 standard
+        endif()
+    endif()
+    message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")
+
     else()
         message(WARNING "cuBLAS not found")
     endif()
@@ -493,22 +502,6 @@ if (BUILD_SHARED_LIBS)
     endif()
 endif()
 
-if (GGML_SOURCES_CUDA)
-    message(STATUS "GGML CUDA sources found, configuring CUDA architecture")
-    set_property(TARGET ggml  PROPERTY CUDA_ARCHITECTURES "native")
-    set_property(TARGET ggml  PROPERTY CUDA_SELECT_NVCC_ARCH_FLAGS "Auto")
-
-    set_property(TARGET ggml_static PROPERTY CUDA_ARCHITECTURES "native")
-    set_property(TARGET ggml_static PROPERTY CUDA_SELECT_NVCC_ARCH_FLAGS "Auto")
-
-    if (BUILD_SHARED_LIBS)
-        set_property(TARGET ggml_shared PROPERTY CUDA_ARCHITECTURES "native")
-        set_property(TARGET ggml_shared PROPERTY CUDA_SELECT_NVCC_ARCH_FLAGS "Auto")
-    endif()
-
-    set_property(TARGET llama PROPERTY CUDA_ARCHITECTURES "native")
-endif()
-
 
 #
 # programs, examples and tests