CUDA: Fix models with output size != 32000

Author: JohannesGaessler

CMakeLists.txt

@@ -280,8 +280,8 @@ if (LLAMA_CUBLAS)
         # 52 == lowest CUDA 12 standard
         # 60 == f16 CUDA intrinsics
         # 61 == integer CUDA intrinsics
-        # 70 == (assumed) compute capability at which unrolling a loop in mul_mat_q kernels is faster
-        if (LLAMA_CUDA_DMMV_F16)
+        # 70 == compute capability at which unrolling a loop in mul_mat_q kernels is faster
+        if (LLAMA_CUDA_F16 OR LLAMA_CUDA_DMMV_F16)
             set(CMAKE_CUDA_ARCHITECTURES "60;61;70") # needed for f16 CUDA intrinsics
         else()
             set(CMAKE_CUDA_ARCHITECTURES "52;61;70") # lowest CUDA 12 standard + lowest for integer intrinsics