diff options
Diffstat (limited to 'CMakeLists.txt')
| -rw-r--r-- | CMakeLists.txt | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/CMakeLists.txt b/CMakeLists.txt index 1d4e63f..d085bc8 100644 --- a/CMakeLists.txt +++ b/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 |