vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix cmake build

Browse source
This commit is contained in:
slaren 2023-12-23 02:06:49 +01:00
parent eb223dcddd
commit bd78dc9aee
2 changed files with 2 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
CMakeLists.txt
View file

@ -302,6 +302,8 @@ if (LLAMA_CUBLAS)
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt) set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
endif() endif()
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} CUDA::cuda_driver)
if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES) if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
# 52 == lowest CUDA 12 standard # 52 == lowest CUDA 12 standard
# 60 == f16 CUDA intrinsics # 60 == f16 CUDA intrinsics

3
tests/test-grad0.cpp
View file

@ -883,9 +883,6 @@ int main(int argc, const char ** argv) {
srand(seed); srand(seed);
const int nargs = 1; const int nargs = 1;
int64_t ne2[4];
ne2[0] = 1;
for (int ndims = 1; ndims <= 2; ++ndims) { for (int ndims = 1; ndims <= 2; ++ndims) {
x[0] = get_random_tensor_f32(ctx0, ndims, ne, -1.0f, 1.0f); x[0] = get_random_tensor_f32(ctx0, ndims, ne, -1.0f, 1.0f);