llama.cpp
ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON
#18413
Merged
Merged
ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON #18413
am17an
merged
1 commit into
ggml-org:master
from
QDelta:master
ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON
16cbfa29
JohannesGaessler
approved these changes
on 2025-12-27
Login to write a write a comment.
Login via GitHub