tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-09-08 08:23:20 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: app option to compile without FlashAttention (#12025)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-02-22 20:44:34 +01:00
committed by GitHub
parent 36c258ee92
commit a28e0d5eb1
13 changed files with 46 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/CMakeLists.txt
View File

@@ -69,6 +69,10 @@ if (CUDAToolkit_FOUND)
add_compile_definitions(GGML_CUDA_NO_VMM)
endif()
if (NOT GGML_CUDA_FA)
add_compile_definitions(GGML_CUDA_NO_FA)
endif()
if (GGML_CUDA_F16 OR GGML_CUDA_DMMV_F16)
add_compile_definitions(GGML_CUDA_F16)
endif()