CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-17 11:37:10 +00:00
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-hip/CMakeLists.txt
View File

@@ -107,6 +107,10 @@ if (GGML_HIP_NO_VMM)
add_compile_definitions(GGML_HIP_NO_VMM)
endif()
if (NOT GGML_CUDA_FA)
add_compile_definitions(GGML_CUDA_NO_FA)
endif()
if (CXX_IS_HIPCC)
set_source_files_properties(${GGML_SOURCES_ROCM} PROPERTIES LANGUAGE CXX)
target_link_libraries(ggml-hip PRIVATE hip::device)