ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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)