highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-07-17 12:32:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

cuda: enable flash attention

Browse Source 
ggml added an option to disable flash attention so explicitly enable it
This commit is contained in:
Michael Yang
2025-02-28 11:28:26 -08:00
parent 25885e5335
commit b42aba40ed
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
CMakeLists.txt
View File

@ -23,6 +23,7 @@ set(GGML_SCHED_MAX_COPIES 4)
set(GGML_LLAMAFILE ON) set(GGML_LLAMAFILE ON)
set(GGML_CUDA_PEER_MAX_BATCH_SIZE 128) set(GGML_CUDA_PEER_MAX_BATCH_SIZE 128)
set(GGML_CUDA_GRAPHS ON) set(GGML_CUDA_GRAPHS ON)
set(GGML_CUDA_FA ON)
if((CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_OSX_ARCHITECTURES MATCHES "arm64") if((CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_OSX_ARCHITECTURES MATCHES "arm64")
OR (NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_SYSTEM_PROCESSOR MATCHES "arm|aarch64|ARM64|ARMv[0-9]+")) OR (NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_SYSTEM_PROCESSOR MATCHES "arm|aarch64|ARM64|ARMv[0-9]+"))