haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

cmake : enable separable compilation for CUDA

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2023-12-07 14:25:24 +02:00
parent 06b5c623ca
commit 09e35d04b1
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
CMakeLists.txt
View file

@ -279,6 +279,10 @@ if (LLAMA_CUBLAS)
if (LLAMA_CUDA_FORCE_MMQ)
add_compile_definitions(GGML_CUDA_FORCE_MMQ)
endif()
# required for dynamic parallelism
set(CMAKE_CUDA_SEPARABLE_COMPILATION ON)
add_compile_definitions(GGML_CUDA_DMMV_X=${LLAMA_CUDA_DMMV_X})
add_compile_definitions(GGML_CUDA_MMV_Y=${LLAMA_CUDA_MMV_Y})
if (DEFINED LLAMA_CUDA_DMMV_Y)