CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

FP16 is supported in CM=6.0 (#2177)

Browse Source 
* FP16 is supported in CM=6.0

* Building PTX code for both of 60 and 61

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Howard Su
2023-07-12 20:18:40 +08:00
committed by GitHub
parent 2b5eb72e10
commit 4e7464ef88
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CMakeLists.txt
View File

@@ -272,7 +272,7 @@ if (LLAMA_CUBLAS)
if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES) if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
if (LLAMA_CUDA_DMMV_F16) if (LLAMA_CUDA_DMMV_F16)
set(CMAKE_CUDA_ARCHITECTURES "61") # needed for f16 CUDA intrinsics set(CMAKE_CUDA_ARCHITECTURES "60;61") # needed for f16 CUDA intrinsics
else() else()
set(CMAKE_CUDA_ARCHITECTURES "52;61") # lowest CUDA 12 standard + lowest for integer intrinsics set(CMAKE_CUDA_ARCHITECTURES "52;61") # lowest CUDA 12 standard + lowest for integer intrinsics
endif() endif()