CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-08-20 16:58:49 +02:00
committed by GitHub
parent fec9519802
commit 7a6e91ad26
12 changed files with 32 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/CMakeLists.txt
View File

@@ -158,7 +158,6 @@ option(GGML_CUDA "ggml: use CUDA"
option(GGML_MUSA "ggml: use MUSA" OFF)
option(GGML_CUDA_FORCE_MMQ "ggml: use mmq kernels instead of cuBLAS" OFF)
option(GGML_CUDA_FORCE_CUBLAS "ggml: always use cuBLAS instead of mmq kernels" OFF)
option(GGML_CUDA_F16 "ggml: use 16 bit floats for some calculations" OFF)
set (GGML_CUDA_PEER_MAX_BATCH_SIZE "128" CACHE STRING
"ggml: max. batch size for using peer access")
option(GGML_CUDA_NO_PEER_COPY "ggml: do not use peer to peer copies" OFF)