tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: compress mode option and default to size (#12029)

Browse Source 
cuda 12.8 added the option to specify stronger compression for binaries, so we now default to "size".
This commit is contained in:
Erik Scholz
2025-03-01 12:57:22 +01:00
committed by GitHub
parent 2cc4a5e44a
commit 80c41ddd8f
2 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/CMakeLists.txt
View File

@ -155,6 +155,9 @@ option(GGML_CUDA_NO_VMM "ggml: do not try to use CUDA VMM"
option(GGML_CUDA_FA "ggml: compile ggml FlashAttention CUDA kernels" ON)
option(GGML_CUDA_FA_ALL_QUANTS "ggml: compile all quants for FlashAttention" OFF)
option(GGML_CUDA_GRAPHS "ggml: use CUDA graphs (llama.cpp only)" ${GGML_CUDA_GRAPHS_DEFAULT})
set (GGML_CUDA_COMPRESSION_MODE "size" CACHE STRING
"ggml: cuda link binary compression mode; requires cuda 12.8+")
set_property(CACHE GGML_CUDA_COMPRESSION_MODE PROPERTY STRINGS "none;speed;balance;size")
option(GGML_HIP "ggml: use HIP" OFF)
option(GGML_HIP_GRAPHS "ggml: use HIP graph, experimental, slow" OFF)