git/ik_llama.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Disable CUDA fusion by default for now (#903)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow 2025-11-05 10:58:12 +02:00 committed by GitHub
parent 1a3aaa33c1
commit 320fc606cd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/CMakeLists.txt
View File

@ -133,7 +133,7 @@ option(GGML_CUDA_NO_PEER_COPY "ggml: do not use peer to peer copie
option(GGML_CUDA_NO_VMM "ggml: do not try to use CUDA VMM" OFF)
option(GGML_CUDA_FA_ALL_QUANTS "ggml: compile all quants for FlashAttention" OFF)
option(GGML_CUDA_USE_GRAPHS "ggml: use CUDA graphs (llama.cpp only)" ON)
set (GGML_CUDA_FUSION "1" CACHE STRING "ggml: enable/disable fusion")
set (GGML_CUDA_FUSION "0" CACHE STRING "ggml: enable/disable fusion")
option(GGML_IQK_FLASH_ATTENTION "ggml: enable the IQK FlashAttention CPU kernels" ON)
option(GGML_IQK_FA_ALL_QUANTS "ggml: compile all quants for IQK FlashAttention" OFF)