tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix llamafile sgemm wdata offsets (#6710)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2024-04-16 23:50:22 +03:00
committed by GitHub
parent 8cc91dc63c
commit 666867b799
3 changed files with 12 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
CMakeLists.txt
View File

@ -88,6 +88,7 @@ endif()
# 3rd party libs
option(LLAMA_ACCELERATE "llama: enable Accelerate framework" ON)
option(LLAMA_BLAS "llama: use BLAS" OFF)
option(LLAMA_LLAMAFILE "llama: use llamafile SGEMM" ON)
set(LLAMA_BLAS_VENDOR "Generic" CACHE STRING "llama: BLAS library vendor")
option(LLAMA_CUDA "llama: use CUDA" OFF)
option(LLAMA_CUBLAS "llama: use CUDA (deprecated, use LLAMA_CUDA)" OFF)
@ -286,6 +287,7 @@ if (LLAMA_METAL)
${METALKIT_FRAMEWORK}
)
endif()
if (LLAMA_BLAS)
if (LLAMA_STATIC)
set(BLA_STATIC ON)
@ -368,6 +370,10 @@ if (LLAMA_BLAS)
endif()
endif()
if (LLAMA_LLAMAFILE)
add_compile_definitions(GGML_USE_LLAMAFILE)
endif()
if (LLAMA_QKK_64)
add_compile_definitions(GGML_QKK_64)
endif()