ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

MUSA: support ARM64 and enable dp4a .etc (#11843)

Browse source 
* MUSA:  support ARM64 and enable __dp4a .etc

* fix cross entropy loss op for musa

* update

* add cc info log for musa

* add comment for the MUSA .cc calculation block

---------

Co-authored-by: Bodhi Hu <huaishun.hu@mthreads.com>
This commit is contained in:
Bodhi 2025-02-21 15:46:23 +08:00 • committed by GitHub
parent ee02ad02c5
commit 0b3863ff95
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 25 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-musa/CMakeLists.txt
View file

@ -49,7 +49,7 @@ if (MUSAToolkit_FOUND)
set_source_files_properties(${GGML_SOURCES_MUSA} PROPERTIES LANGUAGE CXX)
foreach(SOURCE ${GGML_SOURCES_MUSA})
set(COMPILE_FLAGS "-x musa -mtgpu")
set(COMPILE_FLAGS "-fsigned-char -x musa -mtgpu")
foreach(ARCH ${MUSA_ARCHITECTURES})
set(COMPILE_FLAGS "${COMPILE_FLAGS} --cuda-gpu-arch=mp_${ARCH}")
endforeach()