MUSA: support ARM64 and enable dp4a .etc (#11843)
* 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:
parent
ee02ad02c5
commit
0b3863ff95
7 changed files with 25 additions and 15 deletions
2
Makefile
2
Makefile
|
@ -847,7 +847,7 @@ ifdef GGML_MUSA
|
|||
CXX := $(MUSA_PATH)/bin/clang++
|
||||
MCC := $(CCACHE) $(MUSA_PATH)/bin/mcc
|
||||
|
||||
MUSAFLAGS = -x musa -mtgpu
|
||||
MUSAFLAGS = -fsigned-char -x musa -mtgpu
|
||||
MUSAFLAGS += $(foreach arch,$(subst ;, ,$(MUSA_ARCHITECTURES)),--cuda-gpu-arch=mp_$(arch))
|
||||
|
||||
ifdef GGML_CUDA_FORCE_MMQ
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue