tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-09-02 21:28:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

musa: enable building fat binaries, enable unified memory, and disable Flash Attention on QY1 (MTT S80) (#9526)

Browse Source 
* mtgpu: add mp_21 support

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* mtgpu: disable flash attention on qy1 (MTT S80); disable q3_k and mul_mat_batched_cublas

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* mtgpu: enable unified memory

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* mtgpu: map cublasOperation_t to mublasOperation_t (sync code to latest)

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR
2024-09-22 22:55:49 +08:00
committed by GitHub
parent 912c331d3d
commit c35e586ea5
6 changed files with 31 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@@ -611,7 +611,7 @@ ifdef GGML_CUDA
MK_CPPFLAGS += -DGGML_USE_CUDA -I$(CUDA_PATH)/include
MK_LDFLAGS += -lmusa -lmublas -lmusart -lpthread -ldl -lrt -L$(CUDA_PATH)/lib -L/usr/lib64
MK_NVCCFLAGS += -x musa -mtgpu --cuda-gpu-arch=mp_22
MK_NVCCFLAGS += -x musa -mtgpu --cuda-gpu-arch=mp_21 --cuda-gpu-arch=mp_22
else
ifneq ('', '$(wildcard /opt/cuda)')
CUDA_PATH ?= /opt/cuda