tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-13 03:47:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: use MMQ instead of cuBLAS by default (#8075)

Browse Source
This commit is contained in:
Johannes Gäßler
2024-06-24 17:43:42 +02:00
committed by GitHub
parent d62e4aaa02
commit a818f3028d
8 changed files with 124 additions and 122 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
Makefile
View File

@@ -537,6 +537,9 @@ endif # LLAMA_CUDA_FORCE_DMMV
ifdef LLAMA_CUDA_FORCE_MMQ
MK_NVCCFLAGS += -DGGML_CUDA_FORCE_MMQ
endif # LLAMA_CUDA_FORCE_MMQ
ifdef LLAMA_CUDA_FORCE_CUBLAS
MK_NVCCFLAGS += -DGGML_CUDA_FORCE_CUBLAS
endif # LLAMA_CUDA_FORCE_CUBLAS
ifdef LLAMA_CUDA_DMMV_X
MK_NVCCFLAGS += -DGGML_CUDA_DMMV_X=$(LLAMA_CUDA_DMMV_X)
else