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

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	README.md
#	ggml-cuda.cu
This commit is contained in:
Concedo 2023-08-09 21:18:34 +08:00
commit ba09f1c807
2 changed files with 676 additions and 384 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Makefile
View file

@ -176,11 +176,6 @@ ifdef LLAMA_CUDA_KQUANTS_ITER
else else
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=2 NVCCFLAGS += -DK_QUANTS_PER_ITERATION=2
endif endif
ifdef LLAMA_CUDA_MMQ_Y
NVCCFLAGS += -DGGML_CUDA_MMQ_Y=$(LLAMA_CUDA_MMQ_Y)
else
NVCCFLAGS += -DGGML_CUDA_MMQ_Y=64
endif # LLAMA_CUDA_MMQ_Y
#ifdef LLAMA_CUDA_CUBLAS #ifdef LLAMA_CUDA_CUBLAS
# NVCCFLAGS += -DGGML_CUDA_CUBLAS # NVCCFLAGS += -DGGML_CUDA_CUBLAS
#endif # LLAMA_CUDA_CUBLAS #endif # LLAMA_CUDA_CUBLAS

1055
ggml-cuda.cu
View file

File diff suppressed because it is too large Load diff