vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	Makefile
#	README.md
#	common/log.h
This commit is contained in:
Concedo 2023-09-02 11:24:28 +08:00
commit eed651494e
26 changed files with 1143 additions and 658 deletions
Download patch file Download diff file Expand all files Collapse all files

23
koboldcpp.py
View file

@ -223,13 +223,24 @@ def load_model(model_filename):
else:
inputs.tensor_split[n] = 0
# we must force an explicit tensor split
# otherwise the default will divide equally and multigpu crap will slow it down badly
inputs.cublas_info = 0
if (args.usecublas and "0" in args.usecublas):
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
elif (args.usecublas and "1" in args.usecublas):
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
elif (args.usecublas and "2" in args.usecublas):
os.environ["CUDA_VISIBLE_DEVICES"] = "2"
if not args.tensor_split:
if (args.usecublas and "0" in args.usecublas):
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
elif (args.usecublas and "1" in args.usecublas):
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
elif (args.usecublas and "2" in args.usecublas):
os.environ["CUDA_VISIBLE_DEVICES"] = "2"
else:
if (args.usecublas and "0" in args.usecublas):
inputs.cublas_info = 0
elif (args.usecublas and "1" in args.usecublas):
inputs.cublas_info = 1
elif (args.usecublas and "2" in args.usecublas):
inputs.cublas_info = 2
inputs.executable_path = (getdirpath()+"/").encode("UTF-8")
inputs.debugmode = args.debugmode