vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

tweaks for rocm blas

Browse source
This commit is contained in:
Concedo 2023-09-02 09:22:32 +08:00
parent 6d06695c7e
commit 8df03ed026
2 changed files with 5 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

14
koboldcpp.py
View file

@ -223,21 +223,13 @@ 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):
inputs.cublas_info = 0
if not args.tensor_split:
inputs.tensor_split[inputs.cublas_info] = 100
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
elif (args.usecublas and "1" in args.usecublas):
inputs.cublas_info = 1
if not args.tensor_split:
inputs.tensor_split[inputs.cublas_info] = 100
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
elif (args.usecublas and "2" in args.usecublas):
inputs.cublas_info = 2
if not args.tensor_split:
inputs.tensor_split[inputs.cublas_info] = 100
os.environ["CUDA_VISIBLE_DEVICES"] = "2"
inputs.executable_path = (getdirpath()+"/").encode("UTF-8")
inputs.debugmode = args.debugmode