mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2025-09-10 17:14:36 +00:00
fix cuda garbage results and gpu selection issues
This commit is contained in:
parent
95eca51bef
commit
ddaa4f2a26
3 changed files with 22 additions and 5 deletions
10
koboldcpp.py
10
koboldcpp.py
|
@ -191,10 +191,12 @@ def load_model(model_filename):
|
|||
clblastids = 100 + int(args.useclblast[0])*10 + int(args.useclblast[1])
|
||||
inputs.clblast_info = clblastids
|
||||
inputs.cublas_info = 0
|
||||
if (args.usecublas and "1" in args.usecublas):
|
||||
inputs.cublas_info = 1
|
||||
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):
|
||||
inputs.cublas_info = 2
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = "2"
|
||||
inputs.executable_path = (getdirpath()+"/").encode("UTF-8")
|
||||
inputs.debugmode = args.debugmode
|
||||
banned_tokens = args.bantokens
|
||||
|
@ -267,7 +269,7 @@ maxhordectx = 1024
|
|||
maxhordelen = 256
|
||||
modelbusy = False
|
||||
defaultport = 5001
|
||||
KcppVersion = "1.34"
|
||||
KcppVersion = "1.34.2"
|
||||
showdebug = True
|
||||
|
||||
class ServerRequestHandler(http.server.SimpleHTTPRequestHandler):
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue