mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-09-13 10:18:49 +02:00
Fix hordeconfig max context setting, and add Makefile flags for cuda F16/KQuants per iter. (#252)
* Fix hordeconfig maxcontext setting. * cuda: Bring DMMV_F16 and KQUANTS_ITER Makefile flags over from llama.
This commit is contained in:
+1
-1
@@ -724,7 +724,7 @@ def main(args):
|
||||
sys.exit(2)
|
||||
|
||||
if args.hordeconfig and args.hordeconfig[0]!="":
|
||||
global friendlymodelname, maxhordelen, showdebug
|
||||
global friendlymodelname, maxhordelen, maxhordectx, showdebug
|
||||
friendlymodelname = "koboldcpp/"+args.hordeconfig[0]
|
||||
if len(args.hordeconfig) > 1:
|
||||
maxhordelen = int(args.hordeconfig[1])
|
||||
|
||||
Reference in New Issue
Block a user