Skip to content

Fix hordeconfig max context setting, and add Makefile flags for cuda F16/KQuants per iter. #252

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
LostRuins merged 2 commits into from
Jun 21, 2023
Merged

Fix hordeconfig max context setting, and add Makefile flags for cuda F16/KQuants per iter. #252

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f581377
Fix hordeconfig maxcontext setting.
ycros Jun 21, 2023
f28decf
cuda: Bring DMMV_F16 and KQUANTS_ITER Makefile flags over from llama.
ycros Jun 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,6 +149,14 @@ ifdef LLAMA_CUDA_DMMV_Y
else
NVCCFLAGS += -DGGML_CUDA_DMMV_Y=1
endif # LLAMA_CUDA_DMMV_Y
ifdef LLAMA_CUDA_DMMV_F16
NVCCFLAGS += -DGGML_CUDA_DMMV_F16
endif # LLAMA_CUDA_DMMV_F16
ifdef LLAMA_CUDA_KQUANTS_ITER
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=$(LLAMA_CUDA_KQUANTS_ITER)
else
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=2
endif
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) $(CUBLAS_CXXFLAGS) -Wno-pedantic -c $< -o $@
ggml_v2-cuda.o: otherarch/ggml_v2-cuda.cu otherarch/ggml_v2-cuda.h
Expand Down
2 changes: 1 addition & 1 deletion koboldcpp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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])
Expand Down