CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-20 12:07:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

gguf : start implementing quantization (WIP)

Browse Source
This commit is contained in:
M. Yusuf Sarıgöz
2023-08-12 14:28:17 +03:00
parent c4f02b4f74
commit b2571af255
3 changed files with 14 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@@ -393,7 +393,7 @@ $(LIB_PRE)embdinput$(DSO_EXT): examples/embd-input/embd-input.h examples/embd-in
embd-input-test: $(LIB_PRE)embdinput$(DSO_EXT) examples/embd-input/embd-input-test.cpp build-info.h ggml.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %$(DSO_EXT),$(filter-out %.h,$(filter-out %.hpp,$^))) -o $@ $(LDFLAGS) -L. -lembdinput
gguf: examples/gguf/gguf.cpp build-info.h ggml.o $(OBJS)
gguf: examples/gguf/gguf.cpp build-info.h ggml.o gguf-llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
gguf-llama-simple: examples/gguf/gguf-llama-simple.cpp build-info.h ggml.o gguf-llama.o common.o $(OBJS)