Skip to content

Commit 226b2d0

Browse files
committed
ggml : add Q8_0 quantization for intermediate results
1 parent c56b715 commit 226b2d0

File tree

3 files changed

+273
-18
lines changed

3 files changed

+273
-18
lines changed

Makefile

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -142,10 +142,10 @@ default: main quantize perplexity embedding
142142
ggml.o: ggml.c ggml.h
143143
$(CC) $(CFLAGS) -c ggml.c -o ggml.o
144144

145-
llama.o: llama.cpp llama.h llama_util.h
145+
llama.o: llama.cpp llama.h llama_util.h ggml.h
146146
$(CXX) $(CXXFLAGS) -c llama.cpp -o llama.o
147147

148-
common.o: examples/common.cpp examples/common.h
148+
common.o: examples/common.cpp examples/common.h llama.h
149149
$(CXX) $(CXXFLAGS) -c examples/common.cpp -o common.o
150150

151151
clean:

0 commit comments

Comments
 (0)