Skip to content

Commit

Permalink
dont build quantize
Browse files Browse the repository at this point in the history
  • Loading branch information
LostRuins committed Apr 7, 2023
1 parent 4f5faf9 commit 1d48db4
Show file tree
Hide file tree
Showing 2 changed files with 6 additions and 2 deletions.
5 changes: 4 additions & 1 deletion Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -139,7 +139,7 @@ $(info I CC: $(CCV))
$(info I CXX: $(CXXV))
$(info )

default: llamalib quantize llamalib_blas
default: llamalib llamalib_blas

#
# Build library
Expand Down Expand Up @@ -187,6 +187,9 @@ llamalib_blas: ggml_blas.o ggml_v1.o expose.o common.o llama_adapter.o gpttype_a
quantize: examples/quantize/quantize.cpp ggml.o llama.o
$(CXX) $(CXXFLAGS) examples/quantize/quantize.cpp ggml.o llama.o -o quantize $(LDFLAGS)

quantize_gptj: ggml.o llama.o
$(CXX) $(CXXFLAGS) otherarch/gptj_quantize.cpp ggml.o llama.o -o quantize_gptj $(LDFLAGS)

perplexity: examples/perplexity/perplexity.cpp ggml.o llama.o common.o
$(CXX) $(CXXFLAGS) examples/perplexity/perplexity.cpp ggml.o llama.o common.o -o perplexity $(LDFLAGS)

Expand Down
3 changes: 2 additions & 1 deletion otherarch/gptj_quantize.cpp
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#include "ggml.h"

#include "utils.h"
#include "otherarch/utils.h"

#include <cassert>
#include <cmath>
Expand Down Expand Up @@ -283,6 +283,7 @@ bool gptj_model_quantize(const std::string & fname_inp, const std::string & fnam
// ./gpt-2-quantize models/gpt-2-117M/ggml-model.bin models/gpt-2-117M/ggml-model-quant.bin type
//
int main(int argc, char ** argv) {
ggml_time_init();
if (argc != 4) {
fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
fprintf(stderr, " type = 2 - q4_0\n");
Expand Down

0 comments on commit 1d48db4

Please sign in to comment.