haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710)

Browse source
This commit is contained in:
Georgi Gerganov 2023-06-06 10:18:03 +03:00
parent 7ad7750c5c
commit 2d43387daf
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
3 changed files with 22 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
.gitignore vendored
View file

@ -35,6 +35,7 @@ models/*
/benchmark-matmult
/vdot
/Pipfile
/libllama.so
build-info.h
arm_neon.h

18
Makefile
View file

@ -243,7 +243,7 @@ llama.o: llama.cpp ggml.h ggml-cuda.h llama.h llama-util.h
common.o: examples/common.cpp examples/common.h
$(CXX) $(CXXFLAGS) -c $< -o $@
libllama.so: llama.o ggml.o $(OBJS)
libllama.so: llama.o ggml.o ggml-quants-k.o $(OBJS)
$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
clean:
@ -253,28 +253,28 @@ clean:
# Examples
#
main: examples/main/main.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
main: examples/main/main.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
@echo
@echo '==== Run ./main -h for help. ===='
@echo
quantize: examples/quantize/quantize.cpp build-info.h ggml.o llama.o ggml-quants-k.o $(OBJS)
quantize: examples/quantize/quantize.cpp build-info.h ggml.o ggml-quants-k.o llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
quantize-stats: examples/quantize-stats/quantize-stats.cpp build-info.h ggml.o llama.o ggml-quants-k.o $(OBJS)
quantize-stats: examples/quantize-stats/quantize-stats.cpp build-info.h ggml.o ggml-quants-k.o llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
perplexity: examples/perplexity/perplexity.cpp build-info.h ggml.o llama.o common.o ggml-quants-k.o $(OBJS)
perplexity: examples/perplexity/perplexity.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
embedding: examples/embedding/embedding.cpp build-info.h ggml.o llama.o common.o ggml-quants-k.o $(OBJS)
embedding: examples/embedding/embedding.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.o llama.o common.o ggml-quants-k.o $(OBJS)
save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp build-info.h ggml.o llama.o common.o $(OBJS)
server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) -Iexamples/server $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS)
build-info.h: $(wildcard .git/index) scripts/build-info.sh
@ -289,7 +289,7 @@ build-info.h: $(wildcard .git/index) scripts/build-info.sh
# Tests
#
benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o $(OBJS)
benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o ggml-quants-k.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
./$@

20
ggml.c
View file

@ -14753,7 +14753,7 @@ static void ggml_graph_export_leaf(const struct ggml_tensor * tensor, FILE * fou
const int64_t * ne = tensor->ne;
const size_t * nb = tensor->nb;
fprintf(fout, "%-6s %-12s %8d %8lld %8lld %8lld %8lld %16zu %16zu %16zu %16zu %16p %32s\n",
fprintf(fout, "%-6s %-12s %8d %8jd %jd %jd %jd %16zu %16zu %16zu %16zu %16p %32s\n",
ggml_type_name(tensor->type),
ggml_op_name (tensor->op),
tensor->n_dims,
@ -14767,7 +14767,7 @@ static void ggml_graph_export_node(const struct ggml_tensor * tensor, const char
const int64_t * ne = tensor->ne;
const size_t * nb = tensor->nb;
fprintf(fout, "%-6s %-6s %-12s %8d %8lld %8lld %8lld %8lld %16zu %16zu %16zu %16zu %8d %16p %32s\n",
fprintf(fout, "%-6s %-6s %-12s %8d %jd %jd %jd %jd %16zu %16zu %16zu %16zu %8d %16p %32s\n",
arg,
ggml_type_name(tensor->type),
ggml_op_name (tensor->op),
@ -14796,11 +14796,11 @@ void ggml_graph_export(const struct ggml_cgraph * cgraph, const char * fname) {
FILE * fout = stdout;
fprintf(fout, "\n");
fprintf(fout, "%-16s %8x\n", "magic", GGML_FILE_MAGIC);
fprintf(fout, "%-16s %8d\n", "version", GGML_FILE_VERSION);
fprintf(fout, "%-16s %8d\n", "leafs", cgraph->n_leafs);
fprintf(fout, "%-16s %8d\n", "nodes", cgraph->n_nodes);
fprintf(fout, "%-16s %8llu\n", "eval", size_eval);
fprintf(fout, "%-16s %8x\n", "magic", GGML_FILE_MAGIC);
fprintf(fout, "%-16s %8d\n", "version", GGML_FILE_VERSION);
fprintf(fout, "%-16s %8d\n", "leafs", cgraph->n_leafs);
fprintf(fout, "%-16s %8d\n", "nodes", cgraph->n_nodes);
fprintf(fout, "%-16s %8ju\n", "eval", size_eval);
// header
fprintf(fout, "\n");
@ -15033,7 +15033,11 @@ struct ggml_cgraph ggml_graph_import(const char * fname, struct ggml_context **
data = ggml_new_tensor_1d(*ctx_data, GGML_TYPE_I8, fsize);
fread(data->data, sizeof(char), fsize, fin);
const size_t ret = fread(data->data, sizeof(char), fsize, fin);
if (ret != fsize) {
fprintf(stderr, "%s: failed to read %s\n", __func__, fname);
return result;
}
fclose(fin);
}