From 2d43387dafe9c60f15f57aa23ee0b37864b98b32 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 6 Jun 2023 10:18:03 +0300 Subject: ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710) --- .gitignore | 1 + Makefile | 18 +++++++++--------- ggml.c | 20 ++++++++++++-------- 3 files changed, 22 insertions(+), 17 deletions(-) diff --git a/.gitignore b/.gitignore index 6cf5c45..9b6905e 100644 --- a/.gitignore +++ b/.gitignore @@ -35,6 +35,7 @@ models/* /benchmark-matmult /vdot /Pipfile +/libllama.so build-info.h arm_neon.h diff --git a/Makefile b/Makefile index 7c9e7f7..0205f19 100644 --- a/Makefile +++ b/Makefile @@ -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 $@ $(LDFLAGS) ./$@ diff --git a/ggml.c b/ggml.c index 4e3e7ed..8308dd9 100644 --- a/ggml.c +++ b/ggml.c @@ -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); } -- cgit v1.2.3