k-quants : allow to optionally disable at compile time (#1734)

* k-quants : put behind optional compile flag LLAMA_K_QUANTS

* build : enable k-quants by default
This commit is contained in:
Georgi Gerganov 2023-06-07 10:59:52 +03:00 committed by GitHub
parent 5b57a5b726
commit 5c64a0952e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 250 additions and 228 deletions

View file

@ -121,6 +121,11 @@ ifneq ($(filter ppc64%,$(UNAME_M)),)
endif
endif
ifndef LLAMA_NO_K_QUANTS
CFLAGS += -DGGML_USE_K_QUANTS
OBJS += k_quants.o
endif
ifndef LLAMA_NO_ACCELERATE
# Mac M1 - include Accelerate framework.
# `-framework Accelerate` works on Mac Intel as well, with negliable performance boost (as of the predict time).
@ -140,7 +145,7 @@ ifdef LLAMA_OPENBLAS
endif # LLAMA_OPENBLAS
ifdef LLAMA_BLIS
CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/blis -I/usr/include/blis
CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/blis -I/usr/include/blis
LDFLAGS += -lblis -L/usr/local/lib
endif # LLAMA_BLIS
@ -212,6 +217,11 @@ ifneq ($(filter armv8%,$(UNAME_M)),)
CFLAGS += -mfp16-format=ieee -mno-unaligned-access
endif
ifdef LLAMA_NO_K_QUANTS
k_quants.o: k_quants.c k_quants.h
$(CC) $(CFLAGS) -c $< -o $@
endif # LLAMA_NO_K_QUANTS
#
# Print build information
#
@ -231,10 +241,7 @@ $(info )
# Build library
#
ggml.o: ggml.c ggml.h ggml-cuda.h ggml-quants-k.h
$(CC) $(CFLAGS) -c $< -o $@
ggml-quants-k.o: ggml-quants-k.c ggml-quants-k.h ggml.h ggml-cuda.h
ggml.o: ggml.c ggml.h ggml-cuda.h
$(CC) $(CFLAGS) -c $< -o $@
llama.o: llama.cpp ggml.h ggml-cuda.h llama.h llama-util.h
@ -243,7 +250,7 @@ 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 ggml-quants-k.o $(OBJS)
libllama.so: llama.o ggml.o $(OBJS)
$(CXX) $(CXXFLAGS) -shared -fPIC -o $@ $^ $(LDFLAGS)
clean:
@ -253,28 +260,28 @@ 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 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 ggml-quants-k.o llama.o $(OBJS)
quantize: examples/quantize/quantize.cpp build-info.h ggml.o llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
quantize-stats: examples/quantize-stats/quantize-stats.cpp build-info.h ggml.o ggml-quants-k.o llama.o $(OBJS)
quantize-stats: examples/quantize-stats/quantize-stats.cpp build-info.h ggml.o llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
perplexity: examples/perplexity/perplexity.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
perplexity: examples/perplexity/perplexity.cpp build-info.h ggml.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
embedding: examples/embedding/embedding.cpp build-info.h ggml.o ggml-quants-k.o llama.o common.o $(OBJS)
embedding: examples/embedding/embedding.cpp build-info.h ggml.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 ggml-quants-k.o llama.o common.o $(OBJS)
save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.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 ggml-quants-k.o llama.o common.o $(OBJS)
server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp build-info.h ggml.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
@ -289,11 +296,11 @@ build-info.h: $(wildcard .git/index) scripts/build-info.sh
# Tests
#
benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o ggml-quants-k.o $(OBJS)
benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
./$@
vdot: pocs/vdot/vdot.cpp ggml.o ggml-quants-k.o $(OBJS)
vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
.PHONY: tests clean