Skip to content

Commit

Permalink
Merge branch 'master' of https://github.com/ggerganov/llama.cpp
Browse files Browse the repository at this point in the history
  • Loading branch information
@FSSRepo
FSSRepo committed Oct 12, 2023
2 parents 7850421 + 370359e commit b716eeb
Show file tree
Hide file tree
Showing 37 changed files with 13,716 additions and 2,553 deletions.
2 changes: 2 additions & 0 deletions .gitignore
View file
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@ models-mnt
/infill
/libllama.so
/llama-bench
/llava
/main
/metal
/perplexity
Expand All @@ -56,6 +57,7 @@ models-mnt
/server
/simple
/batched
/batched-bench
/export-lora
/finetune
/speculative
Expand Down
6 changes: 3 additions & 3 deletions CMakeLists.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -422,8 +422,7 @@ endif()
if (LLAMA_ALL_WARNINGS)
if (NOT MSVC)
set(warning_flags -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function)
set(c_flags -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int
-Werror=implicit-function-declaration)
set(c_flags -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration)
set(cxx_flags -Wmissing-declarations -Wmissing-noreturn)
set(host_cxx_flags "")

Expand Down Expand Up @@ -455,7 +454,8 @@ if (LLAMA_ALL_WARNINGS)
set(c_flags ${c_flags} ${warning_flags})
set(cxx_flags ${cxx_flags} ${warning_flags})
add_compile_options("$<$<COMPILE_LANGUAGE:C>:${c_flags}>"
"$<$<COMPILE_LANGUAGE:CXX>:${cxx_flags} ${host_cxx_flags}>")
"$<$<COMPILE_LANGUAGE:CXX>:${cxx_flags}>"
"$<$<COMPILE_LANGUAGE:CXX>:${host_cxx_flags}>")

endif()

Expand Down
102 changes: 69 additions & 33 deletions Makefile
View file
Original file line number Diff line number Diff line change
@@ -1,8 +1,14 @@
# Define the default target now so that it is always the first target
BUILD_TARGETS = main quantize quantize-stats perplexity embedding vdot q8dot train-text-from-scratch convert-llama2c-to-ggml simple batched save-load-state server embd-input-test gguf llama-bench baby-llama beam-search speculative infill benchmark-matmult parallel finetune export-lora tests/test-c.o
BUILD_TARGETS = \
main quantize quantize-stats perplexity embedding vdot q8dot train-text-from-scratch convert-llama2c-to-ggml \
simple batched batched-bench save-load-state server embd-input-test gguf llama-bench llava baby-llama beam-search \
speculative infill benchmark-matmult parallel finetune export-lora tests/test-c.o

# Binaries only useful for tests
TEST_TARGETS = tests/test-llama-grammar tests/test-grammar-parser tests/test-double-float tests/test-grad0 tests/test-opt tests/test-quantize-fns tests/test-quantize-perf tests/test-sampling tests/test-tokenizer-0-llama tests/test-tokenizer-0-falcon tests/test-tokenizer-1-llama tests/test-tokenizer-1-bpe
TEST_TARGETS = \
tests/test-llama-grammar tests/test-grammar-parser tests/test-double-float tests/test-grad0 tests/test-opt \
tests/test-quantize-fns tests/test-quantize-perf tests/test-sampling tests/test-tokenizer-0-llama \
tests/test-tokenizer-0-falcon tests/test-tokenizer-1-llama tests/test-tokenizer-1-bpe

# Code coverage output files
COV_TARGETS = *.gcno tests/*.gcno *.gcda tests/*.gcda *.gcov tests/*.gcov lcov-report gcovr-report
Expand Down Expand Up @@ -172,6 +178,24 @@ else
MK_CPPFLAGS += -DNDEBUG
endif

ifdef LLAMA_SANITIZE_THREAD
MK_CFLAGS += -fsanitize=thread -g
MK_CXXFLAGS += -fsanitize=thread -g
MK_LDFLAGS += -fsanitize=thread -g
endif

ifdef LLAMA_SANITIZE_ADDRESS
MK_CFLAGS += -fsanitize=address -fno-omit-frame-pointer -g
MK_CXXFLAGS += -fsanitize=address -fno-omit-frame-pointer -g
MK_LDFLAGS += -fsanitize=address -fno-omit-frame-pointer -g
endif

ifdef LLAMA_SANITIZE_UNDEFINED
MK_CFLAGS += -fsanitize=undefined -g
MK_CXXFLAGS += -fsanitize=undefined -g
MK_LDFLAGS += -fsanitize=undefined -g
endif

ifdef LLAMA_SERVER_VERBOSE
MK_CPPFLAGS += -DSERVER_VERBOSE=$(LLAMA_SERVER_VERBOSE)
endif
Expand Down Expand Up @@ -520,7 +544,13 @@ OBJS += ggml-alloc.o ggml-backend.o
llama.o: llama.cpp ggml.h ggml-alloc.h ggml-backend.h ggml-cuda.h ggml-metal.h llama.h
$(CXX) $(CXXFLAGS) -c $< -o $@

common.o: common/common.cpp common/common.h build-info.h common/log.h
COMMON_H_DEPS = common/common.h common/sampling.h build-info.h common/log.h
COMMON_DEPS = $(COMMON_H_DEPS) common.o sampling.o

common.o: common/common.cpp $(COMMON_H_DEPS)
$(CXX) $(CXXFLAGS) -c $< -o $@

sampling.o: common/sampling.cpp $(COMMON_H_DEPS)
$(CXX) $(CXXFLAGS) -c $< -o $@

console.o: common/console.cpp common/console.h
Expand All @@ -542,19 +572,22 @@ clean:
# Examples
#

main: examples/main/main.cpp build-info.h ggml.o llama.o common.o console.o grammar-parser.o $(OBJS)
main: examples/main/main.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) console.o grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
@echo
@echo '==== Run ./main -h for help. ===='
@echo

infill: examples/infill/infill.cpp build-info.h ggml.o llama.o common.o console.o grammar-parser.o $(OBJS)
infill: examples/infill/infill.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) console.o grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

simple: examples/simple/simple.cpp build-info.h ggml.o llama.o common.o $(OBJS)
simple: examples/simple/simple.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

batched: examples/batched/batched.cpp build-info.h ggml.o llama.o common.o $(OBJS)
batched: examples/batched/batched.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

batched-bench: examples/batched-bench/batched-bench.cpp build-info.h ggml.o llama.o common.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

quantize: examples/quantize/quantize.cpp build-info.h ggml.o llama.o $(OBJS)
Expand All @@ -563,53 +596,56 @@ quantize: examples/quantize/quantize.cpp build-info.h ggml.
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 llama.o common.o $(OBJS)
perplexity: examples/perplexity/perplexity.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

embedding: examples/embedding/embedding.cpp build-info.h ggml.o llama.o common.o $(OBJS)
embedding: examples/embedding/embedding.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(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 $(OBJS)
save-load-state: examples/save-load-state/save-load-state.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp examples/server/index.html.hpp examples/server/index.js.hpp examples/server/completion.js.hpp build-info.h ggml.o llama.o common.o grammar-parser.o $(OBJS)
server: examples/server/server.cpp examples/server/httplib.h examples/server/json.hpp examples/server/index.html.hpp examples/server/index.js.hpp examples/server/completion.js.hpp build-info.h ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) -Iexamples/server $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS) $(LWINSOCK2)

$(LIB_PRE)embdinput$(DSO_EXT): examples/embd-input/embd-input.h examples/embd-input/embd-input-lib.cpp build-info.h ggml.o llama.o common.o $(OBJS)
$(LIB_PRE)embdinput$(DSO_EXT): examples/embd-input/embd-input.h examples/embd-input/embd-input-lib.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) --shared $(CXXFLAGS) $(filter-out %.h,$(filter-out %.hpp,$^)) -o $@ $(LDFLAGS)


embd-input-test: $(LIB_PRE)embdinput$(DSO_EXT) examples/embd-input/embd-input-test.cpp build-info.h ggml.o llama.o common.o $(OBJS)
embd-input-test: $(LIB_PRE)embdinput$(DSO_EXT) examples/embd-input/embd-input-test.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %$(DSO_EXT),$(filter-out %.h,$(filter-out %.hpp,$^))) -o $@ $(LDFLAGS) -L. -lembdinput

gguf: examples/gguf/gguf.cpp ggml.o llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

train-text-from-scratch: examples/train-text-from-scratch/train-text-from-scratch.cpp ggml.o llama.o common.o train.o $(OBJS)
train-text-from-scratch: examples/train-text-from-scratch/train-text-from-scratch.cpp ggml.o llama.o $(COMMON_DEPS) train.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

convert-llama2c-to-ggml: examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp ggml.o llama.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

llama-bench: examples/llama-bench/llama-bench.cpp build-info.h ggml.o llama.o common.o $(OBJS)
llama-bench: examples/llama-bench/llama-bench.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

baby-llama: examples/baby-llama/baby-llama.cpp ggml.o llama.o common.o train.o $(OBJS)
llava: examples/llava/llava.cpp examples/llava/llava-utils.h examples/llava/clip.cpp examples/llava/clip.h common/stb_image.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS) -Wno-cast-qual

baby-llama: examples/baby-llama/baby-llama.cpp ggml.o llama.o $(COMMON_DEPS) train.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

beam-search: examples/beam-search/beam-search.cpp build-info.h ggml.o llama.o common.o $(OBJS)
beam-search: examples/beam-search/beam-search.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

finetune: examples/finetune/finetune.cpp build-info.h ggml.o llama.o common.o train.o $(OBJS)
finetune: examples/finetune/finetune.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) train.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

export-lora: examples/export-lora/export-lora.cpp build-info.h ggml.o llama.o common.o $(OBJS)
export-lora: examples/export-lora/export-lora.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

speculative: examples/speculative/speculative.cpp build-info.h ggml.o llama.o common.o grammar-parser.o $(OBJS)
speculative: examples/speculative/speculative.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

parallel: examples/parallel/parallel.cpp build-info.h ggml.o llama.o common.o $(OBJS)
parallel: examples/parallel/parallel.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

ifdef LLAMA_METAL
Expand Down Expand Up @@ -650,40 +686,40 @@ vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
q8dot: pocs/vdot/q8dot.cpp ggml.o $(OBJS)
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)

tests/test-llama-grammar: tests/test-llama-grammar.cpp build-info.h ggml.o common.o grammar-parser.o $(OBJS)
tests/test-llama-grammar: tests/test-llama-grammar.cpp build-info.h ggml.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-grammar-parser: tests/test-grammar-parser.cpp build-info.h ggml.o llama.o common.o grammar-parser.o $(OBJS)
tests/test-grammar-parser: tests/test-grammar-parser.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) grammar-parser.o $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-double-float: tests/test-double-float.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-double-float: tests/test-double-float.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-grad0: tests/test-grad0.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-grad0: tests/test-grad0.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-opt: tests/test-opt.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-opt: tests/test-opt.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-quantize-fns: tests/test-quantize-fns.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-quantize-fns: tests/test-quantize-fns.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-quantize-perf: tests/test-quantize-perf.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-quantize-perf: tests/test-quantize-perf.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-sampling: tests/test-sampling.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-sampling: tests/test-sampling.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-tokenizer-0-falcon: tests/test-tokenizer-0-falcon.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-tokenizer-0-falcon: tests/test-tokenizer-0-falcon.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-tokenizer-0-llama: tests/test-tokenizer-0-llama.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-tokenizer-0-llama: tests/test-tokenizer-0-llama.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-tokenizer-1-bpe: tests/test-tokenizer-1-bpe.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-tokenizer-1-bpe: tests/test-tokenizer-1-bpe.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-tokenizer-1-llama: tests/test-tokenizer-1-llama.cpp build-info.h ggml.o llama.o common.o $(OBJS)
tests/test-tokenizer-1-llama: tests/test-tokenizer-1-llama.cpp build-info.h ggml.o llama.o $(COMMON_DEPS) $(OBJS)
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)

tests/test-c.o: tests/test-c.c llama.h
Expand Down
2 changes: 1 addition & 1 deletion README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -279,7 +279,7 @@ In order to build llama.cpp you have three different options.
On MacOS, Metal is enabled by default. Using Metal makes the computation run on the GPU.
To disable the Metal build at compile time use the `LLAMA_NO_METAL=1` flag or the `LLAMA_METAL=OFF` cmake option.

When built with Metal support, you can explicitly disable GPU inference with the `--gpu-layers|-ngl 0` command-line
When built with Metal support, you can explicitly disable GPU inference with the `--n-gpu-layers|-ngl 0` command-line
argument.

### MPI Build
Expand Down
5 changes: 3 additions & 2 deletions build.zig
View file
Original file line number Diff line number Diff line change
Expand Up @@ -128,17 +128,18 @@ pub fn build(b: *std.build.Builder) !void {
const llama = make.obj("llama", "llama.cpp");
const common = make.obj("common", "common/common.cpp");
const console = make.obj("console", "common/console.cpp");
const sampling = make.obj("sampling", "common/sampling.cpp");
const grammar_parser = make.obj("grammar-parser", "common/grammar-parser.cpp");
const train = make.obj("train", "common/train.cpp");

_ = make.exe("main", "examples/main/main.cpp", &.{ ggml, ggml_alloc, ggml_backend, llama, common, console, grammar_parser });
_ = make.exe("main", "examples/main/main.cpp", &.{ ggml, ggml_alloc, ggml_backend, llama, common, sampling, console, grammar_parser });
_ = make.exe("quantize", "examples/quantize/quantize.cpp", &.{ ggml, ggml_alloc, ggml_backend, llama, common });
_ = make.exe("perplexity", "examples/perplexity/perplexity.cpp", &.{ ggml, ggml_alloc, ggml_backend, llama, common });
_ = make.exe("embedding", "examples/embedding/embedding.cpp", &.{ ggml, ggml_alloc, ggml_backend, llama, common });
_ = make.exe("finetune", "examples/finetune/finetune.cpp", &.{ ggml, ggml_alloc, ggml_backend, llama, common, train });
_ = make.exe("train-text-from-scratch", "examples/train-text-from-scratch/train-text-from-scratch.cpp", &.{ ggml, ggml_alloc, ggml_backend, llama, common, train });

const server = make.exe("server", "examples/server/server.cpp", &.{ ggml, ggml_alloc, ggml_backend, llama, common, grammar_parser });
const server = make.exe("server", "examples/server/server.cpp", &.{ ggml, ggml_alloc, ggml_backend, llama, common, sampling, grammar_parser });
if (server.target.isWindows()) {
server.linkSystemLibrary("ws2_32");
}
Expand Down
10 changes: 6 additions & 4 deletions ci/run.sh
View file
Original file line number Diff line number Diff line change
Expand Up @@ -496,10 +496,12 @@ test $ret -eq 0 && gg_run ctest_debug
test $ret -eq 0 && gg_run ctest_release

if [ -z ${GG_BUILD_LOW_PERF} ]; then
if [ -z ${GG_BUILD_CUDA} ]; then
test $ret -eq 0 && gg_run open_llama_3b_v2
else
test $ret -eq 0 && gg_run open_llama_7b_v2
if [ -z ${GG_BUILD_VRAM_GB} ] || [ ${GG_BUILD_VRAM_GB} -ge 8 ]; then
if [ -z ${GG_BUILD_CUDA} ]; then
test $ret -eq 0 && gg_run open_llama_3b_v2
else
test $ret -eq 0 && gg_run open_llama_7b_v2
fi
fi
fi

Expand Down
2 changes: 2 additions & 0 deletions common/CMakeLists.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ set(TARGET common)
add_library(${TARGET} OBJECT
common.h
common.cpp
sampling.h
sampling.cpp
console.h
console.cpp
grammar-parser.h
Expand Down
Loading

0 comments on commit b716eeb

Please sign in to comment.