common : fix mirostat state when using multiple sequences (#3543)
* Fix mirostat state when using multiple sequences * Fix mirostat by completely refactoring sampling! * Try to fix zig build. * Export function to fetch/create default sampler states Code formatting cleanups and add some comments Silence a warning about id not being used when logging is disabled * Apply some renaming suggestions. Fix comments that were out of sync with the pull. * Use more consistant naming convention for sampling contexts
This commit is contained in:
Kerfuffle
GitHub
parent
8c70a5ff25
commit
70c29da118
14 changed files with 495 additions and 334 deletions
86
Makefile
86
Makefile
|
|
@ -178,6 +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
|
||||
|
|
@ -526,7 +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
|
||||
|
|
@ -548,19 +572,19 @@ 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)
|
||||
|
|
@ -572,53 +596,53 @@ 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)
|
||||
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
|
||||
|
|
@ -659,40 +683,40 @@ 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
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue