❯ make clean && LLAMA_METAL=1 make -j
I llama.cpp build info:
I UNAME_S:  Darwin
I UNAME_P:  arm
I UNAME_M:  arm64
I CFLAGS:   -I.              -O3 -std=c11   -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -pthread -DGGML_USE_K_QUANTS -DGGML_USE_ACCELERATE
I CXXFLAGS: -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS
I LDFLAGS:   -framework Accelerate
I CC:       Apple clang version 14.0.3 (clang-1403.0.22.14.1)
I CXX:      Apple clang version 14.0.3 (clang-1403.0.22.14.1)

rm -vf *.o *.so *.dll main quantize quantize-stats perplexity embedding benchmark-matmult save-load-state server simple vdot train-text-from-scratch embd-input-test build-info.h 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
common.o
ggml-alloc.o
ggml-metal.o
ggml.o
grammar-parser.o
k_quants.o
llama.o
libembdinput.so
main
quantize
quantize-stats
perplexity
embedding
server
simple
vdot
train-text-from-scratch
embd-input-test
build-info.h
I llama.cpp build info:
I UNAME_S:  Darwin
I UNAME_P:  arm
I UNAME_M:  arm64
I CFLAGS:   -I.              -O3 -std=c11   -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -pthread -DGGML_USE_K_QUANTS -DGGML_USE_ACCELERATE -DGGML_USE_METAL -DGGML_METAL_NDEBUG
I CXXFLAGS: -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL
I LDFLAGS:   -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
I CC:       Apple clang version 14.0.3 (clang-1403.0.22.14.1)
I CXX:      Apple clang version 14.0.3 (clang-1403.0.22.14.1)

cc  -I.              -O3 -std=c11   -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -pthread -DGGML_USE_K_QUANTS -DGGML_USE_ACCELERATE -DGGML_USE_METAL -DGGML_METAL_NDEBUG   -c ggml.c -o ggml.o
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL -c llama.cpp -o llama.o
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL -c examples/common.cpp -o common.o
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL -c examples/grammar-parser.cpp -o grammar-parser.o
cc -I.              -O3 -std=c11   -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -pthread -DGGML_USE_K_QUANTS -DGGML_USE_ACCELERATE -DGGML_USE_METAL -DGGML_METAL_NDEBUG   -c -o k_quants.o k_quants.c
cc -I.              -O3 -std=c11   -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -pthread -DGGML_USE_K_QUANTS -DGGML_USE_ACCELERATE -DGGML_USE_METAL -DGGML_METAL_NDEBUG -c ggml-metal.m -o ggml-metal.o
cc  -I.              -O3 -std=c11   -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -pthread -DGGML_USE_K_QUANTS -DGGML_USE_ACCELERATE -DGGML_USE_METAL -DGGML_METAL_NDEBUG   -c ggml-alloc.c -o ggml-alloc.o
examples/common.cpp:569:122: warning: format specifies type 'int' but the argument has type 'size_t' (aka 'unsigned long') [-Wformat]
    fprintf(stdout, "  --hellaswag-tasks N   number of tasks to use when computing the HellaSwag score (default: %d)\n", params.hellaswag_tasks);
                                                                                                                 ~~      ^~~~~~~~~~~~~~~~~~~~~~
                                                                                                                 %zu
1 warning generated.
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL examples/main/main.cpp ggml.o llama.o common.o grammar-parser.o k_quants.o ggml-metal.o ggml-alloc.o -o main  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL examples/quantize/quantize.cpp ggml.o llama.o k_quants.o ggml-metal.o ggml-alloc.o -o quantize  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL examples/quantize-stats/quantize-stats.cpp ggml.o llama.o k_quants.o ggml-metal.o ggml-alloc.o -o quantize-stats  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL examples/perplexity/perplexity.cpp ggml.o llama.o common.o k_quants.o ggml-metal.o ggml-alloc.o -o perplexity  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL examples/embedding/embedding.cpp ggml.o llama.o common.o k_quants.o ggml-metal.o ggml-alloc.o -o embedding  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL pocs/vdot/vdot.cpp ggml.o k_quants.o ggml-metal.o ggml-alloc.o -o vdot  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL examples/train-text-from-scratch/train-text-from-scratch.cpp ggml.o llama.o k_quants.o ggml-metal.o ggml-alloc.o -o train-text-from-scratch  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL examples/simple/simple.cpp ggml.o llama.o common.o k_quants.o ggml-metal.o ggml-alloc.o -o simple  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL -Iexamples/server examples/server/server.cpp ggml.o llama.o common.o k_quants.o ggml-metal.o ggml-alloc.o -o server  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ --shared -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL examples/embd-input/embd-input-lib.cpp ggml.o llama.o common.o k_quants.o ggml-metal.o ggml-alloc.o -o libembdinput.so  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders
c++ -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS -DGGML_USE_METAL examples/embd-input/embd-input-test.cpp ggml.o llama.o common.o k_quants.o ggml-metal.o ggml-alloc.o -o embd-input-test  -framework Accelerate -framework Foundation -framework Metal -framework MetalKit -framework MetalPerformanceShaders -L. -lembdinput

====  Run ./main -h for help.  ====