Modelpublic
Felipe97/llama-cpp-compiled

sourceHugging Faceupdated 21d agoView on Hugging Face
0likes1.2kdownloads
compile_commands.json2684 linesDownload Raw Back to build
1[2{3  "directory": "/kaggle/working/llama.cpp/build/ggml/src",4  "command": "/usr/bin/cc -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_base_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/build/ggml/src -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu11 -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -fopenmp -o CMakeFiles/ggml-base.dir/ggml.c.o -c /kaggle/working/llama.cpp/ggml/src/ggml.c",5  "file": "/kaggle/working/llama.cpp/ggml/src/ggml.c",6  "output": "ggml/src/CMakeFiles/ggml-base.dir/ggml.c.o"7},8{9  "directory": "/kaggle/working/llama.cpp/build/ggml/src",10  "command": "/usr/bin/c++ -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_base_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/build/ggml/src -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -fopenmp -o CMakeFiles/ggml-base.dir/ggml.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml.cpp",11  "file": "/kaggle/working/llama.cpp/ggml/src/ggml.cpp",12  "output": "ggml/src/CMakeFiles/ggml-base.dir/ggml.cpp.o"13},14{15  "directory": "/kaggle/working/llama.cpp/build/ggml/src",16  "command": "/usr/bin/cc -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_base_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/build/ggml/src -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu11 -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -fopenmp -o CMakeFiles/ggml-base.dir/ggml-alloc.c.o -c /kaggle/working/llama.cpp/ggml/src/ggml-alloc.c",17  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-alloc.c",18  "output": "ggml/src/CMakeFiles/ggml-base.dir/ggml-alloc.c.o"19},20{21  "directory": "/kaggle/working/llama.cpp/build/ggml/src",22  "command": "/usr/bin/c++ -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_base_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/build/ggml/src -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -fopenmp -o CMakeFiles/ggml-base.dir/ggml-backend.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-backend.cpp",23  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-backend.cpp",24  "output": "ggml/src/CMakeFiles/ggml-base.dir/ggml-backend.cpp.o"25},26{27  "directory": "/kaggle/working/llama.cpp/build/ggml/src",28  "command": "/usr/bin/c++ -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_base_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/build/ggml/src -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -fopenmp -o CMakeFiles/ggml-base.dir/ggml-backend-meta.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-backend-meta.cpp",29  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-backend-meta.cpp",30  "output": "ggml/src/CMakeFiles/ggml-base.dir/ggml-backend-meta.cpp.o"31},32{33  "directory": "/kaggle/working/llama.cpp/build/ggml/src",34  "command": "/usr/bin/c++ -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_base_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/build/ggml/src -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -fopenmp -o CMakeFiles/ggml-base.dir/ggml-opt.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-opt.cpp",35  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-opt.cpp",36  "output": "ggml/src/CMakeFiles/ggml-base.dir/ggml-opt.cpp.o"37},38{39  "directory": "/kaggle/working/llama.cpp/build/ggml/src",40  "command": "/usr/bin/c++ -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_base_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/build/ggml/src -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -fopenmp -o CMakeFiles/ggml-base.dir/ggml-threading.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-threading.cpp",41  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-threading.cpp",42  "output": "ggml/src/CMakeFiles/ggml-base.dir/ggml-threading.cpp.o"43},44{45  "directory": "/kaggle/working/llama.cpp/build/ggml/src",46  "command": "/usr/bin/cc -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_base_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/build/ggml/src -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu11 -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -fopenmp -o CMakeFiles/ggml-base.dir/ggml-quants.c.o -c /kaggle/working/llama.cpp/ggml/src/ggml-quants.c",47  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-quants.c",48  "output": "ggml/src/CMakeFiles/ggml-base.dir/ggml-quants.c.o"49},50{51  "directory": "/kaggle/working/llama.cpp/build/ggml/src",52  "command": "/usr/bin/c++ -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_base_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/build/ggml/src -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -fopenmp -o CMakeFiles/ggml-base.dir/gguf.cpp.o -c /kaggle/working/llama.cpp/ggml/src/gguf.cpp",53  "file": "/kaggle/working/llama.cpp/ggml/src/gguf.cpp",54  "output": "ggml/src/CMakeFiles/ggml-base.dir/gguf.cpp.o"55},56{57  "directory": "/kaggle/working/llama.cpp/build/ggml/src",58  "command": "/usr/bin/cc -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu11 -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/ggml-cpu.c.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c",59  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c",60  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/ggml-cpu.c.o"61},62{63  "directory": "/kaggle/working/llama.cpp/build/ggml/src",64  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/ggml-cpu.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp",65  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp",66  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/ggml-cpu.cpp.o"67},68{69  "directory": "/kaggle/working/llama.cpp/build/ggml/src",70  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/repack.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/repack.cpp",71  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/repack.cpp",72  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/repack.cpp.o"73},74{75  "directory": "/kaggle/working/llama.cpp/build/ggml/src",76  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/iqp.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/iqp.cpp",77  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/iqp.cpp",78  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/iqp.cpp.o"79},80{81  "directory": "/kaggle/working/llama.cpp/build/ggml/src",82  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/hbm.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/hbm.cpp",83  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/hbm.cpp",84  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/hbm.cpp.o"85},86{87  "directory": "/kaggle/working/llama.cpp/build/ggml/src",88  "command": "/usr/bin/cc -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu11 -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/quants.c.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/quants.c",89  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/quants.c",90  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/quants.c.o"91},92{93  "directory": "/kaggle/working/llama.cpp/build/ggml/src",94  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/traits.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/traits.cpp",95  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/traits.cpp",96  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/traits.cpp.o"97},98{99  "directory": "/kaggle/working/llama.cpp/build/ggml/src",100  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/amx/amx.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/amx/amx.cpp",101  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/amx/amx.cpp",102  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/amx/amx.cpp.o"103},104{105  "directory": "/kaggle/working/llama.cpp/build/ggml/src",106  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/amx/mmq.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp",107  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp",108  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/amx/mmq.cpp.o"109},110{111  "directory": "/kaggle/working/llama.cpp/build/ggml/src",112  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/binary-ops.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp",113  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp",114  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/binary-ops.cpp.o"115},116{117  "directory": "/kaggle/working/llama.cpp/build/ggml/src",118  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/unary-ops.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/unary-ops.cpp",119  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/unary-ops.cpp",120  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/unary-ops.cpp.o"121},122{123  "directory": "/kaggle/working/llama.cpp/build/ggml/src",124  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/vec.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/vec.cpp",125  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/vec.cpp",126  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/vec.cpp.o"127},128{129  "directory": "/kaggle/working/llama.cpp/build/ggml/src",130  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/ops.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/ops.cpp",131  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/ops.cpp",132  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/ops.cpp.o"133},134{135  "directory": "/kaggle/working/llama.cpp/build/ggml/src",136  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/llamafile/sgemm.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp",137  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp",138  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/llamafile/sgemm.cpp.o"139},140{141  "directory": "/kaggle/working/llama.cpp/build/ggml/src",142  "command": "/usr/bin/cc -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu11 -fPIC -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wdouble-promotion -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/x86/quants.c.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c",143  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c",144  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/x86/quants.c.o"145},146{147  "directory": "/kaggle/working/llama.cpp/build/ggml/src",148  "command": "/usr/bin/c++ -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU_REPACK -DGGML_USE_LLAMAFILE -DGGML_USE_OPENMP -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cpu_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/.. -I/kaggle/working/llama.cpp/ggml/src/. -I/kaggle/working/llama.cpp/ggml/src/ggml-cpu -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -march=native -fopenmp -o CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/x86/repack.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp",149  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp",150  "output": "ggml/src/CMakeFiles/ggml-cpu.dir/ggml-cpu/arch/x86/repack.cpp.o"151},152{153  "directory": "/kaggle/working/llama.cpp/build/ggml/src",154  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/ggml.dir/ggml-backend-dl.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-backend-dl.cpp",155  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-backend-dl.cpp",156  "output": "ggml/src/CMakeFiles/ggml.dir/ggml-backend-dl.cpp.o"157},158{159  "directory": "/kaggle/working/llama.cpp/build/ggml/src",160  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_BUILD -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_EXPORTS -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -std=gnu++17 -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/ggml.dir/ggml-backend-reg.cpp.o -c /kaggle/working/llama.cpp/ggml/src/ggml-backend-reg.cpp",161  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-backend-reg.cpp",162  "output": "ggml/src/CMakeFiles/ggml.dir/ggml-backend-reg.cpp.o"163},164{165  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",166  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/acc.cu -o CMakeFiles/ggml-cuda.dir/acc.cu.o",167  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/acc.cu",168  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/acc.cu.o"169},170{171  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",172  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/add-id.cu -o CMakeFiles/ggml-cuda.dir/add-id.cu.o",173  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/add-id.cu",174  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/add-id.cu.o"175},176{177  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",178  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/allreduce.cu -o CMakeFiles/ggml-cuda.dir/allreduce.cu.o",179  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/allreduce.cu",180  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/allreduce.cu.o"181},182{183  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",184  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/arange.cu -o CMakeFiles/ggml-cuda.dir/arange.cu.o",185  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/arange.cu",186  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/arange.cu.o"187},188{189  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",190  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/argmax.cu -o CMakeFiles/ggml-cuda.dir/argmax.cu.o",191  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/argmax.cu",192  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argmax.cu.o"193},194{195  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",196  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/argsort.cu -o CMakeFiles/ggml-cuda.dir/argsort.cu.o",197  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/argsort.cu",198  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/argsort.cu.o"199},200{201  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",202  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/binbcast.cu -o CMakeFiles/ggml-cuda.dir/binbcast.cu.o",203  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/binbcast.cu",204  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/binbcast.cu.o"205},206{207  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",208  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/clamp.cu -o CMakeFiles/ggml-cuda.dir/clamp.cu.o",209  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/clamp.cu",210  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/clamp.cu.o"211},212{213  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",214  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/col2im-1d.cu -o CMakeFiles/ggml-cuda.dir/col2im-1d.cu.o",215  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/col2im-1d.cu",216  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/col2im-1d.cu.o"217},218{219  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",220  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/concat.cu -o CMakeFiles/ggml-cuda.dir/concat.cu.o",221  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/concat.cu",222  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/concat.cu.o"223},224{225  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",226  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/conv-transpose-1d.cu -o CMakeFiles/ggml-cuda.dir/conv-transpose-1d.cu.o",227  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/conv-transpose-1d.cu",228  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv-transpose-1d.cu.o"229},230{231  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",232  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/conv2d-dw.cu -o CMakeFiles/ggml-cuda.dir/conv2d-dw.cu.o",233  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/conv2d-dw.cu",234  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-dw.cu.o"235},236{237  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",238  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/conv2d-transpose.cu -o CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.o",239  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/conv2d-transpose.cu",240  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d-transpose.cu.o"241},242{243  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",244  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/conv2d.cu -o CMakeFiles/ggml-cuda.dir/conv2d.cu.o",245  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/conv2d.cu",246  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/conv2d.cu.o"247},248{249  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",250  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/convert.cu -o CMakeFiles/ggml-cuda.dir/convert.cu.o",251  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/convert.cu",252  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/convert.cu.o"253},254{255  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",256  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/count-equal.cu -o CMakeFiles/ggml-cuda.dir/count-equal.cu.o",257  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/count-equal.cu",258  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/count-equal.cu.o"259},260{261  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",262  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/cpy.cu -o CMakeFiles/ggml-cuda.dir/cpy.cu.o",263  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/cpy.cu",264  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cpy.cu.o"265},266{267  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",268  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/cross-entropy-loss.cu -o CMakeFiles/ggml-cuda.dir/cross-entropy-loss.cu.o",269  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/cross-entropy-loss.cu",270  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cross-entropy-loss.cu.o"271},272{273  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",274  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/cumsum.cu -o CMakeFiles/ggml-cuda.dir/cumsum.cu.o",275  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/cumsum.cu",276  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/cumsum.cu.o"277},278{279  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",280  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/diag.cu -o CMakeFiles/ggml-cuda.dir/diag.cu.o",281  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/diag.cu",282  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diag.cu.o"283},284{285  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",286  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/diagmask.cu -o CMakeFiles/ggml-cuda.dir/diagmask.cu.o",287  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/diagmask.cu",288  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/diagmask.cu.o"289},290{291  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",292  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/dsv4-hc.cu -o CMakeFiles/ggml-cuda.dir/dsv4-hc.cu.o",293  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/dsv4-hc.cu",294  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/dsv4-hc.cu.o"295},296{297  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",298  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/fattn-tile.cu -o CMakeFiles/ggml-cuda.dir/fattn-tile.cu.o",299  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/fattn-tile.cu",300  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn-tile.cu.o"301},302{303  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",304  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/fattn.cu -o CMakeFiles/ggml-cuda.dir/fattn.cu.o",305  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/fattn.cu",306  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fattn.cu.o"307},308{309  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",310  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/fill.cu -o CMakeFiles/ggml-cuda.dir/fill.cu.o",311  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/fill.cu",312  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fill.cu.o"313},314{315  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",316  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/fwht.cu -o CMakeFiles/ggml-cuda.dir/fwht.cu.o",317  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/fwht.cu",318  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/fwht.cu.o"319},320{321  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",322  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/gated_delta_net.cu -o CMakeFiles/ggml-cuda.dir/gated_delta_net.cu.o",323  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/gated_delta_net.cu",324  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/gated_delta_net.cu.o"325},326{327  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",328  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/getrows.cu -o CMakeFiles/ggml-cuda.dir/getrows.cu.o",329  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/getrows.cu",330  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/getrows.cu.o"331},332{333  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",334  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu -o CMakeFiles/ggml-cuda.dir/ggml-cuda.cu.o",335  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/ggml-cuda.cu",336  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ggml-cuda.cu.o"337},338{339  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",340  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/gla.cu -o CMakeFiles/ggml-cuda.dir/gla.cu.o",341  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/gla.cu",342  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/gla.cu.o"343},344{345  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",346  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/im2col.cu -o CMakeFiles/ggml-cuda.dir/im2col.cu.o",347  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/im2col.cu",348  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/im2col.cu.o"349},350{351  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",352  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/lightning-indexer.cu -o CMakeFiles/ggml-cuda.dir/lightning-indexer.cu.o",353  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/lightning-indexer.cu",354  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/lightning-indexer.cu.o"355},356{357  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",358  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/mean.cu -o CMakeFiles/ggml-cuda.dir/mean.cu.o",359  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/mean.cu",360  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mean.cu.o"361},362{363  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",364  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmf.cu -o CMakeFiles/ggml-cuda.dir/mmf.cu.o",365  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmf.cu",366  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmf.cu.o"367},368{369  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",370  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmid.cu -o CMakeFiles/ggml-cuda.dir/mmid.cu.o",371  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmid.cu",372  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmid.cu.o"373},374{375  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",376  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmq.cu -o CMakeFiles/ggml-cuda.dir/mmq.cu.o",377  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmq.cu",378  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmq.cu.o"379},380{381  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",382  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmvf.cu -o CMakeFiles/ggml-cuda.dir/mmvf.cu.o",383  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmvf.cu",384  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmvf.cu.o"385},386{387  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",388  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmvq.cu -o CMakeFiles/ggml-cuda.dir/mmvq.cu.o",389  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/mmvq.cu",390  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/mmvq.cu.o"391},392{393  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",394  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/moe-weighted-reduction.cu -o CMakeFiles/ggml-cuda.dir/moe-weighted-reduction.cu.o",395  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/moe-weighted-reduction.cu",396  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/moe-weighted-reduction.cu.o"397},398{399  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",400  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/norm.cu -o CMakeFiles/ggml-cuda.dir/norm.cu.o",401  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/norm.cu",402  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/norm.cu.o"403},404{405  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",406  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/opt-step-adamw.cu -o CMakeFiles/ggml-cuda.dir/opt-step-adamw.cu.o",407  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/opt-step-adamw.cu",408  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-adamw.cu.o"409},410{411  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",412  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/opt-step-sgd.cu -o CMakeFiles/ggml-cuda.dir/opt-step-sgd.cu.o",413  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/opt-step-sgd.cu",414  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/opt-step-sgd.cu.o"415},416{417  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",418  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/out-prod.cu -o CMakeFiles/ggml-cuda.dir/out-prod.cu.o",419  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/out-prod.cu",420  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/out-prod.cu.o"421},422{423  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",424  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/pad.cu -o CMakeFiles/ggml-cuda.dir/pad.cu.o",425  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/pad.cu",426  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pad.cu.o"427},428{429  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",430  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/pad_reflect_1d.cu -o CMakeFiles/ggml-cuda.dir/pad_reflect_1d.cu.o",431  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/pad_reflect_1d.cu",432  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pad_reflect_1d.cu.o"433},434{435  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",436  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/pool1d.cu -o CMakeFiles/ggml-cuda.dir/pool1d.cu.o",437  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/pool1d.cu",438  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pool1d.cu.o"439},440{441  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",442  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/pool2d.cu -o CMakeFiles/ggml-cuda.dir/pool2d.cu.o",443  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/pool2d.cu",444  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/pool2d.cu.o"445},446{447  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",448  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/quantize.cu -o CMakeFiles/ggml-cuda.dir/quantize.cu.o",449  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/quantize.cu",450  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/quantize.cu.o"451},452{453  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",454  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/roll.cu -o CMakeFiles/ggml-cuda.dir/roll.cu.o",455  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/roll.cu",456  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/roll.cu.o"457},458{459  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",460  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/rope.cu -o CMakeFiles/ggml-cuda.dir/rope.cu.o",461  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/rope.cu",462  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/rope.cu.o"463},464{465  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",466  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/scale.cu -o CMakeFiles/ggml-cuda.dir/scale.cu.o",467  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/scale.cu",468  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/scale.cu.o"469},470{471  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",472  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/set-rows.cu -o CMakeFiles/ggml-cuda.dir/set-rows.cu.o",473  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/set-rows.cu",474  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/set-rows.cu.o"475},476{477  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",478  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/set.cu -o CMakeFiles/ggml-cuda.dir/set.cu.o",479  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/set.cu",480  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/set.cu.o"481},482{483  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",484  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/snake.cu -o CMakeFiles/ggml-cuda.dir/snake.cu.o",485  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/snake.cu",486  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/snake.cu.o"487},488{489  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",490  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/softcap.cu -o CMakeFiles/ggml-cuda.dir/softcap.cu.o",491  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/softcap.cu",492  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softcap.cu.o"493},494{495  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",496  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/softmax.cu -o CMakeFiles/ggml-cuda.dir/softmax.cu.o",497  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/softmax.cu",498  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/softmax.cu.o"499},500{501  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",502  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/solve_tri.cu -o CMakeFiles/ggml-cuda.dir/solve_tri.cu.o",503  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/solve_tri.cu",504  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/solve_tri.cu.o"505},506{507  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",508  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/ssm-conv.cu -o CMakeFiles/ggml-cuda.dir/ssm-conv.cu.o",509  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/ssm-conv.cu",510  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-conv.cu.o"511},512{513  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",514  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/ssm-scan.cu -o CMakeFiles/ggml-cuda.dir/ssm-scan.cu.o",515  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/ssm-scan.cu",516  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/ssm-scan.cu.o"517},518{519  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",520  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/sum.cu -o CMakeFiles/ggml-cuda.dir/sum.cu.o",521  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/sum.cu",522  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sum.cu.o"523},524{525  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",526  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/sumrows.cu -o CMakeFiles/ggml-cuda.dir/sumrows.cu.o",527  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/sumrows.cu",528  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/sumrows.cu.o"529},530{531  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",532  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/top-k.cu -o CMakeFiles/ggml-cuda.dir/top-k.cu.o",533  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/top-k.cu",534  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/top-k.cu.o"535},536{537  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",538  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/topk-moe.cu -o CMakeFiles/ggml-cuda.dir/topk-moe.cu.o",539  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/topk-moe.cu",540  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/topk-moe.cu.o"541},542{543  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",544  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/tri.cu -o CMakeFiles/ggml-cuda.dir/tri.cu.o",545  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/tri.cu",546  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/tri.cu.o"547},548{549  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",550  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/tsembd.cu -o CMakeFiles/ggml-cuda.dir/tsembd.cu.o",551  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/tsembd.cu",552  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/tsembd.cu.o"553},554{555  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",556  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/unary.cu -o CMakeFiles/ggml-cuda.dir/unary.cu.o",557  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/unary.cu",558  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/unary.cu.o"559},560{561  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",562  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/upscale.cu -o CMakeFiles/ggml-cuda.dir/upscale.cu.o",563  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/upscale.cu",564  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/upscale.cu.o"565},566{567  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",568  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/wkv.cu -o CMakeFiles/ggml-cuda.dir/wkv.cu.o",569  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/wkv.cu",570  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/wkv.cu.o"571},572{573  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",574  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq112-dv112.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq112-dv112.cu.o",575  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq112-dv112.cu",576  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq112-dv112.cu.o"577},578{579  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",580  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq128-dv128.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq128-dv128.cu.o",581  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq128-dv128.cu",582  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq128-dv128.cu.o"583},584{585  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",586  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq192-dv128.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq192-dv128.cu.o",587  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq192-dv128.cu",588  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq192-dv128.cu.o"589},590{591  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",592  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq256-dv256.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq256-dv256.cu.o",593  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq256-dv256.cu",594  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq256-dv256.cu.o"595},596{597  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",598  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq320-dv256.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq320-dv256.cu.o",599  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq320-dv256.cu",600  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq320-dv256.cu.o"601},602{603  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",604  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq40-dv40.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq40-dv40.cu.o",605  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq40-dv40.cu",606  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq40-dv40.cu.o"607},608{609  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",610  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq512-dv512.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq512-dv512.cu.o",611  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq512-dv512.cu",612  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq512-dv512.cu.o"613},614{615  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",616  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq576-dv512.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq576-dv512.cu.o",617  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq576-dv512.cu",618  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq576-dv512.cu.o"619},620{621  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",622  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq64-dv64.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq64-dv64.cu.o",623  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq64-dv64.cu",624  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq64-dv64.cu.o"625},626{627  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",628  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq72-dv72.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq72-dv72.cu.o",629  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq72-dv72.cu",630  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq72-dv72.cu.o"631},632{633  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",634  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq80-dv80.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq80-dv80.cu.o",635  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq80-dv80.cu",636  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq80-dv80.cu.o"637},638{639  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",640  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq96-dv96.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq96-dv96.cu.o",641  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq96-dv96.cu",642  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-tile-instance-dkq96-dv96.cu.o"643},644{645  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",646  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu.o",647  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu",648  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_16.cu.o"649},650{651  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",652  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_32.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_32.cu.o",653  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_32.cu",654  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_32.cu.o"655},656{657  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",658  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu.o",659  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu",660  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_1-ncols2_8.cu.o"661},662{663  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",664  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu.o",665  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu",666  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_1.cu.o"667},668{669  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",670  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu.o",671  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu",672  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_2.cu.o"673},674{675  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",676  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu.o",677  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu",678  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_16-ncols2_4.cu.o"679},680{681  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",682  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu.o",683  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu",684  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_16.cu.o"685},686{687  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",688  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_32.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_32.cu.o",689  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_32.cu",690  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_32.cu.o"691},692{693  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",694  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu.o",695  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu",696  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_4.cu.o"697},698{699  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",700  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu.o",701  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu",702  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_2-ncols2_8.cu.o"703},704{705  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",706  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu.o",707  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu",708  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_1.cu.o"709},710{711  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",712  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu.o",713  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu",714  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_32-ncols2_2.cu.o"715},716{717  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",718  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu.o",719  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu",720  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_16.cu.o"721},722{723  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",724  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu.o",725  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu",726  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_2.cu.o"727},728{729  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",730  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu.o",731  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu",732  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_4.cu.o"733},734{735  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",736  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu.o",737  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu",738  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_4-ncols2_8.cu.o"739},740{741  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",742  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu.o",743  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu",744  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_64-ncols2_1.cu.o"745},746{747  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",748  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu.o",749  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu",750  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_1.cu.o"751},752{753  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",754  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu.o",755  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu",756  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_2.cu.o"757},758{759  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",760  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu.o",761  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu",762  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_4.cu.o"763},764{765  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",766  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_8.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_8.cu.o",767  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_8.cu",768  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-mma-f16-instance-ncols1_8-ncols2_8.cu.o"769},770{771  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",772  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq1_s.cu.o",773  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu",774  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq1_s.cu.o"775},776{777  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",778  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_s.cu.o",779  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu",780  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_s.cu.o"781},782{783  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",784  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xs.cu.o",785  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu",786  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xs.cu.o"787},788{789  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",790  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xxs.cu.o",791  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu",792  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq2_xxs.cu.o"793},794{795  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",796  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_s.cu.o",797  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu",798  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_s.cu.o"799},800{801  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",802  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_xxs.cu.o",803  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu",804  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq3_xxs.cu.o"805},806{807  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",808  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_nl.cu.o",809  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu",810  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_nl.cu.o"811},812{813  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",814  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_xs.cu.o",815  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu",816  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-iq4_xs.cu.o"817},818{819  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",820  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-mxfp4.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-mxfp4.cu.o",821  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-mxfp4.cu",822  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-mxfp4.cu.o"823},824{825  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",826  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-nvfp4.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-nvfp4.cu.o",827  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-nvfp4.cu",828  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-nvfp4.cu.o"829},830{831  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",832  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q1_0.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q1_0.cu.o",833  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q1_0.cu",834  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q1_0.cu.o"835},836{837  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",838  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_0.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q2_0.cu.o",839  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_0.cu",840  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q2_0.cu.o"841},842{843  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",844  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q2_k.cu.o",845  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu",846  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q2_k.cu.o"847},848{849  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",850  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q3_k.cu.o",851  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu",852  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q3_k.cu.o"853},854{855  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",856  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_0.cu.o",857  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu",858  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_0.cu.o"859},860{861  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",862  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_1.cu.o",863  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu",864  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_1.cu.o"865},866{867  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",868  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_k.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_k.cu.o",869  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_k.cu",870  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q4_k.cu.o"871},872{873  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",874  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_0.cu.o",875  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu",876  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_0.cu.o"877},878{879  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",880  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_1.cu.o",881  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu",882  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_1.cu.o"883},884{885  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",886  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_k.cu.o",887  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu",888  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q5_k.cu.o"889},890{891  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",892  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q6_k.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q6_k.cu.o",893  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q6_k.cu",894  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q6_k.cu.o"895},896{897  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",898  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q8_0.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q8_0.cu.o",899  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q8_0.cu",900  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmq-instance-q8_0.cu.o"901},902{903  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",904  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_1.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_1.cu.o",905  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_1.cu",906  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_1.cu.o"907},908{909  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",910  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_10.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_10.cu.o",911  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_10.cu",912  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_10.cu.o"913},914{915  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",916  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_11.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_11.cu.o",917  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_11.cu",918  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_11.cu.o"919},920{921  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",922  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_12.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_12.cu.o",923  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_12.cu",924  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_12.cu.o"925},926{927  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",928  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_13.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_13.cu.o",929  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_13.cu",930  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_13.cu.o"931},932{933  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",934  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_14.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_14.cu.o",935  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_14.cu",936  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_14.cu.o"937},938{939  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",940  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_15.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_15.cu.o",941  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_15.cu",942  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_15.cu.o"943},944{945  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",946  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_16.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_16.cu.o",947  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_16.cu",948  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_16.cu.o"949},950{951  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",952  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_2.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_2.cu.o",953  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_2.cu",954  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_2.cu.o"955},956{957  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",958  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_3.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_3.cu.o",959  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_3.cu",960  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_3.cu.o"961},962{963  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",964  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_4.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_4.cu.o",965  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_4.cu",966  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_4.cu.o"967},968{969  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",970  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_5.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_5.cu.o",971  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_5.cu",972  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_5.cu.o"973},974{975  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",976  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_6.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_6.cu.o",977  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_6.cu",978  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_6.cu.o"979},980{981  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",982  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_7.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_7.cu.o",983  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_7.cu",984  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_7.cu.o"985},986{987  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",988  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_8.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_8.cu.o",989  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_8.cu",990  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_8.cu.o"991},992{993  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",994  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_9.cu -o CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_9.cu.o",995  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_9.cu",996  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/mmf-instance-ncols_9.cu.o"997},998{999  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",1000  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-f16-f16.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-f16-f16.cu.o",1001  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-f16-f16.cu",1002  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-f16-f16.cu.o"1003},1004{1005  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",1006  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q4_0-q4_0.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-q4_0-q4_0.cu.o",1007  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q4_0-q4_0.cu",1008  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-q4_0-q4_0.cu.o"1009},1010{1011  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",1012  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-q8_0.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-q8_0-q8_0.cu.o",1013  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-q8_0-q8_0.cu",1014  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-q8_0-q8_0.cu.o"1015},1016{1017  "directory": "/kaggle/working/llama.cpp/build/ggml/src/ggml-cuda",1018  "command": "/usr/local/cuda/bin/nvcc -forward-unknown-to-host-compiler -DGGML_BACKEND_BUILD -DGGML_BACKEND_SHARED -DGGML_CUDA_FA_BF16_BF16=1 -DGGML_CUDA_FA_BF16_F16=0 -DGGML_CUDA_FA_BF16_Q4_0=0 -DGGML_CUDA_FA_BF16_Q4_1=0 -DGGML_CUDA_FA_BF16_Q5_0=0 -DGGML_CUDA_FA_BF16_Q5_1=0 -DGGML_CUDA_FA_BF16_Q8_0=0 -DGGML_CUDA_FA_F16_BF16=0 -DGGML_CUDA_FA_F16_F16=1 -DGGML_CUDA_FA_F16_Q4_0=0 -DGGML_CUDA_FA_F16_Q4_1=0 -DGGML_CUDA_FA_F16_Q5_0=0 -DGGML_CUDA_FA_F16_Q5_1=0 -DGGML_CUDA_FA_F16_Q8_0=0 -DGGML_CUDA_FA_Q4_0_BF16=0 -DGGML_CUDA_FA_Q4_0_F16=0 -DGGML_CUDA_FA_Q4_0_Q4_0=1 -DGGML_CUDA_FA_Q4_0_Q4_1=0 -DGGML_CUDA_FA_Q4_0_Q5_0=0 -DGGML_CUDA_FA_Q4_0_Q5_1=0 -DGGML_CUDA_FA_Q4_0_Q8_0=0 -DGGML_CUDA_FA_Q4_1_BF16=0 -DGGML_CUDA_FA_Q4_1_F16=0 -DGGML_CUDA_FA_Q4_1_Q4_0=0 -DGGML_CUDA_FA_Q4_1_Q4_1=0 -DGGML_CUDA_FA_Q4_1_Q5_0=0 -DGGML_CUDA_FA_Q4_1_Q5_1=0 -DGGML_CUDA_FA_Q4_1_Q8_0=0 -DGGML_CUDA_FA_Q5_0_BF16=0 -DGGML_CUDA_FA_Q5_0_F16=0 -DGGML_CUDA_FA_Q5_0_Q4_0=0 -DGGML_CUDA_FA_Q5_0_Q4_1=0 -DGGML_CUDA_FA_Q5_0_Q5_0=0 -DGGML_CUDA_FA_Q5_0_Q5_1=0 -DGGML_CUDA_FA_Q5_0_Q8_0=0 -DGGML_CUDA_FA_Q5_1_BF16=0 -DGGML_CUDA_FA_Q5_1_F16=0 -DGGML_CUDA_FA_Q5_1_Q4_0=0 -DGGML_CUDA_FA_Q5_1_Q4_1=0 -DGGML_CUDA_FA_Q5_1_Q5_0=0 -DGGML_CUDA_FA_Q5_1_Q5_1=0 -DGGML_CUDA_FA_Q5_1_Q8_0=0 -DGGML_CUDA_FA_Q8_0_BF16=0 -DGGML_CUDA_FA_Q8_0_F16=0 -DGGML_CUDA_FA_Q8_0_Q4_0=0 -DGGML_CUDA_FA_Q8_0_Q4_1=0 -DGGML_CUDA_FA_Q8_0_Q5_0=0 -DGGML_CUDA_FA_Q8_0_Q5_1=0 -DGGML_CUDA_FA_Q8_0_Q8_0=1 -DGGML_CUDA_FA_QUANTS=\\\"q4_0-q4_0,q8_0-q8_0,f16-f16,bf16-bf16\\\" -DGGML_CUDA_USE_GRAPHS -DGGML_SCHED_MAX_COPIES=4 -DGGML_SHARED -D_GNU_SOURCE -D_XOPEN_SOURCE=600 -Dggml_cuda_EXPORTS --options-file CMakeFiles/ggml-cuda.dir/includes_CUDA.rsp -O3 -DNDEBUG -std=c++17 \"--generate-code=arch=compute_75,code=[compute_75,sm_75]\" -Xcompiler=-fPIC -use_fast_math -extended-lambda -compress-mode=size -Xcompiler \"-Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -Wno-pedantic\" -x cu -c /kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-bf16-bf16.cu -o CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-bf16-bf16.cu.o",1019  "file": "/kaggle/working/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-instance-bf16-bf16.cu",1020  "output": "ggml/src/ggml-cuda/CMakeFiles/ggml-cuda.dir/template-instances/fattn-vec-instance-bf16-bf16.cu.o"1021},1022{1023  "directory": "/kaggle/working/llama.cpp/build/src",1024  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_9_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_9_cxx.cxx",1025  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_9_cxx.cxx",1026  "output": "src/CMakeFiles/llama.dir/Unity/unity_9_cxx.cxx.o"1027},1028{1029  "directory": "/kaggle/working/llama.cpp/build/src",1030  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_8_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_8_cxx.cxx",1031  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_8_cxx.cxx",1032  "output": "src/CMakeFiles/llama.dir/Unity/unity_8_cxx.cxx.o"1033},1034{1035  "directory": "/kaggle/working/llama.cpp/build/src",1036  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_7_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_7_cxx.cxx",1037  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_7_cxx.cxx",1038  "output": "src/CMakeFiles/llama.dir/Unity/unity_7_cxx.cxx.o"1039},1040{1041  "directory": "/kaggle/working/llama.cpp/build/src",1042  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_6_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_6_cxx.cxx",1043  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_6_cxx.cxx",1044  "output": "src/CMakeFiles/llama.dir/Unity/unity_6_cxx.cxx.o"1045},1046{1047  "directory": "/kaggle/working/llama.cpp/build/src",1048  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_5_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_5_cxx.cxx",1049  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_5_cxx.cxx",1050  "output": "src/CMakeFiles/llama.dir/Unity/unity_5_cxx.cxx.o"1051},1052{1053  "directory": "/kaggle/working/llama.cpp/build/src",1054  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_4_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_4_cxx.cxx",1055  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_4_cxx.cxx",1056  "output": "src/CMakeFiles/llama.dir/Unity/unity_4_cxx.cxx.o"1057},1058{1059  "directory": "/kaggle/working/llama.cpp/build/src",1060  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_3_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_3_cxx.cxx",1061  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_3_cxx.cxx",1062  "output": "src/CMakeFiles/llama.dir/Unity/unity_3_cxx.cxx.o"1063},1064{1065  "directory": "/kaggle/working/llama.cpp/build/src",1066  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_2_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_2_cxx.cxx",1067  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_2_cxx.cxx",1068  "output": "src/CMakeFiles/llama.dir/Unity/unity_2_cxx.cxx.o"1069},1070{1071  "directory": "/kaggle/working/llama.cpp/build/src",1072  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_1_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_1_cxx.cxx",1073  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_1_cxx.cxx",1074  "output": "src/CMakeFiles/llama.dir/Unity/unity_1_cxx.cxx.o"1075},1076{1077  "directory": "/kaggle/working/llama.cpp/build/src",1078  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/Unity/unity_0_cxx.cxx.o -c /kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_0_cxx.cxx",1079  "file": "/kaggle/working/llama.cpp/build/src/CMakeFiles/llama.dir/Unity/unity_0_cxx.cxx",1080  "output": "src/CMakeFiles/llama.dir/Unity/unity_0_cxx.cxx.o"1081},1082{1083  "directory": "/kaggle/working/llama.cpp/build/src",1084  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama.cpp.o -c /kaggle/working/llama.cpp/src/llama.cpp",1085  "file": "/kaggle/working/llama.cpp/src/llama.cpp",1086  "output": "src/CMakeFiles/llama.dir/llama.cpp.o"1087},1088{1089  "directory": "/kaggle/working/llama.cpp/build/src",1090  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-adapter.cpp.o -c /kaggle/working/llama.cpp/src/llama-adapter.cpp",1091  "file": "/kaggle/working/llama.cpp/src/llama-adapter.cpp",1092  "output": "src/CMakeFiles/llama.dir/llama-adapter.cpp.o"1093},1094{1095  "directory": "/kaggle/working/llama.cpp/build/src",1096  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-arch.cpp.o -c /kaggle/working/llama.cpp/src/llama-arch.cpp",1097  "file": "/kaggle/working/llama.cpp/src/llama-arch.cpp",1098  "output": "src/CMakeFiles/llama.dir/llama-arch.cpp.o"1099},1100{1101  "directory": "/kaggle/working/llama.cpp/build/src",1102  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-batch.cpp.o -c /kaggle/working/llama.cpp/src/llama-batch.cpp",1103  "file": "/kaggle/working/llama.cpp/src/llama-batch.cpp",1104  "output": "src/CMakeFiles/llama.dir/llama-batch.cpp.o"1105},1106{1107  "directory": "/kaggle/working/llama.cpp/build/src",1108  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-chat.cpp.o -c /kaggle/working/llama.cpp/src/llama-chat.cpp",1109  "file": "/kaggle/working/llama.cpp/src/llama-chat.cpp",1110  "output": "src/CMakeFiles/llama.dir/llama-chat.cpp.o"1111},1112{1113  "directory": "/kaggle/working/llama.cpp/build/src",1114  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-context.cpp.o -c /kaggle/working/llama.cpp/src/llama-context.cpp",1115  "file": "/kaggle/working/llama.cpp/src/llama-context.cpp",1116  "output": "src/CMakeFiles/llama.dir/llama-context.cpp.o"1117},1118{1119  "directory": "/kaggle/working/llama.cpp/build/src",1120  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-cparams.cpp.o -c /kaggle/working/llama.cpp/src/llama-cparams.cpp",1121  "file": "/kaggle/working/llama.cpp/src/llama-cparams.cpp",1122  "output": "src/CMakeFiles/llama.dir/llama-cparams.cpp.o"1123},1124{1125  "directory": "/kaggle/working/llama.cpp/build/src",1126  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-grammar.cpp.o -c /kaggle/working/llama.cpp/src/llama-grammar.cpp",1127  "file": "/kaggle/working/llama.cpp/src/llama-grammar.cpp",1128  "output": "src/CMakeFiles/llama.dir/llama-grammar.cpp.o"1129},1130{1131  "directory": "/kaggle/working/llama.cpp/build/src",1132  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-graph.cpp.o -c /kaggle/working/llama.cpp/src/llama-graph.cpp",1133  "file": "/kaggle/working/llama.cpp/src/llama-graph.cpp",1134  "output": "src/CMakeFiles/llama.dir/llama-graph.cpp.o"1135},1136{1137  "directory": "/kaggle/working/llama.cpp/build/src",1138  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-hparams.cpp.o -c /kaggle/working/llama.cpp/src/llama-hparams.cpp",1139  "file": "/kaggle/working/llama.cpp/src/llama-hparams.cpp",1140  "output": "src/CMakeFiles/llama.dir/llama-hparams.cpp.o"1141},1142{1143  "directory": "/kaggle/working/llama.cpp/build/src",1144  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-impl.cpp.o -c /kaggle/working/llama.cpp/src/llama-impl.cpp",1145  "file": "/kaggle/working/llama.cpp/src/llama-impl.cpp",1146  "output": "src/CMakeFiles/llama.dir/llama-impl.cpp.o"1147},1148{1149  "directory": "/kaggle/working/llama.cpp/build/src",1150  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-io.cpp.o -c /kaggle/working/llama.cpp/src/llama-io.cpp",1151  "file": "/kaggle/working/llama.cpp/src/llama-io.cpp",1152  "output": "src/CMakeFiles/llama.dir/llama-io.cpp.o"1153},1154{1155  "directory": "/kaggle/working/llama.cpp/build/src",1156  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-kv-cache.cpp.o -c /kaggle/working/llama.cpp/src/llama-kv-cache.cpp",1157  "file": "/kaggle/working/llama.cpp/src/llama-kv-cache.cpp",1158  "output": "src/CMakeFiles/llama.dir/llama-kv-cache.cpp.o"1159},1160{1161  "directory": "/kaggle/working/llama.cpp/build/src",1162  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-kv-cache-iswa.cpp.o -c /kaggle/working/llama.cpp/src/llama-kv-cache-iswa.cpp",1163  "file": "/kaggle/working/llama.cpp/src/llama-kv-cache-iswa.cpp",1164  "output": "src/CMakeFiles/llama.dir/llama-kv-cache-iswa.cpp.o"1165},1166{1167  "directory": "/kaggle/working/llama.cpp/build/src",1168  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-kv-cache-dsa.cpp.o -c /kaggle/working/llama.cpp/src/llama-kv-cache-dsa.cpp",1169  "file": "/kaggle/working/llama.cpp/src/llama-kv-cache-dsa.cpp",1170  "output": "src/CMakeFiles/llama.dir/llama-kv-cache-dsa.cpp.o"1171},1172{1173  "directory": "/kaggle/working/llama.cpp/build/src",1174  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-kv-cache-dsa-iswa.cpp.o -c /kaggle/working/llama.cpp/src/llama-kv-cache-dsa-iswa.cpp",1175  "file": "/kaggle/working/llama.cpp/src/llama-kv-cache-dsa-iswa.cpp",1176  "output": "src/CMakeFiles/llama.dir/llama-kv-cache-dsa-iswa.cpp.o"1177},1178{1179  "directory": "/kaggle/working/llama.cpp/build/src",1180  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-kv-cache-msa.cpp.o -c /kaggle/working/llama.cpp/src/llama-kv-cache-msa.cpp",1181  "file": "/kaggle/working/llama.cpp/src/llama-kv-cache-msa.cpp",1182  "output": "src/CMakeFiles/llama.dir/llama-kv-cache-msa.cpp.o"1183},1184{1185  "directory": "/kaggle/working/llama.cpp/build/src",1186  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-kv-cache-dsv4.cpp.o -c /kaggle/working/llama.cpp/src/llama-kv-cache-dsv4.cpp",1187  "file": "/kaggle/working/llama.cpp/src/llama-kv-cache-dsv4.cpp",1188  "output": "src/CMakeFiles/llama.dir/llama-kv-cache-dsv4.cpp.o"1189},1190{1191  "directory": "/kaggle/working/llama.cpp/build/src",1192  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-memory.cpp.o -c /kaggle/working/llama.cpp/src/llama-memory.cpp",1193  "file": "/kaggle/working/llama.cpp/src/llama-memory.cpp",1194  "output": "src/CMakeFiles/llama.dir/llama-memory.cpp.o"1195},1196{1197  "directory": "/kaggle/working/llama.cpp/build/src",1198  "command": "/usr/bin/c++ -DGGML_BACKEND_SHARED -DGGML_SHARED -DGGML_USE_CPU -DGGML_USE_CUDA -DLLAMA_BUILD -DLLAMA_SHARED -Dllama_EXPORTS -I/kaggle/working/llama.cpp/src/. -I/kaggle/working/llama.cpp/build/src -I/kaggle/working/llama.cpp/src/../include -I/kaggle/working/llama.cpp/ggml/src/../include -O3 -DNDEBUG -fPIC -Wmissing-declarations -Wmissing-noreturn -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-array-bounds -Wextra-semi -o CMakeFiles/llama.dir/llama-memory-hybrid.cpp.o -c /kaggle/working/llama.cpp/src/llama-memory-hybrid.cpp",1199  "file": "/kaggle/working/llama.cpp/src/llama-memory-hybrid.cpp",1200  "output": "src/CMakeFiles/llama.dir/llama-memory-hybrid.cpp.o"
Showing the first 1,200 of 2684 lines. Download the file for the rest.