Merge branch 'master' into pr-train-mem-usage-improvements
This commit is contained in:
xaedes
commit
d43af4b543
38 changed files with 5339 additions and 2377 deletions
|
|
@ -67,11 +67,13 @@ endif()
|
|||
option(LLAMA_ACCELERATE "llama: enable Accelerate framework" ON)
|
||||
option(LLAMA_BLAS "llama: use BLAS" OFF)
|
||||
set(LLAMA_BLAS_VENDOR "Generic" CACHE STRING "llama: BLAS library vendor")
|
||||
option(LLAMA_CUBLAS "llama: use cuBLAS" OFF)
|
||||
option(LLAMA_CUBLAS "llama: use CUDA" OFF)
|
||||
#option(LLAMA_CUDA_CUBLAS "llama: use cuBLAS for prompt processing" OFF)
|
||||
set(LLAMA_CUDA_MMQ_Y "64" CACHE STRING "llama: y tile size for mmq CUDA kernels")
|
||||
option(LLAMA_CUDA_FORCE_DMMV "llama: use dmmv instead of mmvq CUDA kernels" OFF)
|
||||
set(LLAMA_CUDA_DMMV_X "32" CACHE STRING "llama: x stride for dmmv CUDA kernels")
|
||||
set(LLAMA_CUDA_MMV_Y "1" CACHE STRING "llama: y block size for mmv CUDA kernels")
|
||||
option(LLAMA_CUDA_DMMV_F16 "llama: use 16 bit floats for dmmv CUDA kernels" OFF)
|
||||
option(LLAMA_CUDA_F16 "llama: use 16 bit floats for some calculations" OFF)
|
||||
set(LLAMA_CUDA_KQUANTS_ITER "2" CACHE STRING "llama: iters./thread per block for Q2_K/Q6_K")
|
||||
option(LLAMA_CLBLAST "llama: use CLBlast" OFF)
|
||||
option(LLAMA_METAL "llama: use Metal" OFF)
|
||||
|
|
@ -251,6 +253,10 @@ if (LLAMA_CUBLAS)
|
|||
set(GGML_SOURCES_CUDA ggml-cuda.cu ggml-cuda.h)
|
||||
|
||||
add_compile_definitions(GGML_USE_CUBLAS)
|
||||
# if (LLAMA_CUDA_CUBLAS)
|
||||
# add_compile_definitions(GGML_CUDA_CUBLAS)
|
||||
# endif()
|
||||
add_compile_definitions(GGML_CUDA_MMQ_Y=${LLAMA_CUDA_MMQ_Y})
|
||||
if (LLAMA_CUDA_FORCE_DMMV)
|
||||
add_compile_definitions(GGML_CUDA_FORCE_DMMV)
|
||||
endif()
|
||||
|
|
@ -259,8 +265,8 @@ if (LLAMA_CUBLAS)
|
|||
if (DEFINED LLAMA_CUDA_DMMV_Y)
|
||||
add_compile_definitions(GGML_CUDA_MMV_Y=${LLAMA_CUDA_DMMV_Y}) # for backwards compatibility
|
||||
endif()
|
||||
if (LLAMA_CUDA_DMMV_F16)
|
||||
add_compile_definitions(GGML_CUDA_DMMV_F16)
|
||||
if (LLAMA_CUDA_F16 OR LLAMA_CUDA_DMMV_F16)
|
||||
add_compile_definitions(GGML_CUDA_F16)
|
||||
endif()
|
||||
add_compile_definitions(K_QUANTS_PER_ITERATION=${LLAMA_CUDA_KQUANTS_ITER})
|
||||
|
||||
|
|
@ -271,10 +277,14 @@ if (LLAMA_CUBLAS)
|
|||
endif()
|
||||
|
||||
if (NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
|
||||
if (LLAMA_CUDA_DMMV_F16)
|
||||
set(CMAKE_CUDA_ARCHITECTURES "60;61") # needed for f16 CUDA intrinsics
|
||||
# 52 == lowest CUDA 12 standard
|
||||
# 60 == f16 CUDA intrinsics
|
||||
# 61 == integer CUDA intrinsics
|
||||
# 70 == compute capability at which unrolling a loop in mul_mat_q kernels is faster
|
||||
if (LLAMA_CUDA_F16 OR LLAMA_CUDA_DMMV_F16)
|
||||
set(CMAKE_CUDA_ARCHITECTURES "60;61;70") # needed for f16 CUDA intrinsics
|
||||
else()
|
||||
set(CMAKE_CUDA_ARCHITECTURES "52;61") # lowest CUDA 12 standard + lowest for integer intrinsics
|
||||
set(CMAKE_CUDA_ARCHITECTURES "52;61;70") # lowest CUDA 12 standard + lowest for integer intrinsics
|
||||
endif()
|
||||
endif()
|
||||
message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")
|
||||
|
|
@ -497,6 +507,8 @@ endif()
|
|||
add_library(ggml OBJECT
|
||||
ggml.c
|
||||
ggml.h
|
||||
ggml-alloc.c
|
||||
ggml-alloc.h
|
||||
${GGML_SOURCES_CUDA}
|
||||
${GGML_SOURCES_OPENCL}
|
||||
${GGML_SOURCES_METAL}
|
||||
|
|
|
|||
35
Makefile
35
Makefile
|
|
@ -194,7 +194,7 @@ ifdef LLAMA_CUBLAS
|
|||
CXXFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include
|
||||
LDFLAGS += -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/x86_64-linux/lib
|
||||
OBJS += ggml-cuda.o
|
||||
NVCCFLAGS = --forward-unknown-to-host-compiler
|
||||
NVCCFLAGS = --forward-unknown-to-host-compiler -use_fast_math
|
||||
ifdef LLAMA_CUDA_NVCC
|
||||
NVCC = $(LLAMA_CUDA_NVCC)
|
||||
else
|
||||
|
|
@ -220,19 +220,30 @@ else ifdef LLAMA_CUDA_DMMV_Y
|
|||
else
|
||||
NVCCFLAGS += -DGGML_CUDA_MMV_Y=1
|
||||
endif # LLAMA_CUDA_MMV_Y
|
||||
ifdef LLAMA_CUDA_F16
|
||||
NVCCFLAGS += -DGGML_CUDA_F16
|
||||
endif # LLAMA_CUDA_F16
|
||||
ifdef LLAMA_CUDA_DMMV_F16
|
||||
NVCCFLAGS += -DGGML_CUDA_DMMV_F16
|
||||
NVCCFLAGS += -DGGML_CUDA_F16
|
||||
endif # LLAMA_CUDA_DMMV_F16
|
||||
ifdef LLAMA_CUDA_KQUANTS_ITER
|
||||
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=$(LLAMA_CUDA_KQUANTS_ITER)
|
||||
else
|
||||
NVCCFLAGS += -DK_QUANTS_PER_ITERATION=2
|
||||
endif
|
||||
ifdef LLAMA_CUDA_MMQ_Y
|
||||
NVCCFLAGS += -DGGML_CUDA_MMQ_Y=$(LLAMA_CUDA_MMQ_Y)
|
||||
else
|
||||
NVCCFLAGS += -DGGML_CUDA_MMQ_Y=64
|
||||
endif # LLAMA_CUDA_MMQ_Y
|
||||
#ifdef LLAMA_CUDA_CUBLAS
|
||||
# NVCCFLAGS += -DGGML_CUDA_CUBLAS
|
||||
#endif # LLAMA_CUDA_CUBLAS
|
||||
ifdef LLAMA_CUDA_CCBIN
|
||||
NVCCFLAGS += -ccbin $(LLAMA_CUDA_CCBIN)
|
||||
endif
|
||||
ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
|
||||
$(NVCC) $(NVCCFLAGS) $(CXXFLAGS) -Wno-pedantic -c $< -o $@
|
||||
$(NVCC) $(NVCCFLAGS) $(subst -Ofast,-O3,$(CXXFLAGS)) -Wno-pedantic -c $< -o $@
|
||||
endif # LLAMA_CUBLAS
|
||||
|
||||
ifdef LLAMA_CLBLAST
|
||||
|
|
@ -318,12 +329,20 @@ $(info )
|
|||
ggml.o: ggml.c ggml.h ggml-cuda.h
|
||||
$(CC) $(CFLAGS) -c $< -o $@
|
||||
|
||||
llama.o: llama.cpp ggml.h ggml-cuda.h ggml-metal.h llama.h llama-util.h
|
||||
ggml-alloc.o: ggml-alloc.c ggml.h ggml-alloc.h
|
||||
$(CC) $(CFLAGS) -c $< -o $@
|
||||
|
||||
OBJS += ggml-alloc.o
|
||||
|
||||
llama.o: llama.cpp ggml.h ggml-alloc.h ggml-cuda.h ggml-metal.h llama.h llama-util.h
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
common.o: examples/common.cpp examples/common.h
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
console.o: examples/console.cpp examples/console.h
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
grammar-parser.o: examples/grammar-parser.cpp examples/grammar-parser.h
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
|
|
@ -337,7 +356,7 @@ clean:
|
|||
# Examples
|
||||
#
|
||||
|
||||
main: examples/main/main.cpp build-info.h ggml.o llama.o common.o grammar-parser.o $(OBJS)
|
||||
main: examples/main/main.cpp build-info.h ggml.o llama.o common.o console.o grammar-parser.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.h,$^) -o $@ $(LDFLAGS)
|
||||
@echo
|
||||
@echo '==== Run ./main -h for help. ===='
|
||||
|
|
@ -395,13 +414,13 @@ benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o
|
|||
vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-double-float: tests/test-double-float.c build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
tests/test-double-float: tests/test-double-float.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-grad0: tests/test-grad0.c build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
tests/test-grad0: tests/test-grad0.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-opt: tests/test-opt.c build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
tests/test-opt: tests/test-opt.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
$(CXX) $(CXXFLAGS) $(filter-out %.txt,$^) -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test-quantize-fns: tests/test-quantize-fns.cpp build-info.h ggml.o llama.o common.o $(OBJS)
|
||||
|
|
|
|||
15
README.md
15
README.md
|
|
@ -80,7 +80,7 @@ as the main playground for developing new features for the [ggml](https://github
|
|||
- [x] LLaMA 2 🦙🦙
|
||||
- [X] [Alpaca](https://github.com/ggerganov/llama.cpp#instruction-mode-with-alpaca)
|
||||
- [X] [GPT4All](https://github.com/ggerganov/llama.cpp#using-gpt4all)
|
||||
- [X] [Chinese LLaMA / Alpaca](https://github.com/ymcui/Chinese-LLaMA-Alpaca)
|
||||
- [X] [Chinese LLaMA / Alpaca](https://github.com/ymcui/Chinese-LLaMA-Alpaca) and [Chinese LLaMA-2 / Alpaca-2](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2)
|
||||
- [X] [Vigogne (French)](https://github.com/bofenghuang/vigogne)
|
||||
- [X] [Vicuna](https://github.com/ggerganov/llama.cpp/discussions/643#discussioncomment-5533894)
|
||||
- [X] [Koala](https://bair.berkeley.edu/blog/2023/04/03/koala/)
|
||||
|
|
@ -88,6 +88,7 @@ as the main playground for developing new features for the [ggml](https://github
|
|||
- [X] [Pygmalion 7B / Metharme 7B](#using-pygmalion-7b--metharme-7b)
|
||||
- [X] [WizardLM](https://github.com/nlpxucan/WizardLM)
|
||||
- [X] [Baichuan-7B](https://huggingface.co/baichuan-inc/baichuan-7B) and its derivations (such as [baichuan-7b-sft](https://huggingface.co/hiyouga/baichuan-7b-sft))
|
||||
- [X] [Aquila-7B](https://huggingface.co/BAAI/Aquila-7B) / [AquilaChat-7B](https://huggingface.co/BAAI/AquilaChat-7B)
|
||||
|
||||
**Bindings:**
|
||||
|
||||
|
|
@ -400,12 +401,16 @@ Building the program with BLAS support may lead to some performance improvements
|
|||
|
||||
The environment variable [`CUDA_VISIBLE_DEVICES`](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars) can be used to specify which GPU(s) will be used. The following compilation options are also available to tweak performance:
|
||||
|
||||
<!---
|
||||
| LLAMA_CUDA_CUBLAS | Boolean | false | Use cuBLAS instead of custom CUDA kernels for prompt processing. Faster for all quantization formats except for q4_0 and q8_0, especially for k-quants. Increases VRAM usage (700 MiB for 7b, 970 MiB for 13b, 1430 MiB for 33b). |
|
||||
--->
|
||||
| Option | Legal values | Default | Description |
|
||||
|-------------------------|------------------------|---------|-------------|
|
||||
| LLAMA_CUDA_MMQ_Y | Positive integer >= 32 | 64 | Tile size in y direction when using the custom CUDA kernels for prompt processing. Higher values can be faster depending on the amount of shared memory available. Power of 2 heavily recommended. |
|
||||
| LLAMA_CUDA_FORCE_DMMV | Boolean | false | Force the use of dequantization + matrix vector multiplication kernels instead of using kernels that do matrix vector multiplication on quantized data. By default the decision is made based on compute capability (MMVQ for 6.1/Pascal/GTX 1000 or higher). Does not affect k-quants. |
|
||||
| LLAMA_CUDA_DMMV_X | Positive integer >= 32 | 32 | Number of values in x direction processed by the CUDA dequantization + matrix vector multiplication kernel per iteration. Increasing this value can improve performance on fast GPUs. Power of 2 heavily recommended. Does not affect k-quants. |
|
||||
| LLAMA_CUDA_MMV_Y | Positive integer | 1 | Block size in y direction for the CUDA mul mat vec kernels. Increasing this value can improve performance on fast GPUs. Power of 2 recommended. Does not affect k-quants. |
|
||||
| LLAMA_CUDA_DMMV_F16 | Boolean | false | If enabled, use half-precision floating point arithmetic for the CUDA dequantization + mul mat vec kernels. Can improve performance on relatively recent GPUs. |
|
||||
| LLAMA_CUDA_F16 | Boolean | false | If enabled, use half-precision floating point arithmetic for the CUDA dequantization + mul mat vec kernels and for the q4_1 and q5_1 matrix matrix multiplication kernels. Can improve performance on relatively recent GPUs. |
|
||||
| LLAMA_CUDA_KQUANTS_ITER | 1 or 2 | 2 | Number of values processed per iteration and per CUDA thread for Q2_K and Q6_K quantization formats. Setting this value to 1 can improve performance for slow GPUs. |
|
||||
|
||||
- #### CLBlast
|
||||
|
|
@ -488,6 +493,9 @@ Building the program with BLAS support may lead to some performance improvements
|
|||
# obtain the original LLaMA model weights and place them in ./models
|
||||
ls ./models
|
||||
65B 30B 13B 7B tokenizer_checklist.chk tokenizer.model
|
||||
# [Optional] for models using BPE tokenizers
|
||||
ls ./models
|
||||
65B 30B 13B 7B vocab.json
|
||||
|
||||
# install Python dependencies
|
||||
python3 -m pip install -r requirements.txt
|
||||
|
|
@ -495,6 +503,9 @@ python3 -m pip install -r requirements.txt
|
|||
# convert the 7B model to ggml FP16 format
|
||||
python3 convert.py models/7B/
|
||||
|
||||
# [Optional] for models using BPE tokenizers
|
||||
python convert.py models/7B/ --vocabtype bpe
|
||||
|
||||
# quantize the model to 4-bits (using q4_0 method)
|
||||
./quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin q4_0
|
||||
|
||||
|
|
|
|||
|
|
@ -465,6 +465,13 @@ class GGMLQuantizedTensor(Tensor):
|
|||
def permute(self, n_head: int, n_kv_head: Optional[int] = None) -> 'GGMLQuantizedTensor':
|
||||
return GGMLQuantizedTensor(permute(self.ndarray, n_head, n_kv_head), self.shape, self.data_type)
|
||||
|
||||
def permute_part(self, n_part: int, n_head: int) -> 'UnquantizedTensor':
|
||||
r = self.ndarray.shape[0] // 3
|
||||
return UnquantizedTensor(permute(self.ndarray[r * n_part : r * n_part + r, ...], n_head))
|
||||
|
||||
def part(self, n_part: int) -> 'UnquantizedTensor':
|
||||
r = self.ndarray.shape[0] // 3
|
||||
return UnquantizedTensor(self.ndarray[r * n_part : r * n_part + r, ...])
|
||||
|
||||
GGMLCompatibleTensor = Union[UnquantizedTensor, GGMLQuantizedTensor]
|
||||
|
||||
|
|
|
|||
|
|
@ -13,6 +13,8 @@ set(TARGET common)
|
|||
add_library(${TARGET} OBJECT
|
||||
common.h
|
||||
common.cpp
|
||||
console.h
|
||||
console.cpp
|
||||
grammar-parser.h
|
||||
grammar-parser.cpp
|
||||
)
|
||||
|
|
|
|||
|
|
@ -25,7 +25,6 @@
|
|||
#else
|
||||
#include <sys/ioctl.h>
|
||||
#include <unistd.h>
|
||||
#include <wchar.h>
|
||||
#endif
|
||||
|
||||
#if defined(_MSC_VER)
|
||||
|
|
@ -329,6 +328,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
|
|||
params.instruct = true;
|
||||
} else if (arg == "--multiline-input") {
|
||||
params.multiline_input = true;
|
||||
} else if (arg == "--simple-io") {
|
||||
params.simple_io = true;
|
||||
} else if (arg == "--color") {
|
||||
params.use_color = true;
|
||||
} else if (arg == "--mlock") {
|
||||
|
|
@ -377,6 +378,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
|
|||
}
|
||||
#else
|
||||
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. It is not possible to set a tensor split.\n");
|
||||
#endif // GGML_USE_CUBLAS
|
||||
} else if (arg == "--mul-mat-q" || arg == "-mmq") {
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
params.mul_mat_q = true;
|
||||
#else
|
||||
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. It is not possible to use mul_mat_q kernels.\n");
|
||||
#endif // GGML_USE_CUBLAS
|
||||
} else if (arg == "--low-vram" || arg == "-lv") {
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
|
|
@ -566,7 +573,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
|
|||
fprintf(stdout, " --temp N temperature (default: %.1f)\n", (double)params.temp);
|
||||
fprintf(stdout, " --perplexity compute perplexity over each ctx window of the prompt\n");
|
||||
fprintf(stdout, " --hellaswag compute HellaSwag score over random tasks from datafile supplied with -f\n");
|
||||
fprintf(stdout, " --hellaswag-tasks N number of tasks to use when computing the HellaSwag score (default: %d)\n", params.hellaswag_tasks);
|
||||
fprintf(stdout, " --hellaswag-tasks N number of tasks to use when computing the HellaSwag score (default: %zu)\n", params.hellaswag_tasks);
|
||||
fprintf(stdout, " --keep N number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep);
|
||||
fprintf(stdout, " --chunks N max number of chunks to process (default: %d, -1 = all)\n", params.n_chunks);
|
||||
if (llama_mlock_supported()) {
|
||||
|
|
@ -585,10 +592,14 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
|
|||
fprintf(stdout, " how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
|
||||
fprintf(stdout, " -mg i, --main-gpu i the GPU to use for scratch and small tensors\n" );
|
||||
fprintf(stdout, " -lv, --low-vram don't allocate VRAM scratch buffer\n" );
|
||||
fprintf(stdout, " -mmq, --mul-mat-q use experimental mul_mat_q CUDA kernels instead of cuBLAS. TEMP!!!\n" );
|
||||
fprintf(stdout, " Reduces VRAM usage by 700/970/1430 MiB for 7b/13b/33b but prompt processing speed\n" );
|
||||
fprintf(stdout, " is still suboptimal, especially q2_K, q3_K, q5_K, and q6_K.\n" );
|
||||
#endif
|
||||
fprintf(stdout, " --mtest compute maximum memory usage\n");
|
||||
fprintf(stdout, " --export export the computation graph to 'llama.ggml'\n");
|
||||
fprintf(stdout, " --verbose-prompt print prompt before generation\n");
|
||||
fprintf(stderr, " --simple-io use basic IO for better compatibility in subprocesses and limited consoles\n");
|
||||
fprintf(stdout, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n");
|
||||
fprintf(stdout, " --lora-base FNAME optional model to use as a base for the layers modified by the LoRA adapter\n");
|
||||
fprintf(stdout, " -m FNAME, --model FNAME\n");
|
||||
|
|
@ -637,6 +648,7 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
|
|||
lparams.main_gpu = params.main_gpu;
|
||||
lparams.tensor_split = params.tensor_split;
|
||||
lparams.low_vram = params.low_vram;
|
||||
lparams.mul_mat_q = params.mul_mat_q;
|
||||
lparams.seed = params.seed;
|
||||
lparams.f16_kv = params.memory_f16;
|
||||
lparams.use_mmap = params.use_mmap;
|
||||
|
|
@ -680,376 +692,3 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
|
|||
|
||||
return std::make_tuple(model, lctx);
|
||||
}
|
||||
|
||||
void console_init(console_state & con_st) {
|
||||
#if defined(_WIN32)
|
||||
// Windows-specific console initialization
|
||||
DWORD dwMode = 0;
|
||||
con_st.hConsole = GetStdHandle(STD_OUTPUT_HANDLE);
|
||||
if (con_st.hConsole == INVALID_HANDLE_VALUE || !GetConsoleMode(con_st.hConsole, &dwMode)) {
|
||||
con_st.hConsole = GetStdHandle(STD_ERROR_HANDLE);
|
||||
if (con_st.hConsole != INVALID_HANDLE_VALUE && (!GetConsoleMode(con_st.hConsole, &dwMode))) {
|
||||
con_st.hConsole = NULL;
|
||||
}
|
||||
}
|
||||
if (con_st.hConsole) {
|
||||
// Enable ANSI colors on Windows 10+
|
||||
if (con_st.use_color && !(dwMode & ENABLE_VIRTUAL_TERMINAL_PROCESSING)) {
|
||||
SetConsoleMode(con_st.hConsole, dwMode | ENABLE_VIRTUAL_TERMINAL_PROCESSING);
|
||||
}
|
||||
// Set console output codepage to UTF8
|
||||
SetConsoleOutputCP(CP_UTF8);
|
||||
}
|
||||
HANDLE hConIn = GetStdHandle(STD_INPUT_HANDLE);
|
||||
if (hConIn != INVALID_HANDLE_VALUE && GetConsoleMode(hConIn, &dwMode)) {
|
||||
// Set console input codepage to UTF16
|
||||
_setmode(_fileno(stdin), _O_WTEXT);
|
||||
|
||||
// Turn off ICANON (ENABLE_LINE_INPUT) and ECHO (ENABLE_ECHO_INPUT)
|
||||
dwMode &= ~(ENABLE_LINE_INPUT | ENABLE_ECHO_INPUT);
|
||||
SetConsoleMode(hConIn, dwMode);
|
||||
}
|
||||
#else
|
||||
// POSIX-specific console initialization
|
||||
struct termios new_termios;
|
||||
tcgetattr(STDIN_FILENO, &con_st.prev_state);
|
||||
new_termios = con_st.prev_state;
|
||||
new_termios.c_lflag &= ~(ICANON | ECHO);
|
||||
new_termios.c_cc[VMIN] = 1;
|
||||
new_termios.c_cc[VTIME] = 0;
|
||||
tcsetattr(STDIN_FILENO, TCSANOW, &new_termios);
|
||||
|
||||
con_st.tty = fopen("/dev/tty", "w+");
|
||||
if (con_st.tty != nullptr) {
|
||||
con_st.out = con_st.tty;
|
||||
}
|
||||
|
||||
setlocale(LC_ALL, "");
|
||||
#endif
|
||||
}
|
||||
|
||||
void console_cleanup(console_state & con_st) {
|
||||
// Reset console color
|
||||
console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
|
||||
|
||||
#if !defined(_WIN32)
|
||||
if (con_st.tty != nullptr) {
|
||||
con_st.out = stdout;
|
||||
fclose(con_st.tty);
|
||||
con_st.tty = nullptr;
|
||||
}
|
||||
// Restore the terminal settings on POSIX systems
|
||||
tcsetattr(STDIN_FILENO, TCSANOW, &con_st.prev_state);
|
||||
#endif
|
||||
}
|
||||
|
||||
/* Keep track of current color of output, and emit ANSI code if it changes. */
|
||||
void console_set_color(console_state & con_st, console_color_t color) {
|
||||
if (con_st.use_color && con_st.color != color) {
|
||||
fflush(stdout);
|
||||
switch(color) {
|
||||
case CONSOLE_COLOR_DEFAULT:
|
||||
fprintf(con_st.out, ANSI_COLOR_RESET);
|
||||
break;
|
||||
case CONSOLE_COLOR_PROMPT:
|
||||
fprintf(con_st.out, ANSI_COLOR_YELLOW);
|
||||
break;
|
||||
case CONSOLE_COLOR_USER_INPUT:
|
||||
fprintf(con_st.out, ANSI_BOLD ANSI_COLOR_GREEN);
|
||||
break;
|
||||
case CONSOLE_COLOR_ERROR:
|
||||
fprintf(con_st.out, ANSI_BOLD ANSI_COLOR_RED);
|
||||
break;
|
||||
}
|
||||
con_st.color = color;
|
||||
fflush(con_st.out);
|
||||
}
|
||||
}
|
||||
|
||||
char32_t getchar32() {
|
||||
#if defined(_WIN32)
|
||||
HANDLE hConsole = GetStdHandle(STD_INPUT_HANDLE);
|
||||
wchar_t high_surrogate = 0;
|
||||
|
||||
while (true) {
|
||||
INPUT_RECORD record;
|
||||
DWORD count;
|
||||
if (!ReadConsoleInputW(hConsole, &record, 1, &count) || count == 0) {
|
||||
return WEOF;
|
||||
}
|
||||
|
||||
if (record.EventType == KEY_EVENT && record.Event.KeyEvent.bKeyDown) {
|
||||
wchar_t wc = record.Event.KeyEvent.uChar.UnicodeChar;
|
||||
if (wc == 0) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if ((wc >= 0xD800) && (wc <= 0xDBFF)) { // Check if wc is a high surrogate
|
||||
high_surrogate = wc;
|
||||
continue;
|
||||
} else if ((wc >= 0xDC00) && (wc <= 0xDFFF)) { // Check if wc is a low surrogate
|
||||
if (high_surrogate != 0) { // Check if we have a high surrogate
|
||||
return ((high_surrogate - 0xD800) << 10) + (wc - 0xDC00) + 0x10000;
|
||||
}
|
||||
}
|
||||
|
||||
high_surrogate = 0; // Reset the high surrogate
|
||||
return static_cast<char32_t>(wc);
|
||||
}
|
||||
}
|
||||
#else
|
||||
wchar_t wc = getwchar();
|
||||
if (static_cast<wint_t>(wc) == WEOF) {
|
||||
return WEOF;
|
||||
}
|
||||
|
||||
#if WCHAR_MAX == 0xFFFF
|
||||
if ((wc >= 0xD800) && (wc <= 0xDBFF)) { // Check if wc is a high surrogate
|
||||
wchar_t low_surrogate = getwchar();
|
||||
if ((low_surrogate >= 0xDC00) && (low_surrogate <= 0xDFFF)) { // Check if the next wchar is a low surrogate
|
||||
return (static_cast<char32_t>(wc & 0x03FF) << 10) + (low_surrogate & 0x03FF) + 0x10000;
|
||||
}
|
||||
}
|
||||
if ((wc >= 0xD800) && (wc <= 0xDFFF)) { // Invalid surrogate pair
|
||||
return 0xFFFD; // Return the replacement character U+FFFD
|
||||
}
|
||||
#endif
|
||||
|
||||
return static_cast<char32_t>(wc);
|
||||
#endif
|
||||
}
|
||||
|
||||
void pop_cursor(console_state & con_st) {
|
||||
#if defined(_WIN32)
|
||||
if (con_st.hConsole != NULL) {
|
||||
CONSOLE_SCREEN_BUFFER_INFO bufferInfo;
|
||||
GetConsoleScreenBufferInfo(con_st.hConsole, &bufferInfo);
|
||||
|
||||
COORD newCursorPosition = bufferInfo.dwCursorPosition;
|
||||
if (newCursorPosition.X == 0) {
|
||||
newCursorPosition.X = bufferInfo.dwSize.X - 1;
|
||||
newCursorPosition.Y -= 1;
|
||||
} else {
|
||||
newCursorPosition.X -= 1;
|
||||
}
|
||||
|
||||
SetConsoleCursorPosition(con_st.hConsole, newCursorPosition);
|
||||
return;
|
||||
}
|
||||
#endif
|
||||
putc('\b', con_st.out);
|
||||
}
|
||||
|
||||
int estimateWidth(char32_t codepoint) {
|
||||
#if defined(_WIN32)
|
||||
return 1;
|
||||
#else
|
||||
return wcwidth(codepoint);
|
||||
#endif
|
||||
}
|
||||
|
||||
int put_codepoint(console_state & con_st, const char* utf8_codepoint, size_t length, int expectedWidth) {
|
||||
#if defined(_WIN32)
|
||||
CONSOLE_SCREEN_BUFFER_INFO bufferInfo;
|
||||
if (!GetConsoleScreenBufferInfo(con_st.hConsole, &bufferInfo)) {
|
||||
// go with the default
|
||||
return expectedWidth;
|
||||
}
|
||||
COORD initialPosition = bufferInfo.dwCursorPosition;
|
||||
DWORD nNumberOfChars = length;
|
||||
WriteConsole(con_st.hConsole, utf8_codepoint, nNumberOfChars, &nNumberOfChars, NULL);
|
||||
|
||||
CONSOLE_SCREEN_BUFFER_INFO newBufferInfo;
|
||||
GetConsoleScreenBufferInfo(con_st.hConsole, &newBufferInfo);
|
||||
|
||||
// Figure out our real position if we're in the last column
|
||||
if (utf8_codepoint[0] != 0x09 && initialPosition.X == newBufferInfo.dwSize.X - 1) {
|
||||
DWORD nNumberOfChars;
|
||||
WriteConsole(con_st.hConsole, &" \b", 2, &nNumberOfChars, NULL);
|
||||
GetConsoleScreenBufferInfo(con_st.hConsole, &newBufferInfo);
|
||||
}
|
||||
|
||||
int width = newBufferInfo.dwCursorPosition.X - initialPosition.X;
|
||||
if (width < 0) {
|
||||
width += newBufferInfo.dwSize.X;
|
||||
}
|
||||
return width;
|
||||
#else
|
||||
// we can trust expectedWidth if we've got one
|
||||
if (expectedWidth >= 0 || con_st.tty == nullptr) {
|
||||
fwrite(utf8_codepoint, length, 1, con_st.out);
|
||||
return expectedWidth;
|
||||
}
|
||||
|
||||
fputs("\033[6n", con_st.tty); // Query cursor position
|
||||
int x1, x2, y1, y2;
|
||||
int results = 0;
|
||||
results = fscanf(con_st.tty, "\033[%d;%dR", &y1, &x1);
|
||||
|
||||
fwrite(utf8_codepoint, length, 1, con_st.tty);
|
||||
|
||||
fputs("\033[6n", con_st.tty); // Query cursor position
|
||||
results += fscanf(con_st.tty, "\033[%d;%dR", &y2, &x2);
|
||||
|
||||
if (results != 4) {
|
||||
return expectedWidth;
|
||||
}
|
||||
|
||||
int width = x2 - x1;
|
||||
if (width < 0) {
|
||||
// Calculate the width considering text wrapping
|
||||
struct winsize w;
|
||||
ioctl(STDOUT_FILENO, TIOCGWINSZ, &w);
|
||||
width += w.ws_col;
|
||||
}
|
||||
return width;
|
||||
#endif
|
||||
}
|
||||
|
||||
void replace_last(console_state & con_st, char ch) {
|
||||
#if defined(_WIN32)
|
||||
pop_cursor(con_st);
|
||||
put_codepoint(con_st, &ch, 1, 1);
|
||||
#else
|
||||
fprintf(con_st.out, "\b%c", ch);
|
||||
#endif
|
||||
}
|
||||
|
||||
void append_utf8(char32_t ch, std::string & out) {
|
||||
if (ch <= 0x7F) {
|
||||
out.push_back(static_cast<unsigned char>(ch));
|
||||
} else if (ch <= 0x7FF) {
|
||||
out.push_back(static_cast<unsigned char>(0xC0 | ((ch >> 6) & 0x1F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | (ch & 0x3F)));
|
||||
} else if (ch <= 0xFFFF) {
|
||||
out.push_back(static_cast<unsigned char>(0xE0 | ((ch >> 12) & 0x0F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | ((ch >> 6) & 0x3F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | (ch & 0x3F)));
|
||||
} else if (ch <= 0x10FFFF) {
|
||||
out.push_back(static_cast<unsigned char>(0xF0 | ((ch >> 18) & 0x07)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | ((ch >> 12) & 0x3F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | ((ch >> 6) & 0x3F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | (ch & 0x3F)));
|
||||
} else {
|
||||
// Invalid Unicode code point
|
||||
}
|
||||
}
|
||||
|
||||
// Helper function to remove the last UTF-8 character from a string
|
||||
void pop_back_utf8_char(std::string & line) {
|
||||
if (line.empty()) {
|
||||
return;
|
||||
}
|
||||
|
||||
size_t pos = line.length() - 1;
|
||||
|
||||
// Find the start of the last UTF-8 character (checking up to 4 bytes back)
|
||||
for (size_t i = 0; i < 3 && pos > 0; ++i, --pos) {
|
||||
if ((line[pos] & 0xC0) != 0x80) break; // Found the start of the character
|
||||
}
|
||||
line.erase(pos);
|
||||
}
|
||||
|
||||
bool console_readline(console_state & con_st, std::string & line) {
|
||||
console_set_color(con_st, CONSOLE_COLOR_USER_INPUT);
|
||||
if (con_st.out != stdout) {
|
||||
fflush(stdout);
|
||||
}
|
||||
|
||||
line.clear();
|
||||
std::vector<int> widths;
|
||||
bool is_special_char = false;
|
||||
bool end_of_stream = false;
|
||||
|
||||
char32_t input_char;
|
||||
while (true) {
|
||||
fflush(con_st.out); // Ensure all output is displayed before waiting for input
|
||||
input_char = getchar32();
|
||||
|
||||
if (input_char == '\r' || input_char == '\n') {
|
||||
break;
|
||||
}
|
||||
|
||||
if (input_char == (char32_t) WEOF || input_char == 0x04 /* Ctrl+D*/) {
|
||||
end_of_stream = true;
|
||||
break;
|
||||
}
|
||||
|
||||
if (is_special_char) {
|
||||
console_set_color(con_st, CONSOLE_COLOR_USER_INPUT);
|
||||
replace_last(con_st, line.back());
|
||||
is_special_char = false;
|
||||
}
|
||||
|
||||
if (input_char == '\033') { // Escape sequence
|
||||
char32_t code = getchar32();
|
||||
if (code == '[' || code == 0x1B) {
|
||||
// Discard the rest of the escape sequence
|
||||
while ((code = getchar32()) != (char32_t) WEOF) {
|
||||
if ((code >= 'A' && code <= 'Z') || (code >= 'a' && code <= 'z') || code == '~') {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
} else if (input_char == 0x08 || input_char == 0x7F) { // Backspace
|
||||
if (!widths.empty()) {
|
||||
int count;
|
||||
do {
|
||||
count = widths.back();
|
||||
widths.pop_back();
|
||||
// Move cursor back, print space, and move cursor back again
|
||||
for (int i = 0; i < count; i++) {
|
||||
replace_last(con_st, ' ');
|
||||
pop_cursor(con_st);
|
||||
}
|
||||
pop_back_utf8_char(line);
|
||||
} while (count == 0 && !widths.empty());
|
||||
}
|
||||
} else {
|
||||
int offset = line.length();
|
||||
append_utf8(input_char, line);
|
||||
int width = put_codepoint(con_st, line.c_str() + offset, line.length() - offset, estimateWidth(input_char));
|
||||
if (width < 0) {
|
||||
width = 0;
|
||||
}
|
||||
widths.push_back(width);
|
||||
}
|
||||
|
||||
if (!line.empty() && (line.back() == '\\' || line.back() == '/')) {
|
||||
console_set_color(con_st, CONSOLE_COLOR_PROMPT);
|
||||
replace_last(con_st, line.back());
|
||||
is_special_char = true;
|
||||
}
|
||||
}
|
||||
|
||||
bool has_more = con_st.multiline_input;
|
||||
if (is_special_char) {
|
||||
replace_last(con_st, ' ');
|
||||
pop_cursor(con_st);
|
||||
|
||||
char last = line.back();
|
||||
line.pop_back();
|
||||
if (last == '\\') {
|
||||
line += '\n';
|
||||
fputc('\n', con_st.out);
|
||||
has_more = !has_more;
|
||||
} else {
|
||||
// llama will just eat the single space, it won't act as a space
|
||||
if (line.length() == 1 && line.back() == ' ') {
|
||||
line.clear();
|
||||
pop_cursor(con_st);
|
||||
}
|
||||
has_more = false;
|
||||
}
|
||||
} else {
|
||||
if (end_of_stream) {
|
||||
has_more = false;
|
||||
} else {
|
||||
line += '\n';
|
||||
fputc('\n', con_st.out);
|
||||
}
|
||||
}
|
||||
|
||||
fflush(con_st.out);
|
||||
return has_more;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -11,11 +11,6 @@
|
|||
#include <unordered_map>
|
||||
#include <tuple>
|
||||
|
||||
#if !defined (_WIN32)
|
||||
#include <stdio.h>
|
||||
#include <termios.h>
|
||||
#endif
|
||||
|
||||
//
|
||||
// CLI argument parsing
|
||||
//
|
||||
|
|
@ -74,6 +69,7 @@ struct gpt_params {
|
|||
size_t hellaswag_tasks = 400; // number of tasks to use when computing the HellaSwag score
|
||||
|
||||
bool low_vram = false; // if true, reduce VRAM usage at the cost of performance
|
||||
bool mul_mat_q = false; // if true, use experimental mul_mat_q kernels
|
||||
bool memory_f16 = true; // use f16 instead of f32 for memory kv
|
||||
bool random_prompt = false; // do not randomize prompt if none provided
|
||||
bool use_color = false; // use color to distinguish generations and inputs
|
||||
|
|
@ -84,6 +80,7 @@ struct gpt_params {
|
|||
bool embedding = false; // get only sentence embedding
|
||||
bool interactive_first = false; // wait for user input immediately
|
||||
bool multiline_input = false; // reverse the usage of `\`
|
||||
bool simple_io = false; // improves compatibility with subprocesses and limited consoles
|
||||
|
||||
bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix
|
||||
bool instruct = false; // instruction mode (used for Alpaca models)
|
||||
|
|
@ -115,42 +112,3 @@ std::vector<llama_token> llama_tokenize(struct llama_context * ctx, const std::s
|
|||
|
||||
std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_params(const gpt_params & params);
|
||||
struct llama_context_params llama_context_params_from_gpt_params(const gpt_params & params);
|
||||
|
||||
//
|
||||
// Console utils
|
||||
//
|
||||
|
||||
#define ANSI_COLOR_RED "\x1b[31m"
|
||||
#define ANSI_COLOR_GREEN "\x1b[32m"
|
||||
#define ANSI_COLOR_YELLOW "\x1b[33m"
|
||||
#define ANSI_COLOR_BLUE "\x1b[34m"
|
||||
#define ANSI_COLOR_MAGENTA "\x1b[35m"
|
||||
#define ANSI_COLOR_CYAN "\x1b[36m"
|
||||
#define ANSI_COLOR_RESET "\x1b[0m"
|
||||
#define ANSI_BOLD "\x1b[1m"
|
||||
|
||||
enum console_color_t {
|
||||
CONSOLE_COLOR_DEFAULT=0,
|
||||
CONSOLE_COLOR_PROMPT,
|
||||
CONSOLE_COLOR_USER_INPUT,
|
||||
CONSOLE_COLOR_ERROR
|
||||
};
|
||||
|
||||
struct console_state {
|
||||
bool multiline_input = false;
|
||||
bool use_color = false;
|
||||
console_color_t color = CONSOLE_COLOR_DEFAULT;
|
||||
|
||||
FILE* out = stdout;
|
||||
#if defined (_WIN32)
|
||||
void* hConsole;
|
||||
#else
|
||||
FILE* tty = nullptr;
|
||||
termios prev_state;
|
||||
#endif
|
||||
};
|
||||
|
||||
void console_init(console_state & con_st);
|
||||
void console_cleanup(console_state & con_st);
|
||||
void console_set_color(console_state & con_st, console_color_t color);
|
||||
bool console_readline(console_state & con_st, std::string & line);
|
||||
|
|
|
|||
496
examples/console.cpp
Normal file
496
examples/console.cpp
Normal file
|
|
@ -0,0 +1,496 @@
|
|||
#include "console.h"
|
||||
#include <vector>
|
||||
#include <iostream>
|
||||
|
||||
#if defined(_WIN32)
|
||||
#define WIN32_LEAN_AND_MEAN
|
||||
#ifndef NOMINMAX
|
||||
#define NOMINMAX
|
||||
#endif
|
||||
#include <windows.h>
|
||||
#include <fcntl.h>
|
||||
#include <io.h>
|
||||
#else
|
||||
#include <climits>
|
||||
#include <sys/ioctl.h>
|
||||
#include <unistd.h>
|
||||
#include <wchar.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <signal.h>
|
||||
#include <termios.h>
|
||||
#endif
|
||||
|
||||
#define ANSI_COLOR_RED "\x1b[31m"
|
||||
#define ANSI_COLOR_GREEN "\x1b[32m"
|
||||
#define ANSI_COLOR_YELLOW "\x1b[33m"
|
||||
#define ANSI_COLOR_BLUE "\x1b[34m"
|
||||
#define ANSI_COLOR_MAGENTA "\x1b[35m"
|
||||
#define ANSI_COLOR_CYAN "\x1b[36m"
|
||||
#define ANSI_COLOR_RESET "\x1b[0m"
|
||||
#define ANSI_BOLD "\x1b[1m"
|
||||
|
||||
namespace console {
|
||||
|
||||
//
|
||||
// Console state
|
||||
//
|
||||
|
||||
static bool advanced_display = false;
|
||||
static bool simple_io = true;
|
||||
static display_t current_display = reset;
|
||||
|
||||
static FILE* out = stdout;
|
||||
|
||||
#if defined (_WIN32)
|
||||
static void* hConsole;
|
||||
#else
|
||||
static FILE* tty = nullptr;
|
||||
static termios initial_state;
|
||||
#endif
|
||||
|
||||
//
|
||||
// Init and cleanup
|
||||
//
|
||||
|
||||
void init(bool use_simple_io, bool use_advanced_display) {
|
||||
advanced_display = use_advanced_display;
|
||||
simple_io = use_simple_io;
|
||||
#if defined(_WIN32)
|
||||
// Windows-specific console initialization
|
||||
DWORD dwMode = 0;
|
||||
hConsole = GetStdHandle(STD_OUTPUT_HANDLE);
|
||||
if (hConsole == INVALID_HANDLE_VALUE || !GetConsoleMode(hConsole, &dwMode)) {
|
||||
hConsole = GetStdHandle(STD_ERROR_HANDLE);
|
||||
if (hConsole != INVALID_HANDLE_VALUE && (!GetConsoleMode(hConsole, &dwMode))) {
|
||||
hConsole = nullptr;
|
||||
simple_io = true;
|
||||
}
|
||||
}
|
||||
if (hConsole) {
|
||||
// Enable ANSI colors on Windows 10+
|
||||
if (advanced_display && !(dwMode & ENABLE_VIRTUAL_TERMINAL_PROCESSING)) {
|
||||
SetConsoleMode(hConsole, dwMode | ENABLE_VIRTUAL_TERMINAL_PROCESSING);
|
||||
}
|
||||
// Set console output codepage to UTF8
|
||||
SetConsoleOutputCP(CP_UTF8);
|
||||
}
|
||||
HANDLE hConIn = GetStdHandle(STD_INPUT_HANDLE);
|
||||
if (hConIn != INVALID_HANDLE_VALUE && GetConsoleMode(hConIn, &dwMode)) {
|
||||
// Set console input codepage to UTF16
|
||||
_setmode(_fileno(stdin), _O_WTEXT);
|
||||
|
||||
// Set ICANON (ENABLE_LINE_INPUT) and ECHO (ENABLE_ECHO_INPUT)
|
||||
if (simple_io) {
|
||||
dwMode |= ENABLE_LINE_INPUT | ENABLE_ECHO_INPUT;
|
||||
} else {
|
||||
dwMode &= ~(ENABLE_LINE_INPUT | ENABLE_ECHO_INPUT);
|
||||
}
|
||||
if (!SetConsoleMode(hConIn, dwMode)) {
|
||||
simple_io = true;
|
||||
}
|
||||
}
|
||||
#else
|
||||
// POSIX-specific console initialization
|
||||
if (!simple_io) {
|
||||
struct termios new_termios;
|
||||
tcgetattr(STDIN_FILENO, &initial_state);
|
||||
new_termios = initial_state;
|
||||
new_termios.c_lflag &= ~(ICANON | ECHO);
|
||||
new_termios.c_cc[VMIN] = 1;
|
||||
new_termios.c_cc[VTIME] = 0;
|
||||
tcsetattr(STDIN_FILENO, TCSANOW, &new_termios);
|
||||
|
||||
tty = fopen("/dev/tty", "w+");
|
||||
if (tty != nullptr) {
|
||||
out = tty;
|
||||
}
|
||||
}
|
||||
|
||||
setlocale(LC_ALL, "");
|
||||
#endif
|
||||
}
|
||||
|
||||
void cleanup() {
|
||||
// Reset console display
|
||||
set_display(reset);
|
||||
|
||||
#if !defined(_WIN32)
|
||||
// Restore settings on POSIX systems
|
||||
if (!simple_io) {
|
||||
if (tty != nullptr) {
|
||||
out = stdout;
|
||||
fclose(tty);
|
||||
tty = nullptr;
|
||||
}
|
||||
tcsetattr(STDIN_FILENO, TCSANOW, &initial_state);
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
//
|
||||
// Display and IO
|
||||
//
|
||||
|
||||
// Keep track of current display and only emit ANSI code if it changes
|
||||
void set_display(display_t display) {
|
||||
if (advanced_display && current_display != display) {
|
||||
fflush(stdout);
|
||||
switch(display) {
|
||||
case reset:
|
||||
fprintf(out, ANSI_COLOR_RESET);
|
||||
break;
|
||||
case prompt:
|
||||
fprintf(out, ANSI_COLOR_YELLOW);
|
||||
break;
|
||||
case user_input:
|
||||
fprintf(out, ANSI_BOLD ANSI_COLOR_GREEN);
|
||||
break;
|
||||
case error:
|
||||
fprintf(out, ANSI_BOLD ANSI_COLOR_RED);
|
||||
}
|
||||
current_display = display;
|
||||
fflush(out);
|
||||
}
|
||||
}
|
||||
|
||||
char32_t getchar32() {
|
||||
#if defined(_WIN32)
|
||||
HANDLE hConsole = GetStdHandle(STD_INPUT_HANDLE);
|
||||
wchar_t high_surrogate = 0;
|
||||
|
||||
while (true) {
|
||||
INPUT_RECORD record;
|
||||
DWORD count;
|
||||
if (!ReadConsoleInputW(hConsole, &record, 1, &count) || count == 0) {
|
||||
return WEOF;
|
||||
}
|
||||
|
||||
if (record.EventType == KEY_EVENT && record.Event.KeyEvent.bKeyDown) {
|
||||
wchar_t wc = record.Event.KeyEvent.uChar.UnicodeChar;
|
||||
if (wc == 0) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if ((wc >= 0xD800) && (wc <= 0xDBFF)) { // Check if wc is a high surrogate
|
||||
high_surrogate = wc;
|
||||
continue;
|
||||
}
|
||||
if ((wc >= 0xDC00) && (wc <= 0xDFFF)) { // Check if wc is a low surrogate
|
||||
if (high_surrogate != 0) { // Check if we have a high surrogate
|
||||
return ((high_surrogate - 0xD800) << 10) + (wc - 0xDC00) + 0x10000;
|
||||
}
|
||||
}
|
||||
|
||||
high_surrogate = 0; // Reset the high surrogate
|
||||
return static_cast<char32_t>(wc);
|
||||
}
|
||||
}
|
||||
#else
|
||||
wchar_t wc = getwchar();
|
||||
if (static_cast<wint_t>(wc) == WEOF) {
|
||||
return WEOF;
|
||||
}
|
||||
|
||||
#if WCHAR_MAX == 0xFFFF
|
||||
if ((wc >= 0xD800) && (wc <= 0xDBFF)) { // Check if wc is a high surrogate
|
||||
wchar_t low_surrogate = getwchar();
|
||||
if ((low_surrogate >= 0xDC00) && (low_surrogate <= 0xDFFF)) { // Check if the next wchar is a low surrogate
|
||||
return (static_cast<char32_t>(wc & 0x03FF) << 10) + (low_surrogate & 0x03FF) + 0x10000;
|
||||
}
|
||||
}
|
||||
if ((wc >= 0xD800) && (wc <= 0xDFFF)) { // Invalid surrogate pair
|
||||
return 0xFFFD; // Return the replacement character U+FFFD
|
||||
}
|
||||
#endif
|
||||
|
||||
return static_cast<char32_t>(wc);
|
||||
#endif
|
||||
}
|
||||
|
||||
void pop_cursor() {
|
||||
#if defined(_WIN32)
|
||||
if (hConsole != NULL) {
|
||||
CONSOLE_SCREEN_BUFFER_INFO bufferInfo;
|
||||
GetConsoleScreenBufferInfo(hConsole, &bufferInfo);
|
||||
|
||||
COORD newCursorPosition = bufferInfo.dwCursorPosition;
|
||||
if (newCursorPosition.X == 0) {
|
||||
newCursorPosition.X = bufferInfo.dwSize.X - 1;
|
||||
newCursorPosition.Y -= 1;
|
||||
} else {
|
||||
newCursorPosition.X -= 1;
|
||||
}
|
||||
|
||||
SetConsoleCursorPosition(hConsole, newCursorPosition);
|
||||
return;
|
||||
}
|
||||
#endif
|
||||
putc('\b', out);
|
||||
}
|
||||
|
||||
int estimateWidth(char32_t codepoint) {
|
||||
#if defined(_WIN32)
|
||||
return 1;
|
||||
#else
|
||||
return wcwidth(codepoint);
|
||||
#endif
|
||||
}
|
||||
|
||||
int put_codepoint(const char* utf8_codepoint, size_t length, int expectedWidth) {
|
||||
#if defined(_WIN32)
|
||||
CONSOLE_SCREEN_BUFFER_INFO bufferInfo;
|
||||
if (!GetConsoleScreenBufferInfo(hConsole, &bufferInfo)) {
|
||||
// go with the default
|
||||
return expectedWidth;
|
||||
}
|
||||
COORD initialPosition = bufferInfo.dwCursorPosition;
|
||||
DWORD nNumberOfChars = length;
|
||||
WriteConsole(hConsole, utf8_codepoint, nNumberOfChars, &nNumberOfChars, NULL);
|
||||
|
||||
CONSOLE_SCREEN_BUFFER_INFO newBufferInfo;
|
||||
GetConsoleScreenBufferInfo(hConsole, &newBufferInfo);
|
||||
|
||||
// Figure out our real position if we're in the last column
|
||||
if (utf8_codepoint[0] != 0x09 && initialPosition.X == newBufferInfo.dwSize.X - 1) {
|
||||
DWORD nNumberOfChars;
|
||||
WriteConsole(hConsole, &" \b", 2, &nNumberOfChars, NULL);
|
||||
GetConsoleScreenBufferInfo(hConsole, &newBufferInfo);
|
||||
}
|
||||
|
||||
int width = newBufferInfo.dwCursorPosition.X - initialPosition.X;
|
||||
if (width < 0) {
|
||||
width += newBufferInfo.dwSize.X;
|
||||
}
|
||||
return width;
|
||||
#else
|
||||
// We can trust expectedWidth if we've got one
|
||||
if (expectedWidth >= 0 || tty == nullptr) {
|
||||
fwrite(utf8_codepoint, length, 1, out);
|
||||
return expectedWidth;
|
||||
}
|
||||
|
||||
fputs("\033[6n", tty); // Query cursor position
|
||||
int x1;
|
||||
int y1;
|
||||
int x2;
|
||||
int y2;
|
||||
int results = 0;
|
||||
results = fscanf(tty, "\033[%d;%dR", &y1, &x1);
|
||||
|
||||
fwrite(utf8_codepoint, length, 1, tty);
|
||||
|
||||
fputs("\033[6n", tty); // Query cursor position
|
||||
results += fscanf(tty, "\033[%d;%dR", &y2, &x2);
|
||||
|
||||
if (results != 4) {
|
||||
return expectedWidth;
|
||||
}
|
||||
|
||||
int width = x2 - x1;
|
||||
if (width < 0) {
|
||||
// Calculate the width considering text wrapping
|
||||
struct winsize w;
|
||||
ioctl(STDOUT_FILENO, TIOCGWINSZ, &w);
|
||||
width += w.ws_col;
|
||||
}
|
||||
return width;
|
||||
#endif
|
||||
}
|
||||
|
||||
void replace_last(char ch) {
|
||||
#if defined(_WIN32)
|
||||
pop_cursor();
|
||||
put_codepoint(&ch, 1, 1);
|
||||
#else
|
||||
fprintf(out, "\b%c", ch);
|
||||
#endif
|
||||
}
|
||||
|
||||
void append_utf8(char32_t ch, std::string & out) {
|
||||
if (ch <= 0x7F) {
|
||||
out.push_back(static_cast<unsigned char>(ch));
|
||||
} else if (ch <= 0x7FF) {
|
||||
out.push_back(static_cast<unsigned char>(0xC0 | ((ch >> 6) & 0x1F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | (ch & 0x3F)));
|
||||
} else if (ch <= 0xFFFF) {
|
||||
out.push_back(static_cast<unsigned char>(0xE0 | ((ch >> 12) & 0x0F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | ((ch >> 6) & 0x3F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | (ch & 0x3F)));
|
||||
} else if (ch <= 0x10FFFF) {
|
||||
out.push_back(static_cast<unsigned char>(0xF0 | ((ch >> 18) & 0x07)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | ((ch >> 12) & 0x3F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | ((ch >> 6) & 0x3F)));
|
||||
out.push_back(static_cast<unsigned char>(0x80 | (ch & 0x3F)));
|
||||
} else {
|
||||
// Invalid Unicode code point
|
||||
}
|
||||
}
|
||||
|
||||
// Helper function to remove the last UTF-8 character from a string
|
||||
void pop_back_utf8_char(std::string & line) {
|
||||
if (line.empty()) {
|
||||
return;
|
||||
}
|
||||
|
||||
size_t pos = line.length() - 1;
|
||||
|
||||
// Find the start of the last UTF-8 character (checking up to 4 bytes back)
|
||||
for (size_t i = 0; i < 3 && pos > 0; ++i, --pos) {
|
||||
if ((line[pos] & 0xC0) != 0x80) {
|
||||
break; // Found the start of the character
|
||||
}
|
||||
}
|
||||
line.erase(pos);
|
||||
}
|
||||
|
||||
bool readline_advanced(std::string & line, bool multiline_input) {
|
||||
if (out != stdout) {
|
||||
fflush(stdout);
|
||||
}
|
||||
|
||||
line.clear();
|
||||
std::vector<int> widths;
|
||||
bool is_special_char = false;
|
||||
bool end_of_stream = false;
|
||||
|
||||
char32_t input_char;
|
||||
while (true) {
|
||||
fflush(out); // Ensure all output is displayed before waiting for input
|
||||
input_char = getchar32();
|
||||
|
||||
if (input_char == '\r' || input_char == '\n') {
|
||||
break;
|
||||
}
|
||||
|
||||
if (input_char == (char32_t) WEOF || input_char == 0x04 /* Ctrl+D*/) {
|
||||
end_of_stream = true;
|
||||
break;
|
||||
}
|
||||
|
||||
if (is_special_char) {
|
||||
set_display(user_input);
|
||||
replace_last(line.back());
|
||||
is_special_char = false;
|
||||
}
|
||||
|
||||
if (input_char == '\033') { // Escape sequence
|
||||
char32_t code = getchar32();
|
||||
if (code == '[' || code == 0x1B) {
|
||||
// Discard the rest of the escape sequence
|
||||
while ((code = getchar32()) != (char32_t) WEOF) {
|
||||
if ((code >= 'A' && code <= 'Z') || (code >= 'a' && code <= 'z') || code == '~') {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
} else if (input_char == 0x08 || input_char == 0x7F) { // Backspace
|
||||
if (!widths.empty()) {
|
||||
int count;
|
||||
do {
|
||||
count = widths.back();
|
||||
widths.pop_back();
|
||||
// Move cursor back, print space, and move cursor back again
|
||||
for (int i = 0; i < count; i++) {
|
||||
replace_last(' ');
|
||||
pop_cursor();
|
||||
}
|
||||
pop_back_utf8_char(line);
|
||||
} while (count == 0 && !widths.empty());
|
||||
}
|
||||
} else {
|
||||
int offset = line.length();
|
||||
append_utf8(input_char, line);
|
||||
int width = put_codepoint(line.c_str() + offset, line.length() - offset, estimateWidth(input_char));
|
||||
if (width < 0) {
|
||||
width = 0;
|
||||
}
|
||||
widths.push_back(width);
|
||||
}
|
||||
|
||||
if (!line.empty() && (line.back() == '\\' || line.back() == '/')) {
|
||||
set_display(prompt);
|
||||
replace_last(line.back());
|
||||
is_special_char = true;
|
||||
}
|
||||
}
|
||||
|
||||
bool has_more = multiline_input;
|
||||
if (is_special_char) {
|
||||
replace_last(' ');
|
||||
pop_cursor();
|
||||
|
||||
char last = line.back();
|
||||
line.pop_back();
|
||||
if (last == '\\') {
|
||||
line += '\n';
|
||||
fputc('\n', out);
|
||||
has_more = !has_more;
|
||||
} else {
|
||||
// llama will just eat the single space, it won't act as a space
|
||||
if (line.length() == 1 && line.back() == ' ') {
|
||||
line.clear();
|
||||
pop_cursor();
|
||||
}
|
||||
has_more = false;
|
||||
}
|
||||
} else {
|
||||
if (end_of_stream) {
|
||||
has_more = false;
|
||||
} else {
|
||||
line += '\n';
|
||||
fputc('\n', out);
|
||||
}
|
||||
}
|
||||
|
||||
fflush(out);
|
||||
return has_more;
|
||||
}
|
||||
|
||||
bool readline_simple(std::string & line, bool multiline_input) {
|
||||
#if defined(_WIN32)
|
||||
std::wstring wline;
|
||||
if (!std::getline(std::wcin, wline)) {
|
||||
// Input stream is bad or EOF received
|
||||
line.clear();
|
||||
GenerateConsoleCtrlEvent(CTRL_C_EVENT, 0);
|
||||
return false;
|
||||
}
|
||||
|
||||
int size_needed = WideCharToMultiByte(CP_UTF8, 0, &wline[0], (int)wline.size(), NULL, 0, NULL, NULL);
|
||||
line.resize(size_needed);
|
||||
WideCharToMultiByte(CP_UTF8, 0, &wline[0], (int)wline.size(), &line[0], size_needed, NULL, NULL);
|
||||
#else
|
||||
if (!std::getline(std::cin, line)) {
|
||||
// Input stream is bad or EOF received
|
||||
line.clear();
|
||||
return false;
|
||||
}
|
||||
#endif
|
||||
if (!line.empty()) {
|
||||
char last = line.back();
|
||||
if (last == '/') { // Always return control on '/' symbol
|
||||
line.pop_back();
|
||||
return false;
|
||||
}
|
||||
if (last == '\\') { // '\\' changes the default action
|
||||
line.pop_back();
|
||||
multiline_input = !multiline_input;
|
||||
}
|
||||
}
|
||||
line += '\n';
|
||||
|
||||
// By default, continue input if multiline_input is set
|
||||
return multiline_input;
|
||||
}
|
||||
|
||||
bool readline(std::string & line, bool multiline_input) {
|
||||
set_display(user_input);
|
||||
|
||||
if (simple_io) {
|
||||
return readline_simple(line, multiline_input);
|
||||
}
|
||||
return readline_advanced(line, multiline_input);
|
||||
}
|
||||
|
||||
}
|
||||
19
examples/console.h
Normal file
19
examples/console.h
Normal file
|
|
@ -0,0 +1,19 @@
|
|||
// Console functions
|
||||
|
||||
#pragma once
|
||||
|
||||
#include <string>
|
||||
|
||||
namespace console {
|
||||
enum display_t {
|
||||
reset = 0,
|
||||
prompt,
|
||||
user_input,
|
||||
error
|
||||
};
|
||||
|
||||
void init(bool use_simple_io, bool use_advanced_display);
|
||||
void cleanup();
|
||||
void set_display(display_t display);
|
||||
bool readline(std::string & line, bool multiline_input);
|
||||
}
|
||||
|
|
@ -30,7 +30,7 @@ struct MyModel* create_mymodel(int argc, char ** argv) {
|
|||
fprintf(stderr, "%s: build = %d (%s)\n", __func__, BUILD_NUMBER, BUILD_COMMIT);
|
||||
|
||||
if (params.seed == LLAMA_DEFAULT_SEED) {
|
||||
params.seed = time(NULL);
|
||||
params.seed = uint32_t(time(NULL));
|
||||
}
|
||||
fprintf(stderr, "%s: seed = %d\n", __func__, params.seed);
|
||||
|
||||
|
|
|
|||
|
|
@ -405,7 +405,7 @@ namespace grammar_parser {
|
|||
for (size_t i = 0, end = state.rules.size(); i < end; i++) {
|
||||
// fprintf(file, "%zu: ", i);
|
||||
// print_rule_binary(file, state.rules[i]);
|
||||
print_rule(file, i, state.rules[i], symbol_id_names);
|
||||
print_rule(file, uint32_t(i), state.rules[i], symbol_id_names);
|
||||
// fprintf(file, "\n");
|
||||
}
|
||||
} catch (const std::exception & err) {
|
||||
|
|
|
|||
132
examples/json-schema-to-grammar.py
Normal file
132
examples/json-schema-to-grammar.py
Normal file
|
|
@ -0,0 +1,132 @@
|
|||
import argparse
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
|
||||
# whitespace is constrained to a single space char to prevent model "running away" in
|
||||
# whitespace. Also maybe improves generation quality?
|
||||
SPACE_RULE = '" "?'
|
||||
|
||||
PRIMITIVE_RULES = {
|
||||
'boolean': '("true" | "false") space',
|
||||
'number': '("-"? ([0-9] | [1-9] [0-9]*)) ("." [0-9]+)? ([eE] [-+]? [0-9]+)? space',
|
||||
'integer': '("-"? ([0-9] | [1-9] [0-9]*)) space',
|
||||
'string': r''' "\"" (
|
||||
[^"\\] |
|
||||
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
|
||||
)* "\"" space ''',
|
||||
'null': '"null" space',
|
||||
}
|
||||
|
||||
INVALID_RULE_CHARS_RE = re.compile(r'[^a-zA-Z0-9-]+')
|
||||
GRAMMAR_LITERAL_ESCAPE_RE = re.compile(r'[\r\n"]')
|
||||
GRAMMAR_LITERAL_ESCAPES = {'\r': '\\r', '\n': '\\n', '"': '\\"'}
|
||||
|
||||
|
||||
class SchemaConverter:
|
||||
def __init__(self, prop_order):
|
||||
self._prop_order = prop_order
|
||||
self._rules = {'space': SPACE_RULE}
|
||||
|
||||
def _format_literal(self, literal):
|
||||
escaped = GRAMMAR_LITERAL_ESCAPE_RE.sub(
|
||||
lambda m: GRAMMAR_LITERAL_ESCAPES.get(m.group(0)), json.dumps(literal)
|
||||
)
|
||||
return f'"{escaped}"'
|
||||
|
||||
def _add_rule(self, name, rule):
|
||||
esc_name = INVALID_RULE_CHARS_RE.sub('-', name)
|
||||
if esc_name not in self._rules or self._rules[esc_name] == rule:
|
||||
key = esc_name
|
||||
else:
|
||||
i = 0
|
||||
while f'{esc_name}{i}' in self._rules:
|
||||
i += 1
|
||||
key = f'{esc_name}{i}'
|
||||
self._rules[key] = rule
|
||||
return key
|
||||
|
||||
def visit(self, schema, name):
|
||||
schema_type = schema.get('type')
|
||||
rule_name = name or 'root'
|
||||
|
||||
if 'oneOf' in schema or 'anyOf' in schema:
|
||||
rule = ' | '.join((
|
||||
self.visit(alt_schema, f'{name}{"-" if name else ""}{i}')
|
||||
for i, alt_schema in enumerate(schema.get('oneOf') or schema['anyOf'])
|
||||
))
|
||||
return self._add_rule(rule_name, rule)
|
||||
|
||||
elif 'const' in schema:
|
||||
return self._add_rule(rule_name, self._format_literal(schema['const']))
|
||||
|
||||
elif 'enum' in schema:
|
||||
rule = ' | '.join((self._format_literal(v) for v in schema['enum']))
|
||||
return self._add_rule(rule_name, rule)
|
||||
|
||||
elif schema_type == 'object' and 'properties' in schema:
|
||||
# TODO: `required` keyword
|
||||
prop_order = self._prop_order
|
||||
prop_pairs = sorted(
|
||||
schema['properties'].items(),
|
||||
# sort by position in prop_order (if specified) then by key
|
||||
key=lambda kv: (prop_order.get(kv[0], len(prop_order)), kv[0]),
|
||||
)
|
||||
|
||||
rule = '"{" space'
|
||||
for i, (prop_name, prop_schema) in enumerate(prop_pairs):
|
||||
prop_rule_name = self.visit(prop_schema, f'{name}{"-" if name else ""}{prop_name}')
|
||||
if i > 0:
|
||||
rule += ' "," space'
|
||||
rule += fr' {self._format_literal(prop_name)} space ":" space {prop_rule_name}'
|
||||
rule += ' "}" space'
|
||||
|
||||
return self._add_rule(rule_name, rule)
|
||||
|
||||
elif schema_type == 'array' and 'items' in schema:
|
||||
# TODO `prefixItems` keyword
|
||||
item_rule_name = self.visit(schema['items'], f'{name}{"-" if name else ""}item')
|
||||
rule = f'"[" space ({item_rule_name} ("," space {item_rule_name})*)? "]" space'
|
||||
return self._add_rule(rule_name, rule)
|
||||
|
||||
else:
|
||||
assert schema_type in PRIMITIVE_RULES, f'Unrecognized schema: {schema}'
|
||||
return self._add_rule(
|
||||
'root' if rule_name == 'root' else schema_type,
|
||||
PRIMITIVE_RULES[schema_type]
|
||||
)
|
||||
|
||||
def format_grammar(self):
|
||||
return '\n'.join((f'{name} ::= {rule}' for name, rule in self._rules.items()))
|
||||
|
||||
|
||||
def main(args_in = None):
|
||||
parser = argparse.ArgumentParser(
|
||||
description='''
|
||||
Generates a grammar (suitable for use in ./main) that produces JSON conforming to a
|
||||
given JSON schema. Only a subset of JSON schema features are supported; more may be
|
||||
added in the future.
|
||||
''',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--prop-order',
|
||||
default=[],
|
||||
type=lambda s: s.split(','),
|
||||
help='''
|
||||
comma-separated property names defining the order of precedence for object properties;
|
||||
properties not specified here are given lower precedence than those that are, and are
|
||||
sorted alphabetically
|
||||
'''
|
||||
)
|
||||
parser.add_argument('schema', help='file containing JSON schema ("-" for stdin)')
|
||||
args = parser.parse_args(args_in)
|
||||
|
||||
schema = json.load(sys.stdin if args.schema == '-' else open(args.schema))
|
||||
prop_order = {name: idx for idx, name in enumerate(args.prop_order)}
|
||||
converter = SchemaConverter(prop_order)
|
||||
converter.visit(schema, '')
|
||||
print(converter.format_grammar())
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
|
@ -4,6 +4,7 @@
|
|||
#endif
|
||||
|
||||
#include "common.h"
|
||||
#include "console.h"
|
||||
#include "llama.h"
|
||||
#include "build-info.h"
|
||||
#include "grammar-parser.h"
|
||||
|
|
@ -35,9 +36,7 @@
|
|||
#pragma warning(disable: 4244 4267) // possible loss of data
|
||||
#endif
|
||||
|
||||
static console_state con_st;
|
||||
static llama_context ** g_ctx;
|
||||
|
||||
static bool is_interacting = false;
|
||||
|
||||
#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) || defined (_WIN32)
|
||||
|
|
@ -46,7 +45,7 @@ void sigint_handler(int signo) {
|
|||
if (!is_interacting) {
|
||||
is_interacting=true;
|
||||
} else {
|
||||
console_cleanup(con_st);
|
||||
console::cleanup();
|
||||
printf("\n");
|
||||
llama_print_timings(*g_ctx);
|
||||
_exit(130);
|
||||
|
|
@ -64,10 +63,8 @@ int main(int argc, char ** argv) {
|
|||
|
||||
// save choice to use color for later
|
||||
// (note for later: this is a slightly awkward choice)
|
||||
con_st.use_color = params.use_color;
|
||||
con_st.multiline_input = params.multiline_input;
|
||||
console_init(con_st);
|
||||
atexit([]() { console_cleanup(con_st); });
|
||||
console::init(params.simple_io, params.use_color);
|
||||
atexit([]() { console::cleanup(); });
|
||||
|
||||
if (params.perplexity) {
|
||||
printf("\n************\n");
|
||||
|
|
@ -373,7 +370,7 @@ int main(int argc, char ** argv) {
|
|||
|
||||
if (params.interactive) {
|
||||
const char *control_message;
|
||||
if (con_st.multiline_input) {
|
||||
if (params.multiline_input) {
|
||||
control_message = " - To return control to LLaMa, end your input with '\\'.\n"
|
||||
" - To return control without starting a new line, end your input with '/'.\n";
|
||||
} else {
|
||||
|
|
@ -401,7 +398,7 @@ int main(int argc, char ** argv) {
|
|||
int n_past_guidance = 0;
|
||||
|
||||
// the first thing we will do is to output the prompt, so set color accordingly
|
||||
console_set_color(con_st, CONSOLE_COLOR_PROMPT);
|
||||
console::set_display(console::prompt);
|
||||
|
||||
std::vector<llama_token> embd;
|
||||
std::vector<llama_token> embd_guidance;
|
||||
|
|
@ -422,9 +419,9 @@ int main(int argc, char ** argv) {
|
|||
// Ensure the input doesn't exceed the context size by truncating embd if necessary.
|
||||
if ((int)embd.size() > max_embd_size) {
|
||||
auto skipped_tokens = embd.size() - max_embd_size;
|
||||
console_set_color(con_st, CONSOLE_COLOR_ERROR);
|
||||
console::set_display(console::error);
|
||||
printf("<<input too long: skipped %zu token%s>>", skipped_tokens, skipped_tokens != 1 ? "s" : "");
|
||||
console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
|
||||
console::set_display(console::reset);
|
||||
fflush(stdout);
|
||||
embd.resize(max_embd_size);
|
||||
}
|
||||
|
|
@ -667,7 +664,7 @@ int main(int argc, char ** argv) {
|
|||
}
|
||||
// reset color to default if we there is no pending user input
|
||||
if (input_echo && (int)embd_inp.size() == n_consumed) {
|
||||
console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
|
||||
console::set_display(console::reset);
|
||||
}
|
||||
|
||||
// if not currently processing queued inputs;
|
||||
|
|
@ -693,7 +690,7 @@ int main(int argc, char ** argv) {
|
|||
if (last_output.find(antiprompt.c_str(), search_start_pos) != std::string::npos) {
|
||||
if (params.interactive) {
|
||||
is_interacting = true;
|
||||
console_set_color(con_st, CONSOLE_COLOR_USER_INPUT);
|
||||
console::set_display(console::user_input);
|
||||
}
|
||||
is_antiprompt = true;
|
||||
fflush(stdout);
|
||||
|
|
@ -714,7 +711,7 @@ int main(int argc, char ** argv) {
|
|||
|
||||
is_interacting = true;
|
||||
printf("\n");
|
||||
console_set_color(con_st, CONSOLE_COLOR_USER_INPUT);
|
||||
console::set_display(console::user_input);
|
||||
fflush(stdout);
|
||||
} else if (params.instruct) {
|
||||
is_interacting = true;
|
||||
|
|
@ -739,12 +736,12 @@ int main(int argc, char ** argv) {
|
|||
std::string line;
|
||||
bool another_line = true;
|
||||
do {
|
||||
another_line = console_readline(con_st, line);
|
||||
another_line = console::readline(line, params.multiline_input);
|
||||
buffer += line;
|
||||
} while (another_line);
|
||||
|
||||
// done taking input, reset color
|
||||
console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
|
||||
console::set_display(console::reset);
|
||||
|
||||
// Add tokens to embd only if the input buffer is non-empty
|
||||
// Entering a empty line lets the user pass control back
|
||||
|
|
|
|||
|
|
@ -153,7 +153,7 @@ void hellaswag_score(llama_context * ctx, const gpt_params & params) {
|
|||
}
|
||||
|
||||
size_t hs_task_count = prompt_lines.size()/6;
|
||||
fprintf(stderr, "%s : loaded %lu tasks from prompt.\n", __func__, hs_task_count);
|
||||
fprintf(stderr, "%s : loaded %zu tasks from prompt.\n", __func__, hs_task_count);
|
||||
|
||||
// This is needed as usual for LLaMA models
|
||||
bool prepend_bos = true;
|
||||
|
|
@ -178,7 +178,7 @@ void hellaswag_score(llama_context * ctx, const gpt_params & params) {
|
|||
double ending_logprob[4];
|
||||
};
|
||||
|
||||
fprintf(stderr, "%s : selecting %lu %s tasks.\n", __func__, hs_task_count, (randomize_tasks?"randomized":"the first") );
|
||||
fprintf(stderr, "%s : selecting %zu %s tasks.\n", __func__, hs_task_count, (randomize_tasks?"randomized":"the first") );
|
||||
|
||||
// Select and read data from prompt lines
|
||||
hs_data_t *hs_data = new hs_data_t[hs_task_count];
|
||||
|
|
@ -223,7 +223,7 @@ void hellaswag_score(llama_context * ctx, const gpt_params & params) {
|
|||
|
||||
// Stop if query wont fit the ctx window
|
||||
if (query_size > (size_t)params.n_ctx) {
|
||||
fprintf(stderr, "%s : number of tokens in query %lu > n_ctxl\n", __func__, query_size);
|
||||
fprintf(stderr, "%s : number of tokens in query %zu > n_ctxl\n", __func__, query_size);
|
||||
return;
|
||||
}
|
||||
|
||||
|
|
@ -284,7 +284,7 @@ void hellaswag_score(llama_context * ctx, const gpt_params & params) {
|
|||
}
|
||||
|
||||
// Print the accumulated accuracy mean x 100
|
||||
printf("%li\t%.8lf\n",task_idx+1, acc/double(task_idx+1)*100.0);
|
||||
printf("%zu\t%.8lf\n",task_idx+1, acc/double(task_idx+1)*100.0);
|
||||
fflush(stdout);
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -163,7 +163,7 @@ node .
|
|||
|
||||
`content`: Set the text to tokenize.
|
||||
|
||||
Note that the special `BOS` token is not added in fron of the text and also a space character is not inserted automatically as it is for `/completion`.
|
||||
Note that the special `BOS` token is not added in front of the text and also a space character is not inserted automatically as it is for `/completion`.
|
||||
|
||||
- **POST** `/embedding`: Generate embedding of a given text just as [the embedding example](../embedding) does.
|
||||
|
||||
|
|
|
|||
|
|
@ -87,289 +87,342 @@ unsigned char completion_js[] = {
|
|||
0x20, 0x54, 0x65, 0x78, 0x74, 0x44, 0x65, 0x63, 0x6f, 0x64, 0x65, 0x72,
|
||||
0x28, 0x29, 0x3b, 0x0a, 0x0a, 0x20, 0x20, 0x6c, 0x65, 0x74, 0x20, 0x63,
|
||||
0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20, 0x3d, 0x20, 0x22, 0x22, 0x3b,
|
||||
0x0a, 0x0a, 0x20, 0x20, 0x74, 0x72, 0x79, 0x20, 0x7b, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x6c, 0x65, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x20, 0x3d,
|
||||
0x20, 0x74, 0x72, 0x75, 0x65, 0x3b, 0x0a, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x77, 0x68, 0x69, 0x6c, 0x65, 0x20, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x29,
|
||||
0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e,
|
||||
0x73, 0x74, 0x20, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x20, 0x3d, 0x20,
|
||||
0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x72, 0x65, 0x61, 0x64, 0x65, 0x72,
|
||||
0x2e, 0x72, 0x65, 0x61, 0x64, 0x28, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x72, 0x65, 0x73, 0x75, 0x6c,
|
||||
0x74, 0x2e, 0x64, 0x6f, 0x6e, 0x65, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x62, 0x72, 0x65, 0x61, 0x6b, 0x3b,
|
||||
0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x2f, 0x2f, 0x20, 0x73, 0x73, 0x65, 0x20, 0x61,
|
||||
0x6e, 0x73, 0x77, 0x65, 0x72, 0x73, 0x20, 0x69, 0x6e, 0x20, 0x74, 0x68,
|
||||
0x65, 0x20, 0x66, 0x6f, 0x72, 0x6d, 0x20, 0x6d, 0x75, 0x6c, 0x74, 0x69,
|
||||
0x70, 0x6c, 0x65, 0x20, 0x6c, 0x69, 0x6e, 0x65, 0x73, 0x20, 0x6f, 0x66,
|
||||
0x3a, 0x20, 0x76, 0x61, 0x6c, 0x75, 0x65, 0x5c, 0x6e, 0x20, 0x77, 0x69,
|
||||
0x74, 0x68, 0x20, 0x64, 0x61, 0x74, 0x61, 0x20, 0x61, 0x6c, 0x77, 0x61,
|
||||
0x79, 0x73, 0x20, 0x70, 0x72, 0x65, 0x73, 0x65, 0x6e, 0x74, 0x20, 0x61,
|
||||
0x73, 0x20, 0x61, 0x20, 0x6b, 0x65, 0x79, 0x2e, 0x20, 0x69, 0x6e, 0x20,
|
||||
0x6f, 0x75, 0x72, 0x20, 0x63, 0x61, 0x73, 0x65, 0x20, 0x77, 0x65, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x2f, 0x2f, 0x20, 0x6d, 0x61, 0x69,
|
||||
0x6e, 0x6c, 0x79, 0x20, 0x63, 0x61, 0x72, 0x65, 0x20, 0x61, 0x62, 0x6f,
|
||||
0x75, 0x74, 0x20, 0x74, 0x68, 0x65, 0x20, 0x64, 0x61, 0x74, 0x61, 0x3a,
|
||||
0x20, 0x6b, 0x65, 0x79, 0x20, 0x68, 0x65, 0x72, 0x65, 0x2c, 0x20, 0x77,
|
||||
0x68, 0x69, 0x63, 0x68, 0x20, 0x77, 0x65, 0x20, 0x65, 0x78, 0x70, 0x65,
|
||||
0x63, 0x74, 0x20, 0x61, 0x73, 0x20, 0x6a, 0x73, 0x6f, 0x6e, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x74,
|
||||
0x65, 0x78, 0x74, 0x20, 0x3d, 0x20, 0x64, 0x65, 0x63, 0x6f, 0x64, 0x65,
|
||||
0x72, 0x2e, 0x64, 0x65, 0x63, 0x6f, 0x64, 0x65, 0x28, 0x72, 0x65, 0x73,
|
||||
0x75, 0x6c, 0x74, 0x2e, 0x76, 0x61, 0x6c, 0x75, 0x65, 0x29, 0x3b, 0x0a,
|
||||
0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x2f, 0x2f, 0x20, 0x70, 0x61,
|
||||
0x72, 0x73, 0x65, 0x20, 0x61, 0x6c, 0x6c, 0x20, 0x73, 0x73, 0x65, 0x20,
|
||||
0x65, 0x76, 0x65, 0x6e, 0x74, 0x73, 0x20, 0x61, 0x6e, 0x64, 0x20, 0x61,
|
||||
0x64, 0x64, 0x20, 0x74, 0x68, 0x65, 0x6d, 0x20, 0x74, 0x6f, 0x20, 0x72,
|
||||
0x65, 0x73, 0x75, 0x6c, 0x74, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x72, 0x65, 0x67, 0x65, 0x78, 0x20,
|
||||
0x3d, 0x20, 0x2f, 0x5e, 0x28, 0x5c, 0x53, 0x2b, 0x29, 0x3a, 0x5c, 0x73,
|
||||
0x28, 0x2e, 0x2a, 0x29, 0x24, 0x2f, 0x67, 0x6d, 0x3b, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x28, 0x63, 0x6f, 0x6e,
|
||||
0x73, 0x74, 0x20, 0x6d, 0x61, 0x74, 0x63, 0x68, 0x20, 0x6f, 0x66, 0x20,
|
||||
0x74, 0x65, 0x78, 0x74, 0x2e, 0x6d, 0x61, 0x74, 0x63, 0x68, 0x41, 0x6c,
|
||||
0x6c, 0x28, 0x72, 0x65, 0x67, 0x65, 0x78, 0x29, 0x29, 0x20, 0x7b, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x73, 0x75,
|
||||
0x6c, 0x74, 0x5b, 0x6d, 0x61, 0x74, 0x63, 0x68, 0x5b, 0x31, 0x5d, 0x5d,
|
||||
0x20, 0x3d, 0x20, 0x6d, 0x61, 0x74, 0x63, 0x68, 0x5b, 0x32, 0x5d, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x2f, 0x2f, 0x20, 0x73, 0x69, 0x6e, 0x63, 0x65, 0x20,
|
||||
0x77, 0x65, 0x20, 0x6b, 0x6e, 0x6f, 0x77, 0x20, 0x74, 0x68, 0x69, 0x73,
|
||||
0x20, 0x69, 0x73, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x2e, 0x63, 0x70,
|
||||
0x70, 0x2c, 0x20, 0x6c, 0x65, 0x74, 0x27, 0x73, 0x20, 0x6a, 0x75, 0x73,
|
||||
0x74, 0x20, 0x64, 0x65, 0x63, 0x6f, 0x64, 0x65, 0x20, 0x74, 0x68, 0x65,
|
||||
0x20, 0x6a, 0x73, 0x6f, 0x6e, 0x20, 0x69, 0x6e, 0x20, 0x64, 0x61, 0x74,
|
||||
0x61, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x73, 0x75,
|
||||
0x6c, 0x74, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x20, 0x3d, 0x20, 0x4a, 0x53,
|
||||
0x4f, 0x4e, 0x2e, 0x70, 0x61, 0x72, 0x73, 0x65, 0x28, 0x72, 0x65, 0x73,
|
||||
0x75, 0x6c, 0x74, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x29, 0x3b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74,
|
||||
0x20, 0x2b, 0x3d, 0x20, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64,
|
||||
0x61, 0x74, 0x61, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x3b,
|
||||
0x0a, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x2f, 0x2f, 0x20, 0x79,
|
||||
0x69, 0x65, 0x6c, 0x64, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x79,
|
||||
0x69, 0x65, 0x6c, 0x64, 0x20, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x3b,
|
||||
0x0a, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x2f, 0x2f, 0x20, 0x69,
|
||||
0x66, 0x20, 0x77, 0x65, 0x20, 0x67, 0x6f, 0x74, 0x20, 0x61, 0x20, 0x73,
|
||||
0x74, 0x6f, 0x70, 0x20, 0x74, 0x6f, 0x6b, 0x65, 0x6e, 0x20, 0x66, 0x72,
|
||||
0x6f, 0x6d, 0x20, 0x73, 0x65, 0x72, 0x76, 0x65, 0x72, 0x2c, 0x20, 0x77,
|
||||
0x65, 0x20, 0x77, 0x69, 0x6c, 0x6c, 0x20, 0x62, 0x72, 0x65, 0x61, 0x6b,
|
||||
0x20, 0x68, 0x65, 0x72, 0x65, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x69, 0x66, 0x20, 0x28, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64,
|
||||
0x61, 0x74, 0x61, 0x2e, 0x73, 0x74, 0x6f, 0x70, 0x29, 0x20, 0x7b, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28,
|
||||
0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e,
|
||||
0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73,
|
||||
0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x67, 0x65, 0x6e,
|
||||
0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74,
|
||||
0x69, 0x6e, 0x67, 0x73, 0x20, 0x3d, 0x20, 0x72, 0x65, 0x73, 0x75, 0x6c,
|
||||
0x74, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e, 0x65, 0x72,
|
||||
0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e,
|
||||
0x67, 0x73, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x62, 0x72,
|
||||
0x65, 0x61, 0x6b, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d,
|
||||
0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x7d, 0x20, 0x63,
|
||||
0x61, 0x74, 0x63, 0x68, 0x20, 0x28, 0x65, 0x29, 0x20, 0x7b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x65, 0x2e, 0x6e, 0x61, 0x6d,
|
||||
0x65, 0x20, 0x21, 0x3d, 0x3d, 0x20, 0x27, 0x41, 0x62, 0x6f, 0x72, 0x74,
|
||||
0x45, 0x72, 0x72, 0x6f, 0x72, 0x27, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x6f, 0x6c, 0x65, 0x2e,
|
||||
0x65, 0x72, 0x72, 0x6f, 0x72, 0x28, 0x22, 0x6c, 0x6c, 0x61, 0x6d, 0x61,
|
||||
0x20, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x3a, 0x20, 0x22, 0x2c, 0x20, 0x65,
|
||||
0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x74, 0x68, 0x72, 0x6f, 0x77, 0x20, 0x65, 0x3b, 0x0a, 0x20, 0x20,
|
||||
0x7d, 0x0a, 0x20, 0x20, 0x66, 0x69, 0x6e, 0x61, 0x6c, 0x6c, 0x79, 0x20,
|
||||
0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x72, 0x6f,
|
||||
0x6c, 0x6c, 0x65, 0x72, 0x2e, 0x61, 0x62, 0x6f, 0x72, 0x74, 0x28, 0x29,
|
||||
0x3b, 0x0a, 0x20, 0x20, 0x7d, 0x0a, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74,
|
||||
0x75, 0x72, 0x6e, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x3b,
|
||||
0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x43, 0x61, 0x6c, 0x6c, 0x20,
|
||||
0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x2c, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72,
|
||||
0x6e, 0x20, 0x61, 0x6e, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x20, 0x74,
|
||||
0x61, 0x72, 0x67, 0x65, 0x74, 0x20, 0x74, 0x68, 0x61, 0x74, 0x20, 0x79,
|
||||
0x6f, 0x75, 0x20, 0x63, 0x61, 0x6e, 0x20, 0x73, 0x75, 0x62, 0x63, 0x72,
|
||||
0x69, 0x62, 0x65, 0x20, 0x74, 0x6f, 0x0a, 0x2f, 0x2f, 0x0a, 0x2f, 0x2f,
|
||||
0x20, 0x45, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x3a, 0x0a, 0x2f, 0x2f,
|
||||
0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x69, 0x6d, 0x70, 0x6f, 0x72,
|
||||
0x74, 0x20, 0x7b, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x45, 0x76, 0x65,
|
||||
0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x20, 0x7d, 0x20, 0x66,
|
||||
0x72, 0x6f, 0x6d, 0x20, 0x27, 0x2f, 0x63, 0x6f, 0x6d, 0x70, 0x6c, 0x65,
|
||||
0x74, 0x69, 0x6f, 0x6e, 0x2e, 0x6a, 0x73, 0x27, 0x0a, 0x2f, 0x2f, 0x0a,
|
||||
0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20,
|
||||
0x63, 0x6f, 0x6e, 0x6e, 0x20, 0x3d, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61,
|
||||
0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x28,
|
||||
0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x29, 0x0a, 0x2f, 0x2f, 0x20, 0x20,
|
||||
0x20, 0x20, 0x63, 0x6f, 0x6e, 0x6e, 0x2e, 0x61, 0x64, 0x64, 0x45, 0x76,
|
||||
0x65, 0x6e, 0x74, 0x4c, 0x69, 0x73, 0x74, 0x65, 0x6e, 0x65, 0x72, 0x28,
|
||||
0x22, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x2c, 0x20, 0x28,
|
||||
0x63, 0x68, 0x75, 0x6e, 0x6b, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a,
|
||||
0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x64, 0x6f, 0x63, 0x75,
|
||||
0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72, 0x69, 0x74, 0x65, 0x28, 0x63,
|
||||
0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x2e,
|
||||
0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x0a, 0x2f, 0x2f, 0x20,
|
||||
0x20, 0x20, 0x20, 0x7d, 0x29, 0x0a, 0x2f, 0x2f, 0x0a, 0x65, 0x78, 0x70,
|
||||
0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x6c, 0x6c,
|
||||
0x61, 0x6d, 0x61, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67,
|
||||
0x65, 0x74, 0x20, 0x3d, 0x20, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74,
|
||||
0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x20, 0x3d, 0x20, 0x7b,
|
||||
0x7d, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x20, 0x3d, 0x20,
|
||||
0x7b, 0x7d, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x63,
|
||||
0x6f, 0x6e, 0x73, 0x74, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61,
|
||||
0x72, 0x67, 0x65, 0x74, 0x20, 0x3d, 0x20, 0x6e, 0x65, 0x77, 0x20, 0x45,
|
||||
0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x28, 0x29,
|
||||
0x3b, 0x0a, 0x20, 0x20, 0x28, 0x61, 0x73, 0x79, 0x6e, 0x63, 0x20, 0x28,
|
||||
0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x6c,
|
||||
0x65, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20, 0x3d,
|
||||
0x20, 0x22, 0x22, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x66, 0x6f, 0x72,
|
||||
0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x28, 0x63, 0x6f, 0x6e, 0x73,
|
||||
0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x20, 0x6f, 0x66, 0x20, 0x6c,
|
||||
0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x2c,
|
||||
0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x63, 0x6f, 0x6e,
|
||||
0x66, 0x69, 0x67, 0x29, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e,
|
||||
0x64, 0x61, 0x74, 0x61, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20,
|
||||
0x2b, 0x3d, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74,
|
||||
0x61, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x3b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74,
|
||||
0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61,
|
||||
0x74, 0x63, 0x68, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77,
|
||||
0x20, 0x43, 0x75, 0x73, 0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74,
|
||||
0x28, 0x22, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x2c, 0x20,
|
||||
0x7b, 0x20, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63, 0x68,
|
||||
0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x20, 0x7d, 0x29, 0x29,
|
||||
0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63, 0x68, 0x75, 0x6e,
|
||||
0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e, 0x65, 0x72,
|
||||
0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e,
|
||||
0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65,
|
||||
0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63, 0x68, 0x45, 0x76,
|
||||
0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43, 0x75, 0x73, 0x74,
|
||||
0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22, 0x67, 0x65, 0x6e,
|
||||
0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74,
|
||||
0x69, 0x6e, 0x67, 0x73, 0x22, 0x2c, 0x20, 0x7b, 0x20, 0x64, 0x65, 0x74,
|
||||
0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64,
|
||||
0x0a, 0x20, 0x20, 0x6c, 0x65, 0x74, 0x20, 0x6c, 0x65, 0x66, 0x74, 0x6f,
|
||||
0x76, 0x65, 0x72, 0x20, 0x3d, 0x20, 0x22, 0x22, 0x3b, 0x20, 0x2f, 0x2f,
|
||||
0x20, 0x42, 0x75, 0x66, 0x66, 0x65, 0x72, 0x20, 0x66, 0x6f, 0x72, 0x20,
|
||||
0x70, 0x61, 0x72, 0x74, 0x69, 0x61, 0x6c, 0x6c, 0x79, 0x20, 0x72, 0x65,
|
||||
0x61, 0x64, 0x20, 0x6c, 0x69, 0x6e, 0x65, 0x73, 0x0a, 0x0a, 0x20, 0x20,
|
||||
0x74, 0x72, 0x79, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x6c, 0x65,
|
||||
0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x20, 0x3d, 0x20, 0x74, 0x72, 0x75,
|
||||
0x65, 0x3b, 0x0a, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x77, 0x68, 0x69, 0x6c,
|
||||
0x65, 0x20, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x29, 0x20, 0x7b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x72,
|
||||
0x65, 0x73, 0x75, 0x6c, 0x74, 0x20, 0x3d, 0x20, 0x61, 0x77, 0x61, 0x69,
|
||||
0x74, 0x20, 0x72, 0x65, 0x61, 0x64, 0x65, 0x72, 0x2e, 0x72, 0x65, 0x61,
|
||||
0x64, 0x28, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69,
|
||||
0x66, 0x20, 0x28, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64, 0x6f,
|
||||
0x6e, 0x65, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x62, 0x72, 0x65, 0x61, 0x6b, 0x3b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x7d, 0x0a, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x2f, 0x2f, 0x20, 0x41, 0x64, 0x64, 0x20, 0x61, 0x6e, 0x79, 0x20, 0x6c,
|
||||
0x65, 0x66, 0x74, 0x6f, 0x76, 0x65, 0x72, 0x20, 0x64, 0x61, 0x74, 0x61,
|
||||
0x20, 0x74, 0x6f, 0x20, 0x74, 0x68, 0x65, 0x20, 0x63, 0x75, 0x72, 0x72,
|
||||
0x65, 0x6e, 0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x20, 0x6f, 0x66,
|
||||
0x20, 0x64, 0x61, 0x74, 0x61, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x74, 0x65, 0x78, 0x74, 0x20, 0x3d,
|
||||
0x20, 0x6c, 0x65, 0x66, 0x74, 0x6f, 0x76, 0x65, 0x72, 0x20, 0x2b, 0x20,
|
||||
0x64, 0x65, 0x63, 0x6f, 0x64, 0x65, 0x72, 0x2e, 0x64, 0x65, 0x63, 0x6f,
|
||||
0x64, 0x65, 0x28, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x76, 0x61,
|
||||
0x6c, 0x75, 0x65, 0x29, 0x3b, 0x0a, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x2f, 0x2f, 0x20, 0x43, 0x68, 0x65, 0x63, 0x6b, 0x20, 0x69, 0x66,
|
||||
0x20, 0x74, 0x68, 0x65, 0x20, 0x6c, 0x61, 0x73, 0x74, 0x20, 0x63, 0x68,
|
||||
0x61, 0x72, 0x61, 0x63, 0x74, 0x65, 0x72, 0x20, 0x69, 0x73, 0x20, 0x61,
|
||||
0x20, 0x6c, 0x69, 0x6e, 0x65, 0x20, 0x62, 0x72, 0x65, 0x61, 0x6b, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20,
|
||||
0x65, 0x6e, 0x64, 0x73, 0x57, 0x69, 0x74, 0x68, 0x4c, 0x69, 0x6e, 0x65,
|
||||
0x42, 0x72, 0x65, 0x61, 0x6b, 0x20, 0x3d, 0x20, 0x74, 0x65, 0x78, 0x74,
|
||||
0x2e, 0x65, 0x6e, 0x64, 0x73, 0x57, 0x69, 0x74, 0x68, 0x28, 0x27, 0x5c,
|
||||
0x6e, 0x27, 0x29, 0x3b, 0x0a, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x2f, 0x2f, 0x20, 0x53, 0x70, 0x6c, 0x69, 0x74, 0x20, 0x74, 0x68, 0x65,
|
||||
0x20, 0x74, 0x65, 0x78, 0x74, 0x20, 0x69, 0x6e, 0x74, 0x6f, 0x20, 0x6c,
|
||||
0x69, 0x6e, 0x65, 0x73, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6c,
|
||||
0x65, 0x74, 0x20, 0x6c, 0x69, 0x6e, 0x65, 0x73, 0x20, 0x3d, 0x20, 0x74,
|
||||
0x65, 0x78, 0x74, 0x2e, 0x73, 0x70, 0x6c, 0x69, 0x74, 0x28, 0x27, 0x5c,
|
||||
0x6e, 0x27, 0x29, 0x3b, 0x0a, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x2f, 0x2f, 0x20, 0x49, 0x66, 0x20, 0x74, 0x68, 0x65, 0x20, 0x74, 0x65,
|
||||
0x78, 0x74, 0x20, 0x64, 0x6f, 0x65, 0x73, 0x6e, 0x27, 0x74, 0x20, 0x65,
|
||||
0x6e, 0x64, 0x20, 0x77, 0x69, 0x74, 0x68, 0x20, 0x61, 0x20, 0x6c, 0x69,
|
||||
0x6e, 0x65, 0x20, 0x62, 0x72, 0x65, 0x61, 0x6b, 0x2c, 0x20, 0x74, 0x68,
|
||||
0x65, 0x6e, 0x20, 0x74, 0x68, 0x65, 0x20, 0x6c, 0x61, 0x73, 0x74, 0x20,
|
||||
0x6c, 0x69, 0x6e, 0x65, 0x20, 0x69, 0x73, 0x20, 0x69, 0x6e, 0x63, 0x6f,
|
||||
0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x2f, 0x2f, 0x20, 0x53, 0x74, 0x6f, 0x72, 0x65, 0x20, 0x69, 0x74,
|
||||
0x20, 0x69, 0x6e, 0x20, 0x6c, 0x65, 0x66, 0x74, 0x6f, 0x76, 0x65, 0x72,
|
||||
0x20, 0x74, 0x6f, 0x20, 0x62, 0x65, 0x20, 0x61, 0x64, 0x64, 0x65, 0x64,
|
||||
0x20, 0x74, 0x6f, 0x20, 0x74, 0x68, 0x65, 0x20, 0x6e, 0x65, 0x78, 0x74,
|
||||
0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x20, 0x6f, 0x66, 0x20, 0x64, 0x61,
|
||||
0x74, 0x61, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20,
|
||||
0x28, 0x21, 0x65, 0x6e, 0x64, 0x73, 0x57, 0x69, 0x74, 0x68, 0x4c, 0x69,
|
||||
0x6e, 0x65, 0x42, 0x72, 0x65, 0x61, 0x6b, 0x29, 0x20, 0x7b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6c, 0x65, 0x66, 0x74, 0x6f,
|
||||
0x76, 0x65, 0x72, 0x20, 0x3d, 0x20, 0x6c, 0x69, 0x6e, 0x65, 0x73, 0x2e,
|
||||
0x70, 0x6f, 0x70, 0x28, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x7d, 0x20, 0x65, 0x6c, 0x73, 0x65, 0x20, 0x7b, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6c, 0x65, 0x66, 0x74, 0x6f, 0x76,
|
||||
0x65, 0x72, 0x20, 0x3d, 0x20, 0x22, 0x22, 0x3b, 0x20, 0x2f, 0x2f, 0x20,
|
||||
0x52, 0x65, 0x73, 0x65, 0x74, 0x20, 0x6c, 0x65, 0x66, 0x74, 0x6f, 0x76,
|
||||
0x65, 0x72, 0x20, 0x69, 0x66, 0x20, 0x77, 0x65, 0x20, 0x68, 0x61, 0x76,
|
||||
0x65, 0x20, 0x61, 0x20, 0x6c, 0x69, 0x6e, 0x65, 0x20, 0x62, 0x72, 0x65,
|
||||
0x61, 0x6b, 0x20, 0x61, 0x74, 0x20, 0x74, 0x68, 0x65, 0x20, 0x65, 0x6e,
|
||||
0x64, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x2f, 0x2f, 0x20, 0x50, 0x61, 0x72, 0x73,
|
||||
0x65, 0x20, 0x61, 0x6c, 0x6c, 0x20, 0x73, 0x73, 0x65, 0x20, 0x65, 0x76,
|
||||
0x65, 0x6e, 0x74, 0x73, 0x20, 0x61, 0x6e, 0x64, 0x20, 0x61, 0x64, 0x64,
|
||||
0x20, 0x74, 0x68, 0x65, 0x6d, 0x20, 0x74, 0x6f, 0x20, 0x72, 0x65, 0x73,
|
||||
0x75, 0x6c, 0x74, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f,
|
||||
0x6e, 0x73, 0x74, 0x20, 0x72, 0x65, 0x67, 0x65, 0x78, 0x20, 0x3d, 0x20,
|
||||
0x2f, 0x5e, 0x28, 0x5c, 0x53, 0x2b, 0x29, 0x3a, 0x5c, 0x73, 0x28, 0x2e,
|
||||
0x2a, 0x29, 0x24, 0x2f, 0x67, 0x6d, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x28, 0x63, 0x6f, 0x6e, 0x73, 0x74,
|
||||
0x20, 0x6c, 0x69, 0x6e, 0x65, 0x20, 0x6f, 0x66, 0x20, 0x6c, 0x69, 0x6e,
|
||||
0x65, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x6d, 0x61, 0x74, 0x63,
|
||||
0x68, 0x20, 0x3d, 0x20, 0x72, 0x65, 0x67, 0x65, 0x78, 0x2e, 0x65, 0x78,
|
||||
0x65, 0x63, 0x28, 0x6c, 0x69, 0x6e, 0x65, 0x29, 0x3b, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x6d, 0x61,
|
||||
0x74, 0x63, 0x68, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x5b,
|
||||
0x6d, 0x61, 0x74, 0x63, 0x68, 0x5b, 0x31, 0x5d, 0x5d, 0x20, 0x3d, 0x20,
|
||||
0x6d, 0x61, 0x74, 0x63, 0x68, 0x5b, 0x32, 0x5d, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x2f, 0x2f, 0x20, 0x73, 0x69,
|
||||
0x6e, 0x63, 0x65, 0x20, 0x77, 0x65, 0x20, 0x6b, 0x6e, 0x6f, 0x77, 0x20,
|
||||
0x74, 0x68, 0x69, 0x73, 0x20, 0x69, 0x73, 0x20, 0x6c, 0x6c, 0x61, 0x6d,
|
||||
0x61, 0x2e, 0x63, 0x70, 0x70, 0x2c, 0x20, 0x6c, 0x65, 0x74, 0x27, 0x73,
|
||||
0x20, 0x6a, 0x75, 0x73, 0x74, 0x20, 0x64, 0x65, 0x63, 0x6f, 0x64, 0x65,
|
||||
0x20, 0x74, 0x68, 0x65, 0x20, 0x6a, 0x73, 0x6f, 0x6e, 0x20, 0x69, 0x6e,
|
||||
0x20, 0x64, 0x61, 0x74, 0x61, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x72, 0x65, 0x73, 0x75,
|
||||
0x6c, 0x74, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x29, 0x20, 0x7b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72,
|
||||
0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x20, 0x3d,
|
||||
0x20, 0x4a, 0x53, 0x4f, 0x4e, 0x2e, 0x70, 0x61, 0x72, 0x73, 0x65, 0x28,
|
||||
0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x29,
|
||||
0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20, 0x2b, 0x3d,
|
||||
0x20, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64, 0x61, 0x74, 0x61,
|
||||
0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x3b, 0x0a, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x2f,
|
||||
0x2f, 0x20, 0x79, 0x69, 0x65, 0x6c, 0x64, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x79, 0x69, 0x65, 0x6c,
|
||||
0x64, 0x20, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x3b, 0x0a, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x2f,
|
||||
0x2f, 0x20, 0x69, 0x66, 0x20, 0x77, 0x65, 0x20, 0x67, 0x6f, 0x74, 0x20,
|
||||
0x61, 0x20, 0x73, 0x74, 0x6f, 0x70, 0x20, 0x74, 0x6f, 0x6b, 0x65, 0x6e,
|
||||
0x20, 0x66, 0x72, 0x6f, 0x6d, 0x20, 0x73, 0x65, 0x72, 0x76, 0x65, 0x72,
|
||||
0x2c, 0x20, 0x77, 0x65, 0x20, 0x77, 0x69, 0x6c, 0x6c, 0x20, 0x62, 0x72,
|
||||
0x65, 0x61, 0x6b, 0x20, 0x68, 0x65, 0x72, 0x65, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20,
|
||||
0x28, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64, 0x61, 0x74, 0x61,
|
||||
0x2e, 0x73, 0x74, 0x6f, 0x70, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69,
|
||||
0x66, 0x20, 0x28, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64, 0x61,
|
||||
0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f,
|
||||
0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x29, 0x20,
|
||||
0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61,
|
||||
0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67,
|
||||
0x73, 0x20, 0x3d, 0x20, 0x72, 0x65, 0x73, 0x75, 0x6c, 0x74, 0x2e, 0x64,
|
||||
0x61, 0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69,
|
||||
0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x20,
|
||||
0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d,
|
||||
0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63,
|
||||
0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x74, 0x69,
|
||||
0x6d, 0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61,
|
||||
0x72, 0x67, 0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63,
|
||||
0x68, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43,
|
||||
0x75, 0x73, 0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22,
|
||||
0x74, 0x69, 0x6d, 0x69, 0x6e, 0x67, 0x73, 0x22, 0x2c, 0x20, 0x7b, 0x20,
|
||||
0x64, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63, 0x68, 0x75, 0x6e,
|
||||
0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x74, 0x69, 0x6d, 0x69, 0x6e,
|
||||
0x67, 0x73, 0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65,
|
||||
0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63, 0x68, 0x45, 0x76,
|
||||
0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43, 0x75, 0x73, 0x74,
|
||||
0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22, 0x64, 0x6f, 0x6e,
|
||||
0x65, 0x22, 0x2c, 0x20, 0x7b, 0x20, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c,
|
||||
0x3a, 0x20, 0x7b, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20,
|
||||
0x7d, 0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x7d, 0x29, 0x28,
|
||||
0x29, 0x3b, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e, 0x20,
|
||||
0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x3b,
|
||||
0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x43, 0x61, 0x6c, 0x6c, 0x20,
|
||||
0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x2c, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72,
|
||||
0x6e, 0x20, 0x61, 0x20, 0x70, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x20,
|
||||
0x74, 0x68, 0x61, 0x74, 0x20, 0x72, 0x65, 0x73, 0x6f, 0x6c, 0x76, 0x65,
|
||||
0x73, 0x20, 0x74, 0x6f, 0x20, 0x74, 0x68, 0x65, 0x20, 0x63, 0x6f, 0x6d,
|
||||
0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x20, 0x74, 0x65, 0x78, 0x74, 0x2e,
|
||||
0x20, 0x54, 0x68, 0x69, 0x73, 0x20, 0x64, 0x6f, 0x65, 0x73, 0x20, 0x6e,
|
||||
0x6f, 0x74, 0x20, 0x73, 0x75, 0x70, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x73,
|
||||
0x74, 0x72, 0x65, 0x61, 0x6d, 0x69, 0x6e, 0x67, 0x0a, 0x2f, 0x2f, 0x0a,
|
||||
0x2f, 0x2f, 0x20, 0x45, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x3a, 0x0a,
|
||||
0x2f, 0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6c, 0x6c,
|
||||
0x61, 0x6d, 0x61, 0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x70,
|
||||
0x72, 0x6f, 0x6d, 0x70, 0x74, 0x29, 0x2e, 0x74, 0x68, 0x65, 0x6e, 0x28,
|
||||
0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x20, 0x3d, 0x3e,
|
||||
0x20, 0x7b, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72, 0x69,
|
||||
0x74, 0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x0a,
|
||||
0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x29, 0x0a, 0x2f, 0x2f,
|
||||
0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6f, 0x72, 0x0a, 0x2f,
|
||||
0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e,
|
||||
0x73, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20, 0x3d,
|
||||
0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61,
|
||||
0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x70, 0x72, 0x6f, 0x6d,
|
||||
0x70, 0x74, 0x29, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x64,
|
||||
0x6f, 0x63, 0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72, 0x69, 0x74,
|
||||
0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x0a, 0x2f,
|
||||
0x2f, 0x0a, 0x65, 0x78, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e,
|
||||
0x73, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x50, 0x72, 0x6f, 0x6d,
|
||||
0x69, 0x73, 0x65, 0x20, 0x3d, 0x20, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70,
|
||||
0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x3b,
|
||||
0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x20,
|
||||
0x3d, 0x20, 0x66, 0x61, 0x6c, 0x73, 0x65, 0x3b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x62,
|
||||
0x72, 0x65, 0x61, 0x6b, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x7d, 0x20,
|
||||
0x63, 0x61, 0x74, 0x63, 0x68, 0x20, 0x28, 0x65, 0x29, 0x20, 0x7b, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x65, 0x2e, 0x6e, 0x61,
|
||||
0x6d, 0x65, 0x20, 0x21, 0x3d, 0x3d, 0x20, 0x27, 0x41, 0x62, 0x6f, 0x72,
|
||||
0x74, 0x45, 0x72, 0x72, 0x6f, 0x72, 0x27, 0x29, 0x20, 0x7b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x6f, 0x6c, 0x65,
|
||||
0x2e, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x28, 0x22, 0x6c, 0x6c, 0x61, 0x6d,
|
||||
0x61, 0x20, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x3a, 0x20, 0x22, 0x2c, 0x20,
|
||||
0x65, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x74, 0x68, 0x72, 0x6f, 0x77, 0x20, 0x65, 0x3b, 0x0a, 0x20,
|
||||
0x20, 0x7d, 0x0a, 0x20, 0x20, 0x66, 0x69, 0x6e, 0x61, 0x6c, 0x6c, 0x79,
|
||||
0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x72,
|
||||
0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x2e, 0x61, 0x62, 0x6f, 0x72, 0x74, 0x28,
|
||||
0x29, 0x3b, 0x0a, 0x20, 0x20, 0x7d, 0x0a, 0x0a, 0x20, 0x20, 0x72, 0x65,
|
||||
0x74, 0x75, 0x72, 0x6e, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74,
|
||||
0x3b, 0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x43, 0x61, 0x6c, 0x6c,
|
||||
0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x2c, 0x20, 0x72, 0x65, 0x74, 0x75,
|
||||
0x72, 0x6e, 0x20, 0x61, 0x6e, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x20,
|
||||
0x74, 0x61, 0x72, 0x67, 0x65, 0x74, 0x20, 0x74, 0x68, 0x61, 0x74, 0x20,
|
||||
0x79, 0x6f, 0x75, 0x20, 0x63, 0x61, 0x6e, 0x20, 0x73, 0x75, 0x62, 0x63,
|
||||
0x72, 0x69, 0x62, 0x65, 0x20, 0x74, 0x6f, 0x0a, 0x2f, 0x2f, 0x0a, 0x2f,
|
||||
0x2f, 0x20, 0x45, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x3a, 0x0a, 0x2f,
|
||||
0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x69, 0x6d, 0x70, 0x6f,
|
||||
0x72, 0x74, 0x20, 0x7b, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x45, 0x76,
|
||||
0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x20, 0x7d, 0x20,
|
||||
0x66, 0x72, 0x6f, 0x6d, 0x20, 0x27, 0x2f, 0x63, 0x6f, 0x6d, 0x70, 0x6c,
|
||||
0x65, 0x74, 0x69, 0x6f, 0x6e, 0x2e, 0x6a, 0x73, 0x27, 0x0a, 0x2f, 0x2f,
|
||||
0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74,
|
||||
0x20, 0x63, 0x6f, 0x6e, 0x6e, 0x20, 0x3d, 0x20, 0x6c, 0x6c, 0x61, 0x6d,
|
||||
0x61, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74,
|
||||
0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x29, 0x0a, 0x2f, 0x2f, 0x20,
|
||||
0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x6e, 0x2e, 0x61, 0x64, 0x64, 0x45,
|
||||
0x76, 0x65, 0x6e, 0x74, 0x4c, 0x69, 0x73, 0x74, 0x65, 0x6e, 0x65, 0x72,
|
||||
0x28, 0x22, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x2c, 0x20,
|
||||
0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b,
|
||||
0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x64, 0x6f, 0x63,
|
||||
0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72, 0x69, 0x74, 0x65, 0x28,
|
||||
0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c,
|
||||
0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x0a, 0x2f, 0x2f,
|
||||
0x20, 0x20, 0x20, 0x20, 0x7d, 0x29, 0x0a, 0x2f, 0x2f, 0x0a, 0x65, 0x78,
|
||||
0x70, 0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x6c,
|
||||
0x6c, 0x61, 0x6d, 0x61, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72,
|
||||
0x67, 0x65, 0x74, 0x20, 0x3d, 0x20, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70,
|
||||
0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x20, 0x3d, 0x20,
|
||||
0x7b, 0x7d, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x20, 0x3d,
|
||||
0x20, 0x7b, 0x7d, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20,
|
||||
0x72, 0x65, 0x74, 0x75, 0x72, 0x6e, 0x20, 0x6e, 0x65, 0x77, 0x20, 0x50,
|
||||
0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x61, 0x73, 0x79, 0x6e, 0x63,
|
||||
0x20, 0x28, 0x72, 0x65, 0x73, 0x6f, 0x6c, 0x76, 0x65, 0x2c, 0x20, 0x72,
|
||||
0x65, 0x6a, 0x65, 0x63, 0x74, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x6c, 0x65, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74,
|
||||
0x65, 0x6e, 0x74, 0x20, 0x3d, 0x20, 0x22, 0x22, 0x3b, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x74, 0x72, 0x79, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20,
|
||||
0x28, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b,
|
||||
0x20, 0x6f, 0x66, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x72,
|
||||
0x6f, 0x6d, 0x70, 0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73,
|
||||
0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x29, 0x29, 0x20, 0x7b,
|
||||
0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e,
|
||||
0x74, 0x65, 0x6e, 0x74, 0x20, 0x2b, 0x3d, 0x20, 0x63, 0x68, 0x75, 0x6e,
|
||||
0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65,
|
||||
0x6e, 0x74, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x73, 0x6f, 0x6c, 0x76,
|
||||
0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x3b, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x7d, 0x20, 0x63, 0x61, 0x74, 0x63, 0x68, 0x20,
|
||||
0x28, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x6a, 0x65, 0x63, 0x74, 0x28, 0x65,
|
||||
0x72, 0x72, 0x6f, 0x72, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d,
|
||||
0x0a, 0x20, 0x20, 0x7d, 0x29, 0x3b, 0x0a, 0x7d, 0x3b, 0x0a, 0x0a, 0x2f,
|
||||
0x2a, 0x2a, 0x0a, 0x20, 0x2a, 0x20, 0x28, 0x64, 0x65, 0x70, 0x72, 0x65,
|
||||
0x63, 0x61, 0x74, 0x65, 0x64, 0x29, 0x0a, 0x20, 0x2a, 0x2f, 0x0a, 0x65,
|
||||
0x78, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20,
|
||||
0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x43, 0x6f, 0x6d, 0x70, 0x6c, 0x65, 0x74,
|
||||
0x65, 0x20, 0x3d, 0x20, 0x61, 0x73, 0x79, 0x6e, 0x63, 0x20, 0x28, 0x70,
|
||||
0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x72,
|
||||
0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x2c, 0x20, 0x63, 0x61, 0x6c, 0x6c, 0x62,
|
||||
0x61, 0x63, 0x6b, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20,
|
||||
0x66, 0x6f, 0x72, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x28, 0x63,
|
||||
0x6f, 0x6e, 0x73, 0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x20, 0x6f,
|
||||
0x66, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x61, 0x72, 0x61,
|
||||
0x6d, 0x73, 0x2e, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x2c, 0x20, 0x70,
|
||||
0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x7b, 0x20, 0x63, 0x6f, 0x6e,
|
||||
0x74, 0x72, 0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x20, 0x7d, 0x29, 0x29, 0x20,
|
||||
0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x63, 0x61, 0x6c, 0x6c, 0x62, 0x61,
|
||||
0x63, 0x6b, 0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x29, 0x3b, 0x0a, 0x20,
|
||||
0x20, 0x7d, 0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x47, 0x65, 0x74,
|
||||
0x20, 0x74, 0x68, 0x65, 0x20, 0x6d, 0x6f, 0x64, 0x65, 0x6c, 0x20, 0x69,
|
||||
0x6e, 0x66, 0x6f, 0x20, 0x66, 0x72, 0x6f, 0x6d, 0x20, 0x74, 0x68, 0x65,
|
||||
0x20, 0x73, 0x65, 0x72, 0x76, 0x65, 0x72, 0x2e, 0x20, 0x54, 0x68, 0x69,
|
||||
0x73, 0x20, 0x69, 0x73, 0x20, 0x75, 0x73, 0x65, 0x66, 0x75, 0x6c, 0x20,
|
||||
0x66, 0x6f, 0x72, 0x20, 0x67, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x20,
|
||||
0x74, 0x68, 0x65, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x78, 0x74, 0x20,
|
||||
0x77, 0x69, 0x6e, 0x64, 0x6f, 0x77, 0x20, 0x61, 0x6e, 0x64, 0x20, 0x73,
|
||||
0x6f, 0x20, 0x6f, 0x6e, 0x2e, 0x0a, 0x65, 0x78, 0x70, 0x6f, 0x72, 0x74,
|
||||
0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61,
|
||||
0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x49, 0x6e, 0x66, 0x6f, 0x20, 0x3d, 0x20,
|
||||
0x61, 0x73, 0x79, 0x6e, 0x63, 0x20, 0x28, 0x29, 0x20, 0x3d, 0x3e, 0x20,
|
||||
0x7b, 0x0a, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x21, 0x67, 0x65, 0x6e,
|
||||
0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74,
|
||||
0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54,
|
||||
0x61, 0x72, 0x67, 0x65, 0x74, 0x20, 0x3d, 0x20, 0x6e, 0x65, 0x77, 0x20,
|
||||
0x45, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x28,
|
||||
0x29, 0x3b, 0x0a, 0x20, 0x20, 0x28, 0x61, 0x73, 0x79, 0x6e, 0x63, 0x20,
|
||||
0x28, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x6c, 0x65, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20,
|
||||
0x3d, 0x20, 0x22, 0x22, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x66, 0x6f,
|
||||
0x72, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x28, 0x63, 0x6f, 0x6e,
|
||||
0x73, 0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x20, 0x6f, 0x66, 0x20,
|
||||
0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74,
|
||||
0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x63, 0x6f,
|
||||
0x6e, 0x66, 0x69, 0x67, 0x29, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b,
|
||||
0x2e, 0x64, 0x61, 0x74, 0x61, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74,
|
||||
0x20, 0x2b, 0x3d, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61,
|
||||
0x74, 0x61, 0x2e, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x3b, 0x0a,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e,
|
||||
0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70,
|
||||
0x61, 0x74, 0x63, 0x68, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65,
|
||||
0x77, 0x20, 0x43, 0x75, 0x73, 0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e,
|
||||
0x74, 0x28, 0x22, 0x6d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x2c,
|
||||
0x20, 0x7b, 0x20, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63,
|
||||
0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x20, 0x7d, 0x29,
|
||||
0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x63, 0x68, 0x75,
|
||||
0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e, 0x65,
|
||||
0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69,
|
||||
0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67,
|
||||
0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63, 0x68, 0x45,
|
||||
0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43, 0x75, 0x73,
|
||||
0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22, 0x67, 0x65,
|
||||
0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74,
|
||||
0x74, 0x69, 0x6e, 0x67, 0x73, 0x22, 0x2c, 0x20, 0x7b, 0x20, 0x64, 0x65,
|
||||
0x74, 0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e,
|
||||
0x64, 0x61, 0x74, 0x61, 0x2e, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74,
|
||||
0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73,
|
||||
0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28,
|
||||
0x63, 0x68, 0x75, 0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x74,
|
||||
0x69, 0x6d, 0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54,
|
||||
0x61, 0x72, 0x67, 0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74,
|
||||
0x63, 0x68, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20,
|
||||
0x43, 0x75, 0x73, 0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28,
|
||||
0x22, 0x74, 0x69, 0x6d, 0x69, 0x6e, 0x67, 0x73, 0x22, 0x2c, 0x20, 0x7b,
|
||||
0x20, 0x64, 0x65, 0x74, 0x61, 0x69, 0x6c, 0x3a, 0x20, 0x63, 0x68, 0x75,
|
||||
0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x74, 0x69, 0x6d, 0x69,
|
||||
0x6e, 0x67, 0x73, 0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67,
|
||||
0x65, 0x74, 0x2e, 0x64, 0x69, 0x73, 0x70, 0x61, 0x74, 0x63, 0x68, 0x45,
|
||||
0x76, 0x65, 0x6e, 0x74, 0x28, 0x6e, 0x65, 0x77, 0x20, 0x43, 0x75, 0x73,
|
||||
0x74, 0x6f, 0x6d, 0x45, 0x76, 0x65, 0x6e, 0x74, 0x28, 0x22, 0x64, 0x6f,
|
||||
0x6e, 0x65, 0x22, 0x2c, 0x20, 0x7b, 0x20, 0x64, 0x65, 0x74, 0x61, 0x69,
|
||||
0x6c, 0x3a, 0x20, 0x7b, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74,
|
||||
0x20, 0x7d, 0x20, 0x7d, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x7d, 0x29,
|
||||
0x28, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e,
|
||||
0x20, 0x65, 0x76, 0x65, 0x6e, 0x74, 0x54, 0x61, 0x72, 0x67, 0x65, 0x74,
|
||||
0x3b, 0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x43, 0x61, 0x6c, 0x6c,
|
||||
0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x2c, 0x20, 0x72, 0x65, 0x74, 0x75,
|
||||
0x72, 0x6e, 0x20, 0x61, 0x20, 0x70, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65,
|
||||
0x20, 0x74, 0x68, 0x61, 0x74, 0x20, 0x72, 0x65, 0x73, 0x6f, 0x6c, 0x76,
|
||||
0x65, 0x73, 0x20, 0x74, 0x6f, 0x20, 0x74, 0x68, 0x65, 0x20, 0x63, 0x6f,
|
||||
0x6d, 0x70, 0x6c, 0x65, 0x74, 0x65, 0x64, 0x20, 0x74, 0x65, 0x78, 0x74,
|
||||
0x2e, 0x20, 0x54, 0x68, 0x69, 0x73, 0x20, 0x64, 0x6f, 0x65, 0x73, 0x20,
|
||||
0x6e, 0x6f, 0x74, 0x20, 0x73, 0x75, 0x70, 0x70, 0x6f, 0x72, 0x74, 0x20,
|
||||
0x73, 0x74, 0x72, 0x65, 0x61, 0x6d, 0x69, 0x6e, 0x67, 0x0a, 0x2f, 0x2f,
|
||||
0x0a, 0x2f, 0x2f, 0x20, 0x45, 0x78, 0x61, 0x6d, 0x70, 0x6c, 0x65, 0x3a,
|
||||
0x0a, 0x2f, 0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6c,
|
||||
0x6c, 0x61, 0x6d, 0x61, 0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28,
|
||||
0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x29, 0x2e, 0x74, 0x68, 0x65, 0x6e,
|
||||
0x28, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x20, 0x3d,
|
||||
0x3e, 0x20, 0x7b, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72,
|
||||
0x69, 0x74, 0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29,
|
||||
0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x29, 0x0a, 0x2f,
|
||||
0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x6f, 0x72, 0x0a,
|
||||
0x2f, 0x2f, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f,
|
||||
0x6e, 0x73, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20,
|
||||
0x3d, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d,
|
||||
0x61, 0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x70, 0x72, 0x6f,
|
||||
0x6d, 0x70, 0x74, 0x29, 0x0a, 0x2f, 0x2f, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x64, 0x6f, 0x63, 0x75, 0x6d, 0x65, 0x6e, 0x74, 0x2e, 0x77, 0x72, 0x69,
|
||||
0x74, 0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x0a,
|
||||
0x2f, 0x2f, 0x0a, 0x65, 0x78, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f,
|
||||
0x6e, 0x73, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x50, 0x72, 0x6f,
|
||||
0x6d, 0x69, 0x73, 0x65, 0x20, 0x3d, 0x20, 0x28, 0x70, 0x72, 0x6f, 0x6d,
|
||||
0x70, 0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x20, 0x3d,
|
||||
0x20, 0x7b, 0x7d, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x20,
|
||||
0x3d, 0x20, 0x7b, 0x7d, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20,
|
||||
0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e, 0x20, 0x6e, 0x65, 0x77, 0x20,
|
||||
0x50, 0x72, 0x6f, 0x6d, 0x69, 0x73, 0x65, 0x28, 0x61, 0x73, 0x79, 0x6e,
|
||||
0x63, 0x20, 0x28, 0x72, 0x65, 0x73, 0x6f, 0x6c, 0x76, 0x65, 0x2c, 0x20,
|
||||
0x72, 0x65, 0x6a, 0x65, 0x63, 0x74, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b,
|
||||
0x0a, 0x20, 0x20, 0x20, 0x20, 0x6c, 0x65, 0x74, 0x20, 0x63, 0x6f, 0x6e,
|
||||
0x74, 0x65, 0x6e, 0x74, 0x20, 0x3d, 0x20, 0x22, 0x22, 0x3b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x74, 0x72, 0x79, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74,
|
||||
0x20, 0x28, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x63, 0x68, 0x75, 0x6e,
|
||||
0x6b, 0x20, 0x6f, 0x66, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70,
|
||||
0x72, 0x6f, 0x6d, 0x70, 0x74, 0x2c, 0x20, 0x70, 0x61, 0x72, 0x61, 0x6d,
|
||||
0x73, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x29, 0x29, 0x20,
|
||||
0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x63, 0x6f,
|
||||
0x6e, 0x74, 0x65, 0x6e, 0x74, 0x20, 0x2b, 0x3d, 0x20, 0x63, 0x68, 0x75,
|
||||
0x6e, 0x6b, 0x2e, 0x64, 0x61, 0x74, 0x61, 0x2e, 0x63, 0x6f, 0x6e, 0x74,
|
||||
0x65, 0x6e, 0x74, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x7d,
|
||||
0x0a, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x73, 0x6f, 0x6c,
|
||||
0x76, 0x65, 0x28, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x6e, 0x74, 0x29, 0x3b,
|
||||
0x0a, 0x20, 0x20, 0x20, 0x20, 0x7d, 0x20, 0x63, 0x61, 0x74, 0x63, 0x68,
|
||||
0x20, 0x28, 0x65, 0x72, 0x72, 0x6f, 0x72, 0x29, 0x20, 0x7b, 0x0a, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x72, 0x65, 0x6a, 0x65, 0x63, 0x74, 0x28,
|
||||
0x65, 0x72, 0x72, 0x6f, 0x72, 0x29, 0x3b, 0x0a, 0x20, 0x20, 0x20, 0x20,
|
||||
0x7d, 0x0a, 0x20, 0x20, 0x7d, 0x29, 0x3b, 0x0a, 0x7d, 0x3b, 0x0a, 0x0a,
|
||||
0x2f, 0x2a, 0x2a, 0x0a, 0x20, 0x2a, 0x20, 0x28, 0x64, 0x65, 0x70, 0x72,
|
||||
0x65, 0x63, 0x61, 0x74, 0x65, 0x64, 0x29, 0x0a, 0x20, 0x2a, 0x2f, 0x0a,
|
||||
0x65, 0x78, 0x70, 0x6f, 0x72, 0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74,
|
||||
0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x43, 0x6f, 0x6d, 0x70, 0x6c, 0x65,
|
||||
0x74, 0x65, 0x20, 0x3d, 0x20, 0x61, 0x73, 0x79, 0x6e, 0x63, 0x20, 0x28,
|
||||
0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x63, 0x6f, 0x6e, 0x74,
|
||||
0x72, 0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x2c, 0x20, 0x63, 0x61, 0x6c, 0x6c,
|
||||
0x62, 0x61, 0x63, 0x6b, 0x29, 0x20, 0x3d, 0x3e, 0x20, 0x7b, 0x0a, 0x20,
|
||||
0x20, 0x66, 0x6f, 0x72, 0x20, 0x61, 0x77, 0x61, 0x69, 0x74, 0x20, 0x28,
|
||||
0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x20,
|
||||
0x6f, 0x66, 0x20, 0x6c, 0x6c, 0x61, 0x6d, 0x61, 0x28, 0x70, 0x61, 0x72,
|
||||
0x61, 0x6d, 0x73, 0x2e, 0x70, 0x72, 0x6f, 0x6d, 0x70, 0x74, 0x2c, 0x20,
|
||||
0x70, 0x61, 0x72, 0x61, 0x6d, 0x73, 0x2c, 0x20, 0x7b, 0x20, 0x63, 0x6f,
|
||||
0x6e, 0x74, 0x72, 0x6f, 0x6c, 0x6c, 0x65, 0x72, 0x20, 0x7d, 0x29, 0x29,
|
||||
0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20, 0x20, 0x63, 0x61, 0x6c, 0x6c, 0x62,
|
||||
0x61, 0x63, 0x6b, 0x28, 0x63, 0x68, 0x75, 0x6e, 0x6b, 0x29, 0x3b, 0x0a,
|
||||
0x20, 0x20, 0x7d, 0x0a, 0x7d, 0x0a, 0x0a, 0x2f, 0x2f, 0x20, 0x47, 0x65,
|
||||
0x74, 0x20, 0x74, 0x68, 0x65, 0x20, 0x6d, 0x6f, 0x64, 0x65, 0x6c, 0x20,
|
||||
0x69, 0x6e, 0x66, 0x6f, 0x20, 0x66, 0x72, 0x6f, 0x6d, 0x20, 0x74, 0x68,
|
||||
0x65, 0x20, 0x73, 0x65, 0x72, 0x76, 0x65, 0x72, 0x2e, 0x20, 0x54, 0x68,
|
||||
0x69, 0x73, 0x20, 0x69, 0x73, 0x20, 0x75, 0x73, 0x65, 0x66, 0x75, 0x6c,
|
||||
0x20, 0x66, 0x6f, 0x72, 0x20, 0x67, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67,
|
||||
0x20, 0x74, 0x68, 0x65, 0x20, 0x63, 0x6f, 0x6e, 0x74, 0x65, 0x78, 0x74,
|
||||
0x20, 0x77, 0x69, 0x6e, 0x64, 0x6f, 0x77, 0x20, 0x61, 0x6e, 0x64, 0x20,
|
||||
0x73, 0x6f, 0x20, 0x6f, 0x6e, 0x2e, 0x0a, 0x65, 0x78, 0x70, 0x6f, 0x72,
|
||||
0x74, 0x20, 0x63, 0x6f, 0x6e, 0x73, 0x74, 0x20, 0x6c, 0x6c, 0x61, 0x6d,
|
||||
0x61, 0x4d, 0x6f, 0x64, 0x65, 0x6c, 0x49, 0x6e, 0x66, 0x6f, 0x20, 0x3d,
|
||||
0x20, 0x61, 0x73, 0x79, 0x6e, 0x63, 0x20, 0x28, 0x29, 0x20, 0x3d, 0x3e,
|
||||
0x20, 0x7b, 0x0a, 0x20, 0x20, 0x69, 0x66, 0x20, 0x28, 0x21, 0x67, 0x65,
|
||||
0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65, 0x74,
|
||||
0x74, 0x69, 0x6e, 0x67, 0x73, 0x29, 0x20, 0x7b, 0x0a, 0x20, 0x20, 0x20,
|
||||
0x20, 0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f,
|
||||
0x73, 0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x20, 0x3d, 0x20, 0x61,
|
||||
0x77, 0x61, 0x69, 0x74, 0x20, 0x66, 0x65, 0x74, 0x63, 0x68, 0x28, 0x22,
|
||||
0x2f, 0x6d, 0x6f, 0x64, 0x65, 0x6c, 0x2e, 0x6a, 0x73, 0x6f, 0x6e, 0x22,
|
||||
0x29, 0x2e, 0x74, 0x68, 0x65, 0x6e, 0x28, 0x72, 0x20, 0x3d, 0x3e, 0x20,
|
||||
0x72, 0x2e, 0x6a, 0x73, 0x6f, 0x6e, 0x28, 0x29, 0x29, 0x3b, 0x0a, 0x20,
|
||||
0x20, 0x7d, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e, 0x20,
|
||||
0x67, 0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73,
|
||||
0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x20, 0x3d, 0x20, 0x61, 0x77,
|
||||
0x61, 0x69, 0x74, 0x20, 0x66, 0x65, 0x74, 0x63, 0x68, 0x28, 0x22, 0x2f,
|
||||
0x6d, 0x6f, 0x64, 0x65, 0x6c, 0x2e, 0x6a, 0x73, 0x6f, 0x6e, 0x22, 0x29,
|
||||
0x2e, 0x74, 0x68, 0x65, 0x6e, 0x28, 0x72, 0x20, 0x3d, 0x3e, 0x20, 0x72,
|
||||
0x2e, 0x6a, 0x73, 0x6f, 0x6e, 0x28, 0x29, 0x29, 0x3b, 0x0a, 0x20, 0x20,
|
||||
0x7d, 0x0a, 0x20, 0x20, 0x72, 0x65, 0x74, 0x75, 0x72, 0x6e, 0x20, 0x67,
|
||||
0x65, 0x6e, 0x65, 0x72, 0x61, 0x74, 0x69, 0x6f, 0x6e, 0x5f, 0x73, 0x65,
|
||||
0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x3b, 0x0a, 0x7d, 0x0a
|
||||
0x65, 0x74, 0x74, 0x69, 0x6e, 0x67, 0x73, 0x3b, 0x0a, 0x7d, 0x0a
|
||||
};
|
||||
unsigned int completion_js_len = 4462;
|
||||
unsigned int completion_js_len = 5099;
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -43,6 +43,7 @@ export async function* llama(prompt, params = {}, config = {}) {
|
|||
const decoder = new TextDecoder();
|
||||
|
||||
let content = "";
|
||||
let leftover = ""; // Buffer for partially read lines
|
||||
|
||||
try {
|
||||
let cont = true;
|
||||
|
|
@ -53,17 +54,31 @@ export async function* llama(prompt, params = {}, config = {}) {
|
|||
break;
|
||||
}
|
||||
|
||||
// sse answers in the form multiple lines of: value\n with data always present as a key. in our case we
|
||||
// mainly care about the data: key here, which we expect as json
|
||||
const text = decoder.decode(result.value);
|
||||
// Add any leftover data to the current chunk of data
|
||||
const text = leftover + decoder.decode(result.value);
|
||||
|
||||
// parse all sse events and add them to result
|
||||
const regex = /^(\S+):\s(.*)$/gm;
|
||||
for (const match of text.matchAll(regex)) {
|
||||
result[match[1]] = match[2]
|
||||
// Check if the last character is a line break
|
||||
const endsWithLineBreak = text.endsWith('\n');
|
||||
|
||||
// Split the text into lines
|
||||
let lines = text.split('\n');
|
||||
|
||||
// If the text doesn't end with a line break, then the last line is incomplete
|
||||
// Store it in leftover to be added to the next chunk of data
|
||||
if (!endsWithLineBreak) {
|
||||
leftover = lines.pop();
|
||||
} else {
|
||||
leftover = ""; // Reset leftover if we have a line break at the end
|
||||
}
|
||||
|
||||
// Parse all sse events and add them to result
|
||||
const regex = /^(\S+):\s(.*)$/gm;
|
||||
for (const line of lines) {
|
||||
const match = regex.exec(line);
|
||||
if (match) {
|
||||
result[match[1]] = match[2]
|
||||
// since we know this is llama.cpp, let's just decode the json in data
|
||||
if (result.data) {
|
||||
result.data = JSON.parse(result.data);
|
||||
content += result.data.content;
|
||||
|
||||
|
|
@ -75,9 +90,13 @@ export async function* llama(prompt, params = {}, config = {}) {
|
|||
if (result.data.generation_settings) {
|
||||
generation_settings = result.data.generation_settings;
|
||||
}
|
||||
cont = false;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
} catch (e) {
|
||||
if (e.name !== 'AbortError') {
|
||||
console.error("llama error: ", e);
|
||||
|
|
|
|||
|
|
@ -3,12 +3,11 @@
|
|||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1" />
|
||||
<meta name="color-scheme" content="light dark">
|
||||
<title>llama.cpp - chat</title>
|
||||
|
||||
<style>
|
||||
body {
|
||||
background-color: #fff;
|
||||
color: #000;
|
||||
font-family: system-ui;
|
||||
font-size: 90%;
|
||||
}
|
||||
|
|
@ -283,8 +282,9 @@
|
|||
|
||||
useEffect(() => {
|
||||
// scroll to bottom (if needed)
|
||||
if (container.current && container.current.scrollHeight <= container.current.scrollTop + container.current.offsetHeight + 300) {
|
||||
container.current.scrollTo(0, container.current.scrollHeight)
|
||||
const parent = container.current.parentElement;
|
||||
if (parent && parent.scrollHeight <= parent.scrollTop + parent.offsetHeight + 300) {
|
||||
parent.scrollTo(0, parent.scrollHeight)
|
||||
}
|
||||
}, [messages])
|
||||
|
||||
|
|
|
|||
|
|
@ -631,6 +631,9 @@ static void server_print_usage(const char *argv0, const gpt_params ¶ms,
|
|||
fprintf(stdout, " how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
|
||||
fprintf(stdout, " -mg i, --main-gpu i the GPU to use for scratch and small tensors\n");
|
||||
fprintf(stdout, " -lv, --low-vram don't allocate VRAM scratch buffer\n");
|
||||
fprintf(stdout, " -mmq, --mul-mat-q use experimental mul_mat_q CUDA kernels instead of cuBLAS. TEMP!!!\n" );
|
||||
fprintf(stdout, " Reduces VRAM usage by 700/970/1430 MiB for 7b/13b/33b but prompt processing speed\n" );
|
||||
fprintf(stdout, " is still suboptimal, especially q2_K, q3_K, q5_K, and q6_K.\n" );
|
||||
#endif
|
||||
fprintf(stdout, " -m FNAME, --model FNAME\n");
|
||||
fprintf(stdout, " model path (default: %s)\n", params.model.c_str());
|
||||
|
|
@ -827,7 +830,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
|
|||
}
|
||||
}
|
||||
#else
|
||||
LOG_WARNING("llama.cpp was compiled without cuBLAS. It is not possible to set a tensor split.", {});
|
||||
LOG_WARNING("llama.cpp was compiled without cuBLAS. It is not possible to set a tensor split.\n", {});
|
||||
#endif // GGML_USE_CUBLAS
|
||||
}
|
||||
else if (arg == "--low-vram" || arg == "-lv")
|
||||
|
|
@ -835,7 +838,15 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
|
|||
#ifdef GGML_USE_CUBLAS
|
||||
params.low_vram = true;
|
||||
#else
|
||||
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. It is not possible to set lower vram usage.\n");
|
||||
LOG_WARNING("warning: llama.cpp was compiled without cuBLAS. It is not possible to set lower vram usage.\n", {});
|
||||
#endif // GGML_USE_CUBLAS
|
||||
}
|
||||
else if (arg == "--mul-mat-q" || arg == "-mmq")
|
||||
{
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
params.mul_mat_q = true;
|
||||
#else
|
||||
LOG_WARNING("warning: llama.cpp was compiled without cuBLAS. It is not possible to use mul_mat_q kernels.\n", {});
|
||||
#endif // GGML_USE_CUBLAS
|
||||
}
|
||||
else if (arg == "--main-gpu" || arg == "-mg")
|
||||
|
|
@ -1263,7 +1274,11 @@ int main(int argc, char **argv)
|
|||
sink.done();
|
||||
return true;
|
||||
};
|
||||
res.set_chunked_content_provider("text/event-stream", chunked_content_provider);
|
||||
const auto on_complete = [&](bool) {
|
||||
llama.mutex.unlock();
|
||||
};
|
||||
lock.release();
|
||||
res.set_chunked_content_provider("text/event-stream", chunked_content_provider, on_complete);
|
||||
} });
|
||||
|
||||
svr.Get("/model.json", [&llama](const Request &, Response &res)
|
||||
|
|
|
|||
|
|
@ -123,7 +123,7 @@ int main(int argc, char ** argv)
|
|||
// Evaluate the tokens :
|
||||
//---------------------------------
|
||||
|
||||
if ( llama_eval( ctx , tokens_list.data() , tokens_list.size() , llama_get_kv_cache_token_count( ctx ) , params.n_threads ) )
|
||||
if ( llama_eval( ctx , tokens_list.data() , int(tokens_list.size()) , llama_get_kv_cache_token_count( ctx ) , params.n_threads ) )
|
||||
{
|
||||
fprintf( stderr, "%s : failed to eval\n" , __func__ );
|
||||
return 1;
|
||||
|
|
|
|||
541
ggml-alloc.c
Normal file
541
ggml-alloc.c
Normal file
|
|
@ -0,0 +1,541 @@
|
|||
#include "ggml-alloc.h"
|
||||
#include "ggml.h"
|
||||
#include <assert.h>
|
||||
#include <stdarg.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
#define UNUSED(x) (void)(x)
|
||||
#define MAX(a, b) ((a) > (b) ? (a) : (b))
|
||||
|
||||
//#define GGML_ALLOCATOR_DEBUG
|
||||
|
||||
//#define AT_PRINTF printf
|
||||
#define AT_PRINTF(...) ((void)0)
|
||||
|
||||
struct hash_node {
|
||||
struct ggml_tensor * t;
|
||||
int n_children;
|
||||
int n_views;
|
||||
};
|
||||
|
||||
static size_t hash(void * p) {
|
||||
return (size_t)p % GGML_GRAPH_HASHTABLE_SIZE;
|
||||
}
|
||||
|
||||
static struct hash_node * hash_get(struct hash_node hash_table[], struct ggml_tensor * t) {
|
||||
size_t h = hash(t);
|
||||
|
||||
// linear probing
|
||||
size_t i = h;
|
||||
while (hash_table[i].t != NULL) {
|
||||
if (hash_table[i].t == t) {
|
||||
return &hash_table[i];
|
||||
}
|
||||
i = (i + 1) % GGML_GRAPH_HASHTABLE_SIZE;
|
||||
if (i == h) {
|
||||
// hash table is full
|
||||
GGML_ASSERT(false);
|
||||
}
|
||||
}
|
||||
|
||||
hash_table[i].t = t;
|
||||
return &hash_table[i];
|
||||
}
|
||||
|
||||
// TODO: GGML_PAD ?
|
||||
static size_t aligned_offset(const void * buffer, size_t offset, size_t alignment) {
|
||||
assert(alignment && !(alignment & (alignment - 1))); // power of 2
|
||||
size_t align = (alignment - (((uintptr_t)buffer + offset) % alignment)) % alignment;
|
||||
return offset + align;
|
||||
}
|
||||
|
||||
struct free_block {
|
||||
void * addr;
|
||||
size_t size;
|
||||
};
|
||||
|
||||
#define MAX_FREE_BLOCKS 128
|
||||
|
||||
struct ggml_allocr {
|
||||
void * data;
|
||||
size_t size;
|
||||
size_t alignment;
|
||||
int n_free_blocks;
|
||||
struct free_block free_blocks[MAX_FREE_BLOCKS];
|
||||
struct hash_node hash_table[GGML_GRAPH_HASHTABLE_SIZE];
|
||||
size_t max_size;
|
||||
bool measure;
|
||||
|
||||
#ifdef GGML_ALLOCATOR_DEBUG
|
||||
struct ggml_tensor * allocated_tensors[1024];
|
||||
#endif
|
||||
};
|
||||
|
||||
#ifdef GGML_ALLOCATOR_DEBUG
|
||||
static void add_allocated_tensor(struct ggml_allocator * alloc, struct ggml_tensor * tensor) {
|
||||
for (int i = 0; i < 1024; i++) {
|
||||
if (alloc->allocated_tensors[i] == NULL) {
|
||||
alloc->allocated_tensors[i] = tensor;
|
||||
return;
|
||||
}
|
||||
}
|
||||
GGML_ASSERT(!"out of allocated_tensors");
|
||||
}
|
||||
static void remove_allocated_tensor(struct ggml_allocator * alloc, struct ggml_tensor * tensor) {
|
||||
for (int i = 0; i < 1024; i++) {
|
||||
if (alloc->allocated_tensors[i] == tensor ||
|
||||
(alloc->allocated_tensors[i] != NULL && alloc->allocated_tensors[i]->data == tensor->data)) {
|
||||
alloc->allocated_tensors[i] = NULL;
|
||||
return;
|
||||
}
|
||||
}
|
||||
printf("tried to free tensor %s not found\n", tensor->name);
|
||||
GGML_ASSERT(!"tensor not found");
|
||||
}
|
||||
#endif
|
||||
|
||||
|
||||
static size_t ggml_allocator_get_alloc_size(struct ggml_allocr * alloc, struct ggml_tensor * tensor) {
|
||||
return ggml_nbytes(tensor);
|
||||
|
||||
UNUSED(alloc);
|
||||
}
|
||||
|
||||
void ggml_allocr_alloc(struct ggml_allocr * alloc, struct ggml_tensor * tensor) {
|
||||
size_t size = ggml_allocator_get_alloc_size(alloc, tensor);
|
||||
size = aligned_offset(NULL, size, alloc->alignment);
|
||||
|
||||
AT_PRINTF("%s: allocating %s (%zu bytes) - ", __func__, tensor->name, size);
|
||||
|
||||
size_t max_avail = 0;
|
||||
|
||||
// find the best fitting free block
|
||||
int best_fit_block = -1;
|
||||
size_t best_fit_size = SIZE_MAX;
|
||||
for (int i = 0; i < alloc->n_free_blocks; i++) {
|
||||
struct free_block * block = &alloc->free_blocks[i];
|
||||
max_avail = MAX(max_avail, block->size);
|
||||
if (block->size >= size && block->size <= best_fit_size) {
|
||||
best_fit_block = i;
|
||||
best_fit_size = block->size;
|
||||
}
|
||||
}
|
||||
|
||||
AT_PRINTF("block %d\n", best_fit_block);
|
||||
|
||||
if (best_fit_block == -1) {
|
||||
fprintf(stderr, "%s: not enough space in the buffer (needed %zu, largest block available %zu)\n",
|
||||
__func__, size, max_avail);
|
||||
GGML_ASSERT(!"not enough space in the buffer");
|
||||
return;
|
||||
}
|
||||
struct free_block * block = &alloc->free_blocks[best_fit_block];
|
||||
void * addr = block->addr;
|
||||
block->addr = (char*)block->addr + size;
|
||||
block->size -= size;
|
||||
if (block->size == 0) {
|
||||
// remove block if empty
|
||||
alloc->n_free_blocks--;
|
||||
for (int j = best_fit_block; j < alloc->n_free_blocks; j++) {
|
||||
alloc->free_blocks[j] = alloc->free_blocks[j+1];
|
||||
}
|
||||
}
|
||||
|
||||
tensor->data = addr;
|
||||
|
||||
#ifdef GGML_ALLOCATOR_DEBUG
|
||||
add_allocated_tensor(alloc, tensor);
|
||||
size_t cur_max = (char*)addr - (char*)alloc->data + size;
|
||||
if (cur_max > alloc->max_size) {
|
||||
printf("max_size = %.2f MB: tensors: ", cur_max / 1024.0 / 1024.0);
|
||||
for (int i = 0; i < 1024; i++) {
|
||||
if (alloc->allocated_tensors[i]) {
|
||||
printf("%s (%.2f MB) ", alloc->allocated_tensors[i]->name, ggml_nbytes(alloc->allocated_tensors[i]) / 1024.0 / 1024.0);
|
||||
}
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
#endif
|
||||
|
||||
alloc->max_size = MAX(alloc->max_size, (char*)addr - (char*)alloc->data + size);
|
||||
}
|
||||
|
||||
// this is a very naive implementation, but for our case the number of free blocks should be very small
|
||||
static void ggml_allocator_free_tensor(struct ggml_allocr * alloc, struct ggml_tensor * tensor) {
|
||||
void * ptr = tensor->data;
|
||||
|
||||
if (ptr < alloc->data || (char*)ptr >= (char*)alloc->data + alloc->max_size) {
|
||||
// the tensor was not allocated in this buffer
|
||||
// this can happen because the graph allocator will try to free weights and other tensors from different buffers
|
||||
// the easiest way to deal with this is just to ignore it
|
||||
return;
|
||||
}
|
||||
|
||||
size_t size = ggml_allocator_get_alloc_size(alloc, tensor);
|
||||
size = aligned_offset(NULL, size, alloc->alignment);
|
||||
AT_PRINTF("%s: freeing %s (%zu bytes) - n_free_blocks = %d\n", __func__, tensor->name, size, alloc->n_free_blocks);
|
||||
|
||||
#ifdef GGML_ALLOCATOR_DEBUG
|
||||
remove_allocated_tensor(alloc, tensor);
|
||||
#endif
|
||||
|
||||
// see if we can merge with an existing block
|
||||
for (int i = 0; i < alloc->n_free_blocks; i++) {
|
||||
struct free_block * block = &alloc->free_blocks[i];
|
||||
// check if ptr is at the end of the block
|
||||
if ((char*)block->addr + block->size == ptr) {
|
||||
block->size += size;
|
||||
// check if we can merge with the next block
|
||||
if (i < alloc->n_free_blocks - 1 && (char*)block->addr + block->size == alloc->free_blocks[i+1].addr) {
|
||||
block->size += alloc->free_blocks[i+1].size;
|
||||
alloc->n_free_blocks--;
|
||||
for (int j = i+1; j < alloc->n_free_blocks; j++) {
|
||||
alloc->free_blocks[j] = alloc->free_blocks[j+1];
|
||||
}
|
||||
}
|
||||
return;
|
||||
}
|
||||
// check if ptr is at the beginning of the block
|
||||
if ((char*)ptr + size == block->addr) {
|
||||
block->addr = ptr;
|
||||
block->size += size;
|
||||
// check if we can merge with the previous block
|
||||
if (i > 0 && (char*)alloc->free_blocks[i-1].addr + alloc->free_blocks[i-1].size == block->addr) {
|
||||
alloc->free_blocks[i-1].size += block->size;
|
||||
alloc->n_free_blocks--;
|
||||
for (int j = i; j < alloc->n_free_blocks; j++) {
|
||||
alloc->free_blocks[j] = alloc->free_blocks[j+1];
|
||||
}
|
||||
}
|
||||
return;
|
||||
}
|
||||
}
|
||||
// otherwise, add a new block
|
||||
GGML_ASSERT(alloc->n_free_blocks < MAX_FREE_BLOCKS && "out of free blocks");
|
||||
// insert the new block in the correct position to keep the array sorted by address (to make merging blocks faster)
|
||||
int insert_pos = 0;
|
||||
while (insert_pos < alloc->n_free_blocks && alloc->free_blocks[insert_pos].addr < ptr) {
|
||||
insert_pos++;
|
||||
}
|
||||
// shift all blocks from insert_pos onward to make room for the new block
|
||||
for (int i = alloc->n_free_blocks; i > insert_pos; i--) {
|
||||
alloc->free_blocks[i] = alloc->free_blocks[i-1];
|
||||
}
|
||||
// insert the new block
|
||||
alloc->free_blocks[insert_pos].addr = ptr;
|
||||
alloc->free_blocks[insert_pos].size = size;
|
||||
alloc->n_free_blocks++;
|
||||
}
|
||||
|
||||
void ggml_allocr_reset(struct ggml_allocr * alloc) {
|
||||
alloc->n_free_blocks = 1;
|
||||
size_t align_offset = aligned_offset(alloc->data, 0, alloc->alignment);
|
||||
alloc->free_blocks[0].addr = (char *)alloc->data + align_offset;
|
||||
alloc->free_blocks[0].size = alloc->size - align_offset;
|
||||
}
|
||||
|
||||
struct ggml_allocr * ggml_allocr_new(void * data, size_t size, size_t alignment) {
|
||||
struct ggml_allocr * alloc = (struct ggml_allocr *)malloc(sizeof(struct ggml_allocr) /* + n_free_blocks * sizeof(struct free_block) */);
|
||||
|
||||
*alloc = (struct ggml_allocr){
|
||||
/*.data = */ data,
|
||||
/*.size = */ size,
|
||||
/*.alignment = */ alignment,
|
||||
/*.n_free_blocks = */ 0,
|
||||
/*.free_blocks = */ {{0}},
|
||||
/*.hash_table = */ {{0}},
|
||||
/*.max_size = */ 0,
|
||||
/*.measure = */ false,
|
||||
#ifdef GGML_ALLOCATOR_DEBUG
|
||||
/*.allocated_tensors = */ = {0},
|
||||
#endif
|
||||
};
|
||||
|
||||
ggml_allocr_reset(alloc);
|
||||
|
||||
return alloc;
|
||||
}
|
||||
|
||||
// address and size of the buffer when measuring
|
||||
// it needs to be large enough to fit all the tensors, but it cannot overlap with other existing buffers
|
||||
static void * const MEASURE_BASE_ADDR = (void *) 0x1000;
|
||||
static const size_t MEASURE_MAX_SIZE = 1ULL<<40; // 1 TB
|
||||
|
||||
struct ggml_allocr * ggml_allocr_new_measure(size_t alignment) {
|
||||
struct ggml_allocr * alloc = (struct ggml_allocr *)malloc(sizeof(struct ggml_allocr) /* + n_free_blocks * sizeof(struct free_block) */);
|
||||
|
||||
*alloc = (struct ggml_allocr){
|
||||
/*.data = */ MEASURE_BASE_ADDR,
|
||||
/*.size = */ MEASURE_MAX_SIZE,
|
||||
/*.alignment = */ alignment,
|
||||
/*.n_free_blocks = */ 0,
|
||||
/*.free_blocks = */ {{0}},
|
||||
/*.hash_table = */ {{0}},
|
||||
/*.max_size = */ 0,
|
||||
/*.measure = */ true,
|
||||
#ifdef GGML_ALLOCATOR_DEBUG
|
||||
/*.allocated_tensors = */ = {0},
|
||||
#endif
|
||||
};
|
||||
|
||||
ggml_allocr_reset(alloc);
|
||||
|
||||
return alloc;
|
||||
}
|
||||
|
||||
void ggml_allocr_free(struct ggml_allocr * alloc) {
|
||||
free(alloc);
|
||||
}
|
||||
|
||||
bool ggml_allocr_is_measure(struct ggml_allocr * alloc) {
|
||||
return alloc->measure;
|
||||
}
|
||||
|
||||
//////////// compute graph allocator
|
||||
|
||||
static bool ggml_is_view(struct ggml_tensor * t) {
|
||||
return t->op == GGML_OP_RESHAPE || t->op == GGML_OP_VIEW || t->op == GGML_OP_TRANSPOSE ||
|
||||
t->op == GGML_OP_PERMUTE || t->op == GGML_OP_CPY;
|
||||
}
|
||||
|
||||
static bool ggml_are_same_layout(const struct ggml_tensor * a, const struct ggml_tensor * b) {
|
||||
if (a->type != b->type) {
|
||||
return false;
|
||||
}
|
||||
for (int i = 0; i < GGML_MAX_DIMS; i++) {
|
||||
if (a->ne[i] != b->ne[i]) {
|
||||
return false;
|
||||
}
|
||||
if (a->nb[i] != b->nb[i]) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
static struct ggml_tensor * get_view_parent(struct ggml_tensor * t) {
|
||||
switch (t->op) {
|
||||
case GGML_OP_PERMUTE:
|
||||
case GGML_OP_RESHAPE:
|
||||
case GGML_OP_TRANSPOSE:
|
||||
case GGML_OP_VIEW:
|
||||
return t->src[0];
|
||||
case GGML_OP_CPY:
|
||||
return t->src[1];
|
||||
default:
|
||||
return NULL;
|
||||
}
|
||||
}
|
||||
|
||||
static struct ggml_tensor * get_view_source(struct ggml_tensor * t) {
|
||||
struct ggml_tensor * parent = t;
|
||||
do {
|
||||
parent = get_view_parent(parent);
|
||||
} while (ggml_is_view(parent));
|
||||
return parent;
|
||||
}
|
||||
|
||||
static bool ggml_op_can_inplace(enum ggml_op op) {
|
||||
switch (op) {
|
||||
case GGML_OP_SCALE:
|
||||
case GGML_OP_DIAG_MASK_ZERO:
|
||||
case GGML_OP_DIAG_MASK_INF:
|
||||
case GGML_OP_ADD:
|
||||
case GGML_OP_ADD1:
|
||||
case GGML_OP_ACC:
|
||||
case GGML_OP_SUB:
|
||||
case GGML_OP_MUL:
|
||||
case GGML_OP_DIV:
|
||||
case GGML_OP_SQR:
|
||||
case GGML_OP_SQRT:
|
||||
case GGML_OP_LOG:
|
||||
case GGML_OP_UNARY:
|
||||
case GGML_OP_ROPE:
|
||||
case GGML_OP_RMS_NORM:
|
||||
case GGML_OP_SET:
|
||||
case GGML_OP_SOFT_MAX:
|
||||
case GGML_OP_CONT:
|
||||
return true;
|
||||
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
static void allocate_node(struct ggml_allocr * alloc, struct ggml_tensor * node) {
|
||||
struct hash_node * ht = alloc->hash_table;
|
||||
if (node->data == NULL) {
|
||||
if (ggml_is_view(node)) {
|
||||
size_t offset;
|
||||
switch(node->op) {
|
||||
case GGML_OP_VIEW:
|
||||
memcpy(&offset, node->op_params, sizeof(size_t));
|
||||
node->data = (char *) node->src[0]->data + offset;
|
||||
break;
|
||||
case GGML_OP_PERMUTE:
|
||||
case GGML_OP_RESHAPE:
|
||||
case GGML_OP_TRANSPOSE:
|
||||
node->data = node->src[0]->data;
|
||||
break;
|
||||
case GGML_OP_CPY:
|
||||
node->data = node->src[1]->data;
|
||||
break;
|
||||
default:
|
||||
GGML_ASSERT(!"unknown view op");
|
||||
break;
|
||||
}
|
||||
} else {
|
||||
// see if we can reuse a parent's buffer (inplace)
|
||||
if (ggml_op_can_inplace(node->op)) {
|
||||
for (int i = 0; i < GGML_MAX_SRC; i++) {
|
||||
struct ggml_tensor * parent = node->src[i];
|
||||
if (parent == NULL) {
|
||||
break;
|
||||
}
|
||||
struct hash_node * p_hn = hash_get(ht, parent);
|
||||
if (parent->data != NULL && p_hn->n_children == 1 && p_hn->n_views == 0 && ggml_are_same_layout(node, parent)) {
|
||||
if (ggml_is_view(parent)) {
|
||||
struct ggml_tensor * view_src = get_view_source(parent);
|
||||
struct hash_node * view_src_hn = hash_get(ht, view_src);
|
||||
if (view_src_hn->n_views == 1 && view_src_hn->n_children == 0 && view_src->data == parent->data) {
|
||||
// TODO: the offset of the view parent must be kept to ensure that the op doesn't overwrite
|
||||
// the parent's data that it will need later (same layout requirement). the problem is that then
|
||||
// we cannot free the tensor because the original address of the allocation is lost.
|
||||
// adding a view_src pointer to the tensor would solve this and simplify the code dealing with views
|
||||
// for now, we only reuse the parent's data if the offset is zero (view_src->data == parent->data)
|
||||
AT_PRINTF("reusing view parent %s (%s) for %s\n", parent->name, view_src->name, node->name);
|
||||
node->data = parent->data;
|
||||
return;
|
||||
}
|
||||
}
|
||||
else {
|
||||
AT_PRINTF("reusing parent %s for %s\n", parent->name, node->name);
|
||||
node->data = parent->data;
|
||||
}
|
||||
return;
|
||||
}
|
||||
}
|
||||
}
|
||||
ggml_allocr_alloc(alloc, node);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static size_t ggml_allocator_alloc_graph_tensors_n(
|
||||
struct ggml_allocr * alloc,
|
||||
struct ggml_cgraph ** graphs, int n_graphs,
|
||||
struct ggml_tensor *** inputs, struct ggml_tensor *** outputs) {
|
||||
|
||||
// reset hash table
|
||||
struct hash_node * ht = alloc->hash_table;
|
||||
memset(ht, 0, sizeof(struct hash_node) * GGML_GRAPH_HASHTABLE_SIZE);
|
||||
|
||||
// count number of children and views
|
||||
for (int g = 0; g < n_graphs; g++) {
|
||||
struct ggml_cgraph * gf = graphs[g];
|
||||
for (int i = 0; i < gf->n_nodes; i++) {
|
||||
struct ggml_tensor * node = gf->nodes[i];
|
||||
|
||||
if (ggml_is_view(node)) {
|
||||
struct ggml_tensor * view_src = get_view_source(node);
|
||||
hash_get(ht, view_src)->n_views += 1;
|
||||
}
|
||||
|
||||
for (int j = 0; j < GGML_MAX_SRC; j++) {
|
||||
struct ggml_tensor * parent = node->src[j];
|
||||
if (parent == NULL) {
|
||||
break;
|
||||
}
|
||||
hash_get(ht, parent)->n_children += 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// allocate tensors
|
||||
for (int g = 0; g < n_graphs; g++) {
|
||||
struct ggml_cgraph * gf = graphs[g];
|
||||
AT_PRINTF("####### graph %d/%d\n", g, n_graphs);
|
||||
// graph inputs are allocated first to ensure that they are not overwritten by each other
|
||||
if (inputs != NULL && inputs[g] != NULL) {
|
||||
for (int i = 0; inputs[g][i] != NULL; i++) {
|
||||
struct ggml_tensor * input = inputs[g][i];
|
||||
AT_PRINTF("input: %s\n", input->name);
|
||||
allocate_node(alloc, input);
|
||||
}
|
||||
}
|
||||
for (int i = 0; i < gf->n_nodes; i++) {
|
||||
struct ggml_tensor * node = gf->nodes[i];
|
||||
|
||||
// allocate parents (leafs)
|
||||
for (int j = 0; j < GGML_MAX_SRC; j++) {
|
||||
struct ggml_tensor * parent = node->src[j];
|
||||
if (parent == NULL) {
|
||||
break;
|
||||
}
|
||||
allocate_node(alloc, parent);
|
||||
}
|
||||
|
||||
// allocate node
|
||||
allocate_node(alloc, node);
|
||||
|
||||
AT_PRINTF("exec: %s (%s) <= ", ggml_op_name(node->op), node->name);
|
||||
for (int j = 0; j < GGML_MAX_SRC; j++) {
|
||||
struct ggml_tensor * parent = node->src[j];
|
||||
if (parent == NULL) {
|
||||
break;
|
||||
}
|
||||
AT_PRINTF("%s", parent->name);
|
||||
if (j < GGML_MAX_SRC - 1 && node->src[j + 1] != NULL) {
|
||||
AT_PRINTF(", ");
|
||||
}
|
||||
}
|
||||
AT_PRINTF("\n");
|
||||
|
||||
// update parents
|
||||
for (int j = 0; j < GGML_MAX_SRC; j++) {
|
||||
struct ggml_tensor * parent = node->src[j];
|
||||
if (parent == NULL) {
|
||||
break;
|
||||
}
|
||||
struct hash_node * p_hn = hash_get(ht, parent);
|
||||
p_hn->n_children -= 1;
|
||||
|
||||
//AT_PRINTF("parent %s: %d children, %d views\n", parent->name, parent->n_children, parent->n_views);
|
||||
|
||||
if (p_hn->n_children == 0 && p_hn->n_views == 0) {
|
||||
if (ggml_is_view(parent)) {
|
||||
struct ggml_tensor * view_src = get_view_source(parent);
|
||||
struct hash_node * view_src_hn = hash_get(ht, view_src);
|
||||
view_src_hn->n_views -= 1;
|
||||
AT_PRINTF("view_src %s: %d children, %d views\n", view_src->name, view_src->n_children, view_src->n_views);
|
||||
if (view_src_hn->n_views == 0 && view_src_hn->n_children == 0 && view_src->data != node->data) {
|
||||
ggml_allocator_free_tensor(alloc, view_src);
|
||||
}
|
||||
}
|
||||
else {
|
||||
if (parent->data != node->data) {
|
||||
ggml_allocator_free_tensor(alloc, parent);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
AT_PRINTF("\n");
|
||||
}
|
||||
// free graph outputs here that wouldn't be freed otherwise because they have no children
|
||||
if (outputs != NULL && outputs[g] != NULL) {
|
||||
for (int i = 0; outputs[g][i] != NULL; i++) {
|
||||
struct ggml_tensor * output = outputs[g][i];
|
||||
AT_PRINTF("output: %s\n", output->name);
|
||||
ggml_allocator_free_tensor(alloc, output);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return alloc->max_size;
|
||||
}
|
||||
|
||||
size_t ggml_allocr_alloc_graph(struct ggml_allocr * alloc, struct ggml_cgraph * graph) {
|
||||
return ggml_allocator_alloc_graph_tensors_n(alloc, &graph, 1, NULL, NULL);
|
||||
}
|
||||
22
ggml-alloc.h
Normal file
22
ggml-alloc.h
Normal file
|
|
@ -0,0 +1,22 @@
|
|||
#pragma once
|
||||
|
||||
#include "ggml.h"
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
|
||||
GGML_API struct ggml_allocr * ggml_allocr_new(void * data, size_t size, size_t alignment);
|
||||
GGML_API struct ggml_allocr * ggml_allocr_new_measure(size_t alignment);
|
||||
|
||||
GGML_API void ggml_allocr_free(struct ggml_allocr * alloc);
|
||||
GGML_API bool ggml_allocr_is_measure(struct ggml_allocr * alloc);
|
||||
GGML_API void ggml_allocr_reset(struct ggml_allocr * alloc);
|
||||
GGML_API void ggml_allocr_alloc(struct ggml_allocr * alloc, struct ggml_tensor * tensor);
|
||||
GGML_API size_t ggml_allocr_alloc_graph(struct ggml_allocr * alloc, struct ggml_cgraph * graph);
|
||||
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
2502
ggml-cuda.cu
2502
ggml-cuda.cu
File diff suppressed because it is too large
Load diff
|
|
@ -27,6 +27,7 @@ void ggml_cuda_assign_buffers(struct ggml_tensor * tensor);
|
|||
void ggml_cuda_assign_buffers_no_scratch(struct ggml_tensor * tensor);
|
||||
void ggml_cuda_assign_buffers_force_inplace(struct ggml_tensor * tensor);
|
||||
void ggml_cuda_set_main_device(int main_device);
|
||||
void ggml_cuda_set_mul_mat_q(bool mul_mat_q);
|
||||
void ggml_cuda_set_scratch_size(size_t scratch_size);
|
||||
void ggml_cuda_free_scratch(void);
|
||||
bool ggml_cuda_compute_forward(struct ggml_compute_params * params, struct ggml_tensor * tensor);
|
||||
|
|
|
|||
33
ggml-metal.m
33
ggml-metal.m
|
|
@ -718,7 +718,8 @@ void ggml_metal_graph_compute(
|
|||
// TODO: needs to be updated after PR: https://github.com/ggerganov/ggml/pull/224
|
||||
|
||||
GGML_ASSERT(ne00 == ne10);
|
||||
GGML_ASSERT(ne02 == ne12);
|
||||
// GGML_ASSERT(ne02 == ne12); // Should be checked on individual data types until broadcast is implemented everywhere
|
||||
GGML_ASSERT(ne03 == ne13);
|
||||
|
||||
if (ggml_is_contiguous(src0) &&
|
||||
ggml_is_contiguous(src1) &&
|
||||
|
|
@ -746,11 +747,11 @@ void ggml_metal_graph_compute(
|
|||
initWithDevice:ctx->device transposeLeft:false transposeRight:true
|
||||
resultRows:ne11 resultColumns:ne01 interiorColumns:ne00 alpha:1.0 beta:0.0];
|
||||
|
||||
// we need to do ne02 multiplications
|
||||
// we need to do ne12 multiplications
|
||||
// TODO: is there a way to do this in parallel - currently very slow ..
|
||||
// TODO: might be possible to offload part of the computation to ANE using Accelerate's CBLAS
|
||||
for (int64_t i02 = 0; i02 < ne02; ++i02) {
|
||||
size_t offs_src0_cur = offs_src0 + i02*nb02;
|
||||
for (int64_t i02 = 0; i02 < ne12; ++i02) {
|
||||
size_t offs_src0_cur = offs_src0 + i02/(ne12/ne02)*nb02; // gqa not used for now
|
||||
size_t offs_src1_cur = offs_src1 + i02*nb12;
|
||||
size_t offs_dst_cur = offs_dst + i02*nb2;
|
||||
|
||||
|
|
@ -772,8 +773,6 @@ void ggml_metal_graph_compute(
|
|||
switch (src0t) {
|
||||
case GGML_TYPE_F16:
|
||||
{
|
||||
GGML_ASSERT(ne02 == ne12);
|
||||
|
||||
nth0 = 64;
|
||||
nth1 = 1;
|
||||
[encoder setComputePipelineState:ctx->pipeline_mul_mat_f16_f32];
|
||||
|
|
@ -853,16 +852,18 @@ void ggml_metal_graph_compute(
|
|||
[encoder setBuffer:id_dst offset:offs_dst atIndex:2];
|
||||
[encoder setBytes:&ne00 length:sizeof(ne00) atIndex:3];
|
||||
[encoder setBytes:&ne01 length:sizeof(ne01) atIndex:4];
|
||||
[encoder setBytes:&nb00 length:sizeof(nb00) atIndex:5];
|
||||
[encoder setBytes:&nb01 length:sizeof(nb01) atIndex:6];
|
||||
[encoder setBytes:&nb02 length:sizeof(nb02) atIndex:7];
|
||||
[encoder setBytes:&ne10 length:sizeof(ne10) atIndex:8];
|
||||
[encoder setBytes:&ne11 length:sizeof(ne11) atIndex:9];
|
||||
[encoder setBytes:&nb10 length:sizeof(nb10) atIndex:10];
|
||||
[encoder setBytes:&nb11 length:sizeof(nb11) atIndex:11];
|
||||
[encoder setBytes:&nb12 length:sizeof(nb12) atIndex:12];
|
||||
[encoder setBytes:&ne0 length:sizeof(ne0) atIndex:13];
|
||||
[encoder setBytes:&ne1 length:sizeof(ne1) atIndex:14];
|
||||
[encoder setBytes:&ne02 length:sizeof(ne02) atIndex:5];
|
||||
[encoder setBytes:&nb00 length:sizeof(nb00) atIndex:6];
|
||||
[encoder setBytes:&nb01 length:sizeof(nb01) atIndex:7];
|
||||
[encoder setBytes:&nb02 length:sizeof(nb02) atIndex:8];
|
||||
[encoder setBytes:&ne10 length:sizeof(ne10) atIndex:9];
|
||||
[encoder setBytes:&ne11 length:sizeof(ne11) atIndex:10];
|
||||
[encoder setBytes:&ne12 length:sizeof(ne12) atIndex:11];
|
||||
[encoder setBytes:&nb10 length:sizeof(nb10) atIndex:12];
|
||||
[encoder setBytes:&nb11 length:sizeof(nb11) atIndex:13];
|
||||
[encoder setBytes:&nb12 length:sizeof(nb12) atIndex:14];
|
||||
[encoder setBytes:&ne0 length:sizeof(ne0) atIndex:15];
|
||||
[encoder setBytes:&ne1 length:sizeof(ne1) atIndex:16];
|
||||
|
||||
if (src0t == GGML_TYPE_Q4_0 || src0t == GGML_TYPE_Q4_1 ||
|
||||
src0t == GGML_TYPE_Q2_K || src0t == GGML_TYPE_Q4_K) {
|
||||
|
|
|
|||
|
|
@ -509,11 +509,13 @@ kernel void kernel_mul_mat_f16_f32(
|
|||
device float * dst,
|
||||
constant int64_t & ne00,
|
||||
constant int64_t & ne01,
|
||||
constant int64_t & ne02,
|
||||
constant uint64_t & nb00,
|
||||
constant uint64_t & nb01,
|
||||
constant uint64_t & nb02,
|
||||
constant int64_t & ne10,
|
||||
constant int64_t & ne11,
|
||||
constant int64_t & ne12,
|
||||
constant uint64_t & nb10,
|
||||
constant uint64_t & nb11,
|
||||
constant uint64_t & nb12,
|
||||
|
|
@ -529,7 +531,7 @@ kernel void kernel_mul_mat_f16_f32(
|
|||
const int64_t r1 = tgpig.y;
|
||||
const int64_t im = tgpig.z;
|
||||
|
||||
device const half * x = (device const half *) (src0 + r0*nb01 + im*nb02);
|
||||
device const half * x = (device const half *) (src0 + r0*nb01 + im/(ne12/ne02)*nb02);
|
||||
device const float * y = (device const float *) (src1 + r1*nb11 + im*nb12);
|
||||
|
||||
sum[tpitg.x] = 0.0f;
|
||||
|
|
@ -552,6 +554,7 @@ kernel void kernel_mul_mat_f16_f32(
|
|||
}
|
||||
}
|
||||
|
||||
|
||||
kernel void kernel_alibi_f32(
|
||||
device const float * src0,
|
||||
device float * dst,
|
||||
|
|
|
|||
55
ggml.c
55
ggml.c
|
|
@ -4564,6 +4564,8 @@ static struct ggml_tensor * ggml_new_tensor_impl(
|
|||
const int64_t * ne,
|
||||
void * data) {
|
||||
|
||||
assert(n_dims >= 1 && n_dims <= GGML_MAX_DIMS);
|
||||
|
||||
size_t data_size = 0;
|
||||
|
||||
if (data == NULL && !ctx->no_alloc) {
|
||||
|
|
@ -6243,6 +6245,27 @@ struct ggml_tensor * ggml_reshape_4d(
|
|||
|
||||
// ggml_view_1d
|
||||
|
||||
static struct ggml_tensor * ggml_view_tensor_offset(
|
||||
struct ggml_context * ctx,
|
||||
struct ggml_tensor * a,
|
||||
int n_dims,
|
||||
const int64_t * ne,
|
||||
size_t offset) {
|
||||
// don't calculate an offset from an unallocated tensor
|
||||
void * data = NULL;
|
||||
if (a->data != NULL) {
|
||||
data = (char *) a->data + offset;
|
||||
}
|
||||
|
||||
struct ggml_tensor * result = ggml_new_tensor_impl(ctx, a->type, n_dims, ne, data);
|
||||
|
||||
ggml_format_name(result, "%s (view)", a->name);
|
||||
|
||||
ggml_set_op_params(result, &offset, sizeof(offset));
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
struct ggml_tensor * ggml_view_1d(
|
||||
struct ggml_context * ctx,
|
||||
struct ggml_tensor * a,
|
||||
|
|
@ -6255,10 +6278,7 @@ struct ggml_tensor * ggml_view_1d(
|
|||
is_node = true;
|
||||
}
|
||||
|
||||
struct ggml_tensor * result = ggml_new_tensor_impl(ctx, a->type, 1, &ne0, (char *) a->data + offset);
|
||||
ggml_format_name(result, "%s (view)", a->name);
|
||||
|
||||
ggml_set_op_params(result, &offset, sizeof(offset));
|
||||
struct ggml_tensor * result = ggml_view_tensor_offset(ctx, a, 1, &ne0, offset);
|
||||
|
||||
result->op = GGML_OP_VIEW;
|
||||
result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL;
|
||||
|
|
@ -6285,10 +6305,7 @@ struct ggml_tensor * ggml_view_2d(
|
|||
|
||||
const int64_t ne[GGML_MAX_DIMS] = { ne0, ne1, 1, 1 };
|
||||
|
||||
struct ggml_tensor * result = ggml_new_tensor_impl(ctx, a->type, 2, ne, (char *) a->data + offset);
|
||||
ggml_format_name(result, "%s (view)", a->name);
|
||||
|
||||
ggml_set_op_params(result, &offset, sizeof(offset));
|
||||
struct ggml_tensor * result = ggml_view_tensor_offset(ctx, a, 2, ne, offset);
|
||||
|
||||
result->nb[1] = nb1;
|
||||
result->nb[2] = result->nb[1]*ne1;
|
||||
|
|
@ -6321,10 +6338,7 @@ struct ggml_tensor * ggml_view_3d(
|
|||
|
||||
const int64_t ne[GGML_MAX_DIMS] = { ne0, ne1, ne2, 1 };
|
||||
|
||||
struct ggml_tensor * result = ggml_new_tensor_impl(ctx, a->type, 3, ne, (char *) a->data + offset);
|
||||
ggml_format_name(result, "%s (view)", a->name);
|
||||
|
||||
ggml_set_op_params(result, &offset, sizeof(offset));
|
||||
struct ggml_tensor * result = ggml_view_tensor_offset(ctx, a, 3, ne, offset);
|
||||
|
||||
result->nb[1] = nb1;
|
||||
result->nb[2] = nb2;
|
||||
|
|
@ -6359,10 +6373,7 @@ struct ggml_tensor * ggml_view_4d(
|
|||
|
||||
const int64_t ne[GGML_MAX_DIMS] = { ne0, ne1, ne2, ne3 };
|
||||
|
||||
struct ggml_tensor * result = ggml_new_tensor_impl(ctx, a->type, 4, ne, (char *) a->data + offset);
|
||||
ggml_format_name(result, "%s (view)", a->name);
|
||||
|
||||
ggml_set_op_params(result, &offset, sizeof(offset));
|
||||
struct ggml_tensor * result = ggml_view_tensor_offset(ctx, a, 4, ne, offset);
|
||||
|
||||
result->nb[1] = nb1;
|
||||
result->nb[2] = nb2;
|
||||
|
|
@ -6746,6 +6757,18 @@ struct ggml_tensor * ggml_rope_inplace(
|
|||
return ggml_rope_impl(ctx, a, n_past, n_dims, mode, n_ctx, 10000.0f, 1.0f, true);
|
||||
}
|
||||
|
||||
struct ggml_tensor * ggml_rope_custom(
|
||||
struct ggml_context * ctx,
|
||||
struct ggml_tensor * a,
|
||||
int n_past,
|
||||
int n_dims,
|
||||
int mode,
|
||||
int n_ctx,
|
||||
float freq_base,
|
||||
float freq_scale) {
|
||||
return ggml_rope_impl(ctx, a, n_past, n_dims, mode, n_ctx, freq_base, freq_scale, false);
|
||||
}
|
||||
|
||||
struct ggml_tensor * ggml_rope_custom_inplace(
|
||||
struct ggml_context * ctx,
|
||||
struct ggml_tensor * a,
|
||||
|
|
|
|||
13
ggml.h
13
ggml.h
|
|
@ -1170,7 +1170,18 @@ extern "C" {
|
|||
int mode,
|
||||
int n_ctx);
|
||||
|
||||
// custom RoPE, in-place, returns view(a)
|
||||
// custom RoPE
|
||||
GGML_API struct ggml_tensor * ggml_rope_custom(
|
||||
struct ggml_context * ctx,
|
||||
struct ggml_tensor * a,
|
||||
int n_past,
|
||||
int n_dims,
|
||||
int mode,
|
||||
int n_ctx,
|
||||
float freq_base,
|
||||
float freq_scale);
|
||||
|
||||
// in-place, returns view(a)
|
||||
GGML_API struct ggml_tensor * ggml_rope_custom_inplace(
|
||||
struct ggml_context * ctx,
|
||||
struct ggml_tensor * a,
|
||||
|
|
|
|||
|
|
@ -1,19 +1,17 @@
|
|||
# Grammar for subset of JSON - doesn't support full string or number syntax
|
||||
|
||||
root ::= object
|
||||
value ::= object | array | string | number | boolean | "null"
|
||||
value ::= object | array | string | number | ("true" | "false" | "null") ws
|
||||
|
||||
object ::=
|
||||
"{" ws (
|
||||
string ":" ws value
|
||||
("," ws string ":" ws value)*
|
||||
)? "}"
|
||||
)? "}" ws
|
||||
|
||||
array ::=
|
||||
"[" ws (
|
||||
value
|
||||
("," ws value)*
|
||||
)? "]"
|
||||
)? "]" ws
|
||||
|
||||
string ::=
|
||||
"\"" (
|
||||
|
|
@ -21,9 +19,7 @@ string ::=
|
|||
"\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]) # escapes
|
||||
)* "\"" ws
|
||||
|
||||
# Only plain integers currently
|
||||
number ::= "-"? [0-9]+ ws
|
||||
boolean ::= ("true" | "false") ws
|
||||
number ::= ("-"? ([0-9] | [1-9] [0-9]*)) ("." [0-9]+)? ([eE] [-+]? [0-9]+)? ws
|
||||
|
||||
# Optional space: by convention, applied in this grammar after literal chars when allowed
|
||||
ws ::= ([ \t\n] ws)?
|
||||
|
|
|
|||
40
llama-util.h
40
llama-util.h
|
|
@ -149,6 +149,46 @@ struct llama_file {
|
|||
}
|
||||
};
|
||||
|
||||
// llama_context_data
|
||||
struct llama_data_context {
|
||||
virtual void write(const void * src, size_t size) = 0;
|
||||
virtual size_t get_size_written() = 0;
|
||||
virtual ~llama_data_context() = default;
|
||||
};
|
||||
|
||||
struct llama_data_buffer_context : llama_data_context {
|
||||
uint8_t* ptr;
|
||||
size_t size_written = 0;
|
||||
|
||||
llama_data_buffer_context(uint8_t * p) : ptr(p) {}
|
||||
|
||||
void write(const void * src, size_t size) override {
|
||||
memcpy(ptr, src, size);
|
||||
ptr += size;
|
||||
size_written += size;
|
||||
}
|
||||
|
||||
size_t get_size_written() override {
|
||||
return size_written;
|
||||
}
|
||||
};
|
||||
|
||||
struct llama_data_file_context : llama_data_context {
|
||||
llama_file* file;
|
||||
size_t size_written = 0;
|
||||
|
||||
llama_data_file_context(llama_file * f) : file(f) {}
|
||||
|
||||
void write(const void * src, size_t size) override {
|
||||
file->write_raw(src, size);
|
||||
size_written += size;
|
||||
}
|
||||
|
||||
size_t get_size_written() override {
|
||||
return size_written;
|
||||
}
|
||||
};
|
||||
|
||||
#if defined(_WIN32)
|
||||
static std::string llama_format_win_err(DWORD err) {
|
||||
LPSTR buf;
|
||||
|
|
|
|||
338
llama.cpp
338
llama.cpp
|
|
@ -56,8 +56,14 @@
|
|||
#pragma warning(disable: 4244 4267) // possible loss of data
|
||||
#endif
|
||||
|
||||
#if !defined(GGML_USE_CUBLAS) && !defined(GGML_USE_METAL)
|
||||
#include "ggml-alloc.h"
|
||||
#define LLAMA_USE_ALLOCATOR
|
||||
#else
|
||||
#define LLAMA_USE_SCRATCH
|
||||
#define LLAMA_MAX_SCRATCH_BUFFERS 16
|
||||
#endif
|
||||
|
||||
|
||||
// available llama models
|
||||
enum e_model {
|
||||
|
|
@ -327,13 +333,22 @@ struct llama_model {
|
|||
|
||||
struct llama_context {
|
||||
llama_context(const llama_model & model) : model(model), t_load_us(model.t_load_us), t_start_us(model.t_start_us) {}
|
||||
#ifdef GGML_USE_METAL
|
||||
~llama_context() {
|
||||
if (model_owner) {
|
||||
delete &model;
|
||||
}
|
||||
#ifdef GGML_USE_METAL
|
||||
if (ctx_metal) {
|
||||
ggml_metal_free(ctx_metal);
|
||||
}
|
||||
#endif
|
||||
#ifdef LLAMA_USE_ALLOCATOR
|
||||
if (alloc) {
|
||||
ggml_allocr_free(alloc);
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
std::mt19937 rng;
|
||||
|
||||
bool has_evaluated_once = false;
|
||||
|
|
@ -371,7 +386,17 @@ struct llama_context {
|
|||
// memory buffers used to evaluate the model
|
||||
// TODO: move in llama_state
|
||||
llama_ctx_buffer buf_compute;
|
||||
|
||||
#ifdef LLAMA_USE_ALLOCATOR
|
||||
llama_ctx_buffer buf_alloc;
|
||||
ggml_allocr * alloc = NULL;
|
||||
#endif
|
||||
|
||||
#ifdef LLAMA_USE_SCRATCH
|
||||
llama_ctx_buffer buf_scratch[LLAMA_MAX_SCRATCH_BUFFERS];
|
||||
int buf_last = 0;
|
||||
size_t buf_max_size[LLAMA_MAX_SCRATCH_BUFFERS] = { 0 };
|
||||
#endif
|
||||
|
||||
#ifdef GGML_USE_METAL
|
||||
ggml_metal_context * ctx_metal = NULL;
|
||||
|
|
@ -381,9 +406,6 @@ struct llama_context {
|
|||
ggml_mpi_context * ctx_mpi = NULL;
|
||||
#endif
|
||||
|
||||
int buf_last = 0;
|
||||
size_t buf_max_size[LLAMA_MAX_SCRATCH_BUFFERS] = { 0 };
|
||||
|
||||
void use_buf(struct ggml_context * ctx, int i) {
|
||||
#if defined(LLAMA_USE_SCRATCH)
|
||||
size_t last_size = 0;
|
||||
|
|
@ -879,6 +901,7 @@ struct llama_context_params llama_context_default_params() {
|
|||
/*.progress_callback =*/ nullptr,
|
||||
/*.progress_callback_user_data =*/ nullptr,
|
||||
/*.low_vram =*/ false,
|
||||
/*.mul_mat_q =*/ false,
|
||||
/*.f16_kv =*/ true,
|
||||
/*.logits_all =*/ false,
|
||||
/*.vocab_only =*/ false,
|
||||
|
|
@ -1006,6 +1029,7 @@ static void llama_model_load_internal(
|
|||
int n_gpu_layers,
|
||||
int main_gpu,
|
||||
const float * tensor_split,
|
||||
const bool mul_mat_q,
|
||||
float rope_freq_base,
|
||||
float rope_freq_scale,
|
||||
bool low_vram,
|
||||
|
|
@ -1134,9 +1158,11 @@ static void llama_model_load_internal(
|
|||
}
|
||||
|
||||
(void) main_gpu;
|
||||
(void) mul_mat_q;
|
||||
#if defined(GGML_USE_CUBLAS)
|
||||
fprintf(stderr, "%s: using CUDA for GPU acceleration\n", __func__);
|
||||
ggml_cuda_set_main_device(main_gpu);
|
||||
ggml_cuda_set_mul_mat_q(mul_mat_q);
|
||||
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_GPU
|
||||
#define LLAMA_BACKEND_OFFLOAD_SPLIT GGML_BACKEND_GPU_SPLIT
|
||||
#elif defined(GGML_USE_CLBLAST)
|
||||
|
|
@ -1230,12 +1256,16 @@ static void llama_model_load_internal(
|
|||
const size_t scale = memory_type == GGML_TYPE_F32 ? 2 : 1;
|
||||
|
||||
// this is the total memory required to run the inference
|
||||
const size_t mem_required =
|
||||
size_t mem_required =
|
||||
ctx_size +
|
||||
mmapped_size - vram_weights + // weights in VRAM not in memory
|
||||
mmapped_size - vram_weights; // weights in VRAM not in memory
|
||||
|
||||
#ifndef LLAMA_USE_ALLOCATOR
|
||||
mem_required +=
|
||||
MEM_REQ_SCRATCH0(hparams.n_ctx).at(model.type) +
|
||||
MEM_REQ_SCRATCH1().at(model.type) +
|
||||
MEM_REQ_EVAL().at(model.type);
|
||||
#endif
|
||||
|
||||
// this is the memory required by one llama_state
|
||||
const size_t mem_required_state =
|
||||
|
|
@ -1341,6 +1371,7 @@ static bool llama_model_load(
|
|||
int n_gpu_layers,
|
||||
int main_gpu,
|
||||
const float * tensor_split,
|
||||
const bool mul_mat_q,
|
||||
float rope_freq_base,
|
||||
float rope_freq_scale,
|
||||
bool low_vram,
|
||||
|
|
@ -1351,7 +1382,8 @@ static bool llama_model_load(
|
|||
llama_progress_callback progress_callback,
|
||||
void *progress_callback_user_data) {
|
||||
try {
|
||||
llama_model_load_internal(fname, model, vocab, n_ctx, n_batch, n_gqa, rms_norm_eps, n_gpu_layers, main_gpu, tensor_split, rope_freq_base, rope_freq_scale, low_vram, memory_type,
|
||||
llama_model_load_internal(fname, model, vocab, n_ctx, n_batch, n_gqa, rms_norm_eps, n_gpu_layers,
|
||||
main_gpu, tensor_split, mul_mat_q, rope_freq_base, rope_freq_scale, low_vram, memory_type,
|
||||
use_mmap, use_mlock, vocab_only, progress_callback, progress_callback_user_data);
|
||||
return true;
|
||||
} catch (const std::exception & err) {
|
||||
|
|
@ -1360,32 +1392,15 @@ static bool llama_model_load(
|
|||
}
|
||||
}
|
||||
|
||||
// evaluate the transformer
|
||||
//
|
||||
// - lctx: llama context
|
||||
// - tokens: new batch of tokens to process
|
||||
// - embd embeddings input
|
||||
// - n_tokens number of tokens
|
||||
// - n_past: the context size so far
|
||||
// - n_threads: number of threads to use
|
||||
//
|
||||
static bool llama_eval_internal(
|
||||
static struct ggml_cgraph * llama_build_graph(
|
||||
llama_context & lctx,
|
||||
const llama_token * tokens,
|
||||
const float * embd,
|
||||
int n_tokens,
|
||||
int n_past,
|
||||
int n_threads,
|
||||
const char * cgraph_fname) {
|
||||
int n_past) {
|
||||
|
||||
LLAMA_ASSERT((!tokens && embd) || (tokens && !embd));
|
||||
|
||||
#ifdef GGML_USE_MPI
|
||||
ggml_mpi_eval_init(lctx.ctx_mpi, &n_tokens, &n_past, &n_threads);
|
||||
#endif
|
||||
|
||||
const int64_t t_start_us = ggml_time_us();
|
||||
|
||||
const int N = n_tokens;
|
||||
|
||||
const auto & model = lctx.model;
|
||||
|
|
@ -1401,10 +1416,8 @@ static bool llama_eval_internal(
|
|||
const int64_t n_head = hparams.n_head;
|
||||
const int64_t n_head_kv = hparams.n_head_kv;
|
||||
const int64_t n_embd_head = hparams.n_embd_head();
|
||||
const int64_t n_vocab = hparams.n_vocab;
|
||||
const int64_t n_embd_gqa = hparams.n_embd_gqa();
|
||||
|
||||
|
||||
LLAMA_ASSERT(n_embd_head == hparams.n_rot);
|
||||
|
||||
const float freq_base = hparams.rope_freq_base;
|
||||
|
|
@ -1416,26 +1429,35 @@ static bool llama_eval_internal(
|
|||
auto & mem_per_token = lctx.mem_per_token;
|
||||
auto & buf_compute = lctx.buf_compute;
|
||||
|
||||
|
||||
struct ggml_init_params params = {
|
||||
/*.mem_size =*/ buf_compute.size,
|
||||
/*.mem_buffer =*/ buf_compute.addr,
|
||||
/*.no_alloc =*/ false,
|
||||
};
|
||||
|
||||
#ifdef LLAMA_USE_ALLOCATOR
|
||||
params.no_alloc = true;
|
||||
#endif
|
||||
|
||||
struct ggml_context * ctx0 = ggml_init(params);
|
||||
|
||||
ggml_cgraph * gf = ggml_new_graph(ctx0);
|
||||
|
||||
// for big prompts, if BLAS is enabled, it is better to use only one thread
|
||||
// otherwise, the threads are spin-lock waiting for the BLAS calls and are degrading the performance
|
||||
n_threads = N >= 32 && ggml_cpu_has_blas() && !ggml_cpu_has_gpublas() ? 1 : n_threads;
|
||||
|
||||
struct ggml_tensor * cur;
|
||||
struct ggml_tensor * inpL;
|
||||
|
||||
if (tokens) {
|
||||
struct ggml_tensor * inp_tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N);
|
||||
|
||||
#ifdef LLAMA_USE_ALLOCATOR
|
||||
ggml_allocr_alloc(lctx.alloc, inp_tokens);
|
||||
if (!ggml_allocr_is_measure(lctx.alloc)) {
|
||||
memcpy(inp_tokens->data, tokens, N*ggml_element_size(inp_tokens));
|
||||
}
|
||||
#else
|
||||
memcpy(inp_tokens->data, tokens, N*ggml_element_size(inp_tokens));
|
||||
#endif
|
||||
ggml_set_name(inp_tokens, "inp_tokens");
|
||||
|
||||
inpL = ggml_get_rows(ctx0, model.tok_embeddings, inp_tokens);
|
||||
|
|
@ -1445,8 +1467,16 @@ static bool llama_eval_internal(
|
|||
#endif
|
||||
|
||||
inpL = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_embd, N);
|
||||
|
||||
#ifdef LLAMA_USE_ALLOCATOR
|
||||
ggml_allocr_alloc(lctx.alloc, inpL);
|
||||
if (!ggml_allocr_is_measure(lctx.alloc)) {
|
||||
memcpy(inpL->data, embd, N * n_embd * ggml_element_size(inpL));
|
||||
}
|
||||
#else
|
||||
memcpy(inpL->data, embd, N * n_embd * ggml_element_size(inpL));
|
||||
#endif
|
||||
}
|
||||
|
||||
const int i_gpu_start = n_layer - n_gpu_layers;
|
||||
(void) i_gpu_start;
|
||||
|
|
@ -1472,6 +1502,17 @@ static bool llama_eval_internal(
|
|||
}
|
||||
#endif // GGML_USE_CUBLAS
|
||||
|
||||
struct ggml_tensor * KQ_scale = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, 1);
|
||||
#ifdef LLAMA_USE_ALLOCATOR
|
||||
ggml_allocr_alloc(lctx.alloc, KQ_scale);
|
||||
if (!ggml_allocr_is_measure(lctx.alloc)) {
|
||||
ggml_set_f32(KQ_scale, 1.0f/sqrtf(float(n_embd)/n_head));
|
||||
}
|
||||
#else
|
||||
ggml_set_f32(KQ_scale, 1.0f/sqrtf(float(n_embd)/n_head));
|
||||
#endif
|
||||
ggml_set_name(KQ_scale, "1/sqrt(n_embd_head)");
|
||||
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
ggml_format_name(inpL, "layer_inp_%d", il);
|
||||
|
||||
|
|
@ -1567,9 +1608,6 @@ static bool llama_eval_internal(
|
|||
ggml_set_name(KQ, "KQ");
|
||||
|
||||
// KQ_scaled = KQ / sqrt(n_embd_head)
|
||||
struct ggml_tensor * KQ_scale = ggml_new_f32(ctx0, 1.0f/sqrtf(float(n_embd)/n_head));
|
||||
ggml_set_name(KQ_scale, "1/sqrt(n_embd_head)");
|
||||
|
||||
// KQ_scaled shape [n_past + N, N, n_head, 1]
|
||||
struct ggml_tensor * KQ_scaled = ggml_scale_inplace(ctx0, KQ, KQ_scale);
|
||||
offload_func_kq(KQ_scaled);
|
||||
|
|
@ -1685,9 +1723,6 @@ static bool llama_eval_internal(
|
|||
|
||||
lctx.use_buf(ctx0, 0);
|
||||
|
||||
// used at the end to optionally extract the embeddings
|
||||
struct ggml_tensor * embeddings = NULL;
|
||||
|
||||
// norm
|
||||
{
|
||||
cur = ggml_rms_norm(ctx0, inpL, rms_norm_eps);
|
||||
|
|
@ -1698,8 +1733,6 @@ static bool llama_eval_internal(
|
|||
cur = ggml_mul(ctx0, cur, model.norm);
|
||||
// offload_func_nr(cur); // TODO CPU + GPU mirrored backend
|
||||
ggml_set_name(cur, "result_norm");
|
||||
|
||||
embeddings = cur;
|
||||
}
|
||||
|
||||
// lm_head
|
||||
|
|
@ -1711,12 +1744,88 @@ static bool llama_eval_internal(
|
|||
// logits -> probs
|
||||
//cur = ggml_soft_max_inplace(ctx0, cur);
|
||||
|
||||
// run the computation
|
||||
ggml_build_forward_expand(gf, cur);
|
||||
|
||||
// fprintf(stderr, "graph build time: %.3f ms (%d nodes, %d leafs)\n", (ggml_time_us() - t_start_us)/1000.0, gf.n_nodes, gf.n_leafs);
|
||||
if (mem_per_token == 0) {
|
||||
mem_per_token = ggml_used_mem(ctx0)/N;
|
||||
}
|
||||
|
||||
#if 0
|
||||
printf("\n%s: used_mem: eval ctx %.3f MB, scratch %.3f MB %.3f MB, work buf %.3f MB, n_past = %d, N = %d\n", __func__,
|
||||
ggml_used_mem(ctx0)/1024.0/1024.0,
|
||||
lctx.get_buf_max_mem(0)/1024.0/1024.0,
|
||||
lctx.get_buf_max_mem(1)/1024.0/1024.0,
|
||||
lctx.work_buffer.size()/1024.0/1024.0,
|
||||
n_past, N);
|
||||
#endif
|
||||
|
||||
ggml_free(ctx0);
|
||||
|
||||
return gf;
|
||||
}
|
||||
|
||||
// evaluate the transformer
|
||||
//
|
||||
// - lctx: llama context
|
||||
// - tokens: new batch of tokens to process
|
||||
// - embd embeddings input
|
||||
// - n_tokens number of tokens
|
||||
// - n_past: the context size so far
|
||||
// - n_threads: number of threads to use
|
||||
//
|
||||
static bool llama_eval_internal(
|
||||
llama_context & lctx,
|
||||
const llama_token * tokens,
|
||||
const float * embd,
|
||||
int n_tokens,
|
||||
int n_past,
|
||||
int n_threads,
|
||||
const char * cgraph_fname) {
|
||||
|
||||
LLAMA_ASSERT((!tokens && embd) || (tokens && !embd));
|
||||
|
||||
const int64_t t_start_us = ggml_time_us();
|
||||
|
||||
#ifdef GGML_USE_MPI
|
||||
ggml_mpi_eval_init(lctx.ctx_mpi, &n_tokens, &n_past, &n_threads);
|
||||
#endif
|
||||
|
||||
const int N = n_tokens;
|
||||
|
||||
const auto & model = lctx.model;
|
||||
const auto & hparams = model.hparams;
|
||||
|
||||
const auto & kv_self = lctx.kv_self;
|
||||
|
||||
LLAMA_ASSERT(!!kv_self.ctx);
|
||||
|
||||
const int64_t n_embd = hparams.n_embd;
|
||||
const int64_t n_vocab = hparams.n_vocab;
|
||||
|
||||
#ifdef LLAMA_USE_ALLOCATOR
|
||||
ggml_allocr_reset(lctx.alloc);
|
||||
#endif
|
||||
|
||||
ggml_cgraph * gf = llama_build_graph(lctx, tokens, embd, n_tokens, n_past);
|
||||
|
||||
#ifdef LLAMA_USE_ALLOCATOR
|
||||
ggml_allocr_alloc_graph(lctx.alloc, gf);
|
||||
#endif
|
||||
|
||||
// fprintf(stderr, "graph build time: %.3f ms (%d nodes, %d leafs)\n", (ggml_time_us() - t_start_us)/1000.0, gf->n_nodes, gf->n_leafs);
|
||||
|
||||
// for big prompts, if BLAS is enabled, it is better to use only one thread
|
||||
// otherwise, the threads are spin-lock waiting for the BLAS calls and are degrading the performance
|
||||
n_threads = N >= 32 && ggml_cpu_has_blas() && !ggml_cpu_has_gpublas() ? 1 : n_threads;
|
||||
|
||||
struct ggml_tensor * res = gf->nodes[gf->n_nodes - 1];
|
||||
struct ggml_tensor * embeddings = gf->nodes[gf->n_nodes - 2];
|
||||
|
||||
LLAMA_ASSERT(strcmp(res->name, "result_output") == 0);
|
||||
LLAMA_ASSERT(strcmp(embeddings->name, "result_norm") == 0);
|
||||
|
||||
#if GGML_USE_MPI
|
||||
const int64_t n_layer = hparams.n_layer;
|
||||
ggml_mpi_graph_compute_pre(lctx.ctx_mpi, gf, n_layer);
|
||||
#endif
|
||||
|
||||
|
|
@ -1728,7 +1837,10 @@ static bool llama_eval_internal(
|
|||
//}
|
||||
ggml_metal_set_n_cb (lctx.ctx_metal, n_threads);
|
||||
ggml_metal_graph_compute(lctx.ctx_metal, gf);
|
||||
ggml_metal_get_tensor (lctx.ctx_metal, cur);
|
||||
ggml_metal_get_tensor (lctx.ctx_metal, res);
|
||||
if (!lctx.embedding.empty()) {
|
||||
ggml_metal_get_tensor(lctx.ctx_metal, embeddings);
|
||||
}
|
||||
} else {
|
||||
// IMPORTANT:
|
||||
// Since we don't have efficient Matrix x Matrix Metal multiplication yet, we fallback to vanilla
|
||||
|
|
@ -1759,8 +1871,6 @@ static bool llama_eval_internal(
|
|||
// update kv token count
|
||||
lctx.kv_self.n = n_past + N;
|
||||
|
||||
struct ggml_tensor * res = gf->nodes[gf->n_nodes - 1];
|
||||
|
||||
if (cgraph_fname) {
|
||||
ggml_graph_export(gf, cgraph_fname);
|
||||
}
|
||||
|
|
@ -1798,21 +1908,6 @@ static bool llama_eval_internal(
|
|||
memcpy(embedding_out.data(), (float *) ggml_get_data(embeddings) + (n_embd*(N - 1)), sizeof(float)*n_embd);
|
||||
}
|
||||
|
||||
if (mem_per_token == 0) {
|
||||
mem_per_token = ggml_used_mem(ctx0)/N;
|
||||
}
|
||||
|
||||
#if 0
|
||||
printf("\n%s: used_mem: eval ctx %.3f MB, scratch %.3f MB %.3f MB, work buf %.3f MB, n_past = %d, N = %d\n", __func__,
|
||||
ggml_used_mem(ctx0)/1024.0/1024.0,
|
||||
lctx.get_buf_max_mem(0)/1024.0/1024.0,
|
||||
lctx.get_buf_max_mem(1)/1024.0/1024.0,
|
||||
lctx.work_buffer.size()/1024.0/1024.0,
|
||||
n_past, N);
|
||||
#endif
|
||||
|
||||
ggml_free(ctx0);
|
||||
|
||||
// measure the performance only for the single-token evals
|
||||
if (N == 1) {
|
||||
lctx.t_eval_us += ggml_time_us() - t_start_us;
|
||||
|
|
@ -3103,7 +3198,7 @@ struct llama_model * llama_load_model_from_file(
|
|||
ggml_type memory_type = params.f16_kv ? GGML_TYPE_F16 : GGML_TYPE_F32;
|
||||
|
||||
if (!llama_model_load(path_model, *model, model->vocab, params.n_ctx, params.n_batch, params.n_gqa, params.rms_norm_eps, params.n_gpu_layers,
|
||||
params.main_gpu, params.tensor_split, params.rope_freq_base, params.rope_freq_scale,params.low_vram,
|
||||
params.main_gpu, params.tensor_split, params.mul_mat_q, params.rope_freq_base, params.rope_freq_scale,params.low_vram,
|
||||
memory_type, params.use_mmap, params.use_mlock, params.vocab_only, params.progress_callback,
|
||||
params.progress_callback_user_data)) {
|
||||
delete model;
|
||||
|
|
@ -3180,10 +3275,47 @@ struct llama_context * llama_new_context_with_model(
|
|||
ctx->embedding.resize(hparams.n_embd);
|
||||
}
|
||||
|
||||
ctx->buf_compute.resize(MEM_REQ_EVAL().at(ctx->model.type) + ggml_graph_overhead());
|
||||
#ifdef LLAMA_USE_ALLOCATOR
|
||||
{
|
||||
static const size_t tensor_alignment = 32;
|
||||
// the compute buffer is used to store the tensor and graph structs, while the allocator buffer is used for the tensor data
|
||||
ctx->buf_compute.resize(ggml_tensor_overhead()*GGML_MAX_NODES + ggml_graph_overhead());
|
||||
|
||||
// create measure allocator
|
||||
ctx->alloc = ggml_allocr_new_measure(tensor_alignment);
|
||||
|
||||
// build worst-case graph
|
||||
int n_tokens = std::min((int)hparams.n_ctx, params.n_batch);
|
||||
int n_past = hparams.n_ctx - n_tokens;
|
||||
llama_token token = llama_token_bos(); // not actually used by llama_build_graph, but required to choose between token and embedding inputs graph
|
||||
ggml_cgraph * gf = llama_build_graph(*ctx, &token, NULL, n_tokens, n_past);
|
||||
|
||||
// measure memory requirements for the graph
|
||||
size_t alloc_size = ggml_allocr_alloc_graph(ctx->alloc, gf) + tensor_alignment;
|
||||
|
||||
fprintf(stderr, "%s: compute buffer total size = %7.2f MB\n", __func__, (ctx->buf_compute.size + alloc_size) / 1024.0 / 1024.0);
|
||||
|
||||
// debug - for comparison with scratch buffer
|
||||
//size_t prev_req =
|
||||
// MEM_REQ_SCRATCH0(hparams.n_ctx).at(ctx->model.type) +
|
||||
// MEM_REQ_SCRATCH1().at(ctx->model.type) +
|
||||
// MEM_REQ_EVAL().at(ctx->model.type);
|
||||
//fprintf(stderr, "%s: (debug) equivalent with scratch buffer = %7.2f MB\n", __func__, prev_req / 1024.0 / 1024.0);
|
||||
|
||||
// recreate allocator with exact memory requirements
|
||||
ggml_allocr_free(ctx->alloc);
|
||||
|
||||
ctx->buf_alloc.resize(alloc_size);
|
||||
ctx->alloc = ggml_allocr_new(ctx->buf_alloc.addr, ctx->buf_alloc.size, tensor_alignment);
|
||||
}
|
||||
#else
|
||||
ctx->buf_compute.resize(MEM_REQ_EVAL().at(ctx->model.type) + ggml_graph_overhead());
|
||||
#endif
|
||||
|
||||
#ifdef LLAMA_USE_SCRATCH
|
||||
ctx->buf_scratch[0].resize(MEM_REQ_SCRATCH0(hparams.n_ctx).at(ctx->model.type));
|
||||
ctx->buf_scratch[1].resize(MEM_REQ_SCRATCH1().at(ctx->model.type));
|
||||
#endif
|
||||
}
|
||||
|
||||
#ifdef GGML_USE_METAL
|
||||
|
|
@ -3253,9 +3385,6 @@ struct llama_context * llama_init_from_file(
|
|||
}
|
||||
|
||||
void llama_free(struct llama_context * ctx) {
|
||||
if (ctx->model_owner) {
|
||||
delete &ctx->model;
|
||||
}
|
||||
delete ctx;
|
||||
}
|
||||
|
||||
|
|
@ -3614,10 +3743,20 @@ size_t llama_get_state_size(const struct llama_context * ctx) {
|
|||
return s_total;
|
||||
}
|
||||
|
||||
// Copies the state to the specified destination address
|
||||
size_t llama_copy_state_data(struct llama_context * ctx, uint8_t * dst) {
|
||||
uint8_t * out = dst;
|
||||
|
||||
/** copy state data into either a buffer or file depending on the passed in context
|
||||
*
|
||||
* file context:
|
||||
* llama_file file("/path", "wb");
|
||||
* llama_data_file_context data_ctx(&file);
|
||||
* llama_copy_state_data(ctx, &data_ctx);
|
||||
*
|
||||
* buffer context:
|
||||
* std::vector<uint8_t> buf(max_size, 0);
|
||||
* llama_data_buffer_context data_ctx(&buf.data());
|
||||
* llama_copy_state_data(ctx, &data_ctx);
|
||||
*
|
||||
*/
|
||||
void llama_copy_state_data_internal(struct llama_context * ctx, llama_data_context * data_ctx) {
|
||||
// copy rng
|
||||
{
|
||||
std::stringstream rng_ss;
|
||||
|
|
@ -3629,8 +3768,8 @@ size_t llama_copy_state_data(struct llama_context * ctx, uint8_t * dst) {
|
|||
memset(&rng_buf[0], 0, LLAMA_MAX_RNG_STATE);
|
||||
memcpy(&rng_buf[0], rng_ss.str().data(), rng_ss.str().size());
|
||||
|
||||
memcpy(out, &rng_size, sizeof(rng_size)); out += sizeof(rng_size);
|
||||
memcpy(out, &rng_buf[0], LLAMA_MAX_RNG_STATE); out += LLAMA_MAX_RNG_STATE;
|
||||
data_ctx->write(&rng_size, sizeof(rng_size));
|
||||
data_ctx->write(&rng_buf[0], LLAMA_MAX_RNG_STATE);
|
||||
}
|
||||
|
||||
// copy logits
|
||||
|
|
@ -3638,25 +3777,29 @@ size_t llama_copy_state_data(struct llama_context * ctx, uint8_t * dst) {
|
|||
const size_t logits_cap = ctx->logits.capacity();
|
||||
const size_t logits_size = ctx->logits.size();
|
||||
|
||||
memcpy(out, &logits_cap, sizeof(logits_cap)); out += sizeof(logits_cap);
|
||||
memcpy(out, &logits_size, sizeof(logits_size)); out += sizeof(logits_size);
|
||||
data_ctx->write(&logits_cap, sizeof(logits_cap));
|
||||
data_ctx->write(&logits_size, sizeof(logits_size));
|
||||
|
||||
if (logits_size) {
|
||||
memcpy(out, ctx->logits.data(), logits_size * sizeof(float));
|
||||
data_ctx->write(ctx->logits.data(), logits_size * sizeof(float));
|
||||
}
|
||||
|
||||
out += logits_cap * sizeof(float);
|
||||
// If there is a gap between the size and the capacity, write padding
|
||||
size_t padding_size = (logits_cap - logits_size) * sizeof(float);
|
||||
if (padding_size > 0) {
|
||||
std::vector<uint8_t> padding(padding_size, 0); // Create a buffer filled with zeros
|
||||
data_ctx->write(padding.data(), padding_size);
|
||||
}
|
||||
}
|
||||
|
||||
// copy embeddings
|
||||
{
|
||||
const size_t embedding_size = ctx->embedding.size();
|
||||
|
||||
memcpy(out, &embedding_size, sizeof(embedding_size)); out += sizeof(embedding_size);
|
||||
data_ctx->write(&embedding_size, sizeof(embedding_size));
|
||||
|
||||
if (embedding_size) {
|
||||
memcpy(out, ctx->embedding.data(), embedding_size * sizeof(float));
|
||||
out += embedding_size * sizeof(float);
|
||||
data_ctx->write(ctx->embedding.data(), embedding_size * sizeof(float));
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -3671,8 +3814,8 @@ size_t llama_copy_state_data(struct llama_context * ctx, uint8_t * dst) {
|
|||
const size_t kv_size = kv_self.buf.size;
|
||||
const int kv_ntok = llama_get_kv_cache_token_count(ctx);
|
||||
|
||||
memcpy(out, &kv_size, sizeof(kv_size)); out += sizeof(kv_size);
|
||||
memcpy(out, &kv_ntok, sizeof(kv_ntok)); out += sizeof(kv_ntok);
|
||||
data_ctx->write(&kv_size, sizeof(kv_size));
|
||||
data_ctx->write(&kv_ntok, sizeof(kv_ntok));
|
||||
|
||||
if (kv_size) {
|
||||
const size_t elt_size = ggml_element_size(kv_self.k);
|
||||
|
|
@ -3681,12 +3824,12 @@ size_t llama_copy_state_data(struct llama_context * ctx, uint8_t * dst) {
|
|||
ggml_cgraph gf{};
|
||||
|
||||
ggml_tensor * kout3d = ggml_new_tensor_3d(cpy_ctx, kv_self.k->type, n_embd, kv_ntok, n_layer);
|
||||
kout3d->data = out;
|
||||
out += ggml_nbytes(kout3d);
|
||||
std::vector<uint8_t> kout3d_data(ggml_nbytes(kout3d), 0);
|
||||
kout3d->data = kout3d_data.data();
|
||||
|
||||
ggml_tensor * vout3d = ggml_new_tensor_3d(cpy_ctx, kv_self.v->type, kv_ntok, n_embd, n_layer);
|
||||
vout3d->data = out;
|
||||
out += ggml_nbytes(vout3d);
|
||||
std::vector<uint8_t> vout3d_data(ggml_nbytes(vout3d), 0);
|
||||
vout3d->data = vout3d_data.data();
|
||||
|
||||
ggml_tensor * k3d = ggml_view_3d(cpy_ctx, kv_self.k,
|
||||
n_embd, kv_ntok, n_layer,
|
||||
|
|
@ -3701,15 +3844,20 @@ size_t llama_copy_state_data(struct llama_context * ctx, uint8_t * dst) {
|
|||
ggml_graph_compute_helper(ctx->work_buffer, &gf, /*n_threads*/ 1);
|
||||
|
||||
ggml_free(cpy_ctx);
|
||||
|
||||
// our data is now in the kout3d_data and vout3d_data buffers
|
||||
// write them to file
|
||||
data_ctx->write(kout3d_data.data(), kout3d_data.size());
|
||||
data_ctx->write(vout3d_data.data(), vout3d_data.size());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const size_t written = out - dst;
|
||||
const size_t max_size = llama_get_state_size(ctx);
|
||||
size_t llama_copy_state_data(struct llama_context * ctx, uint8_t * dst) {
|
||||
llama_data_buffer_context data_ctx(dst);
|
||||
llama_copy_state_data_internal(ctx, &data_ctx);
|
||||
|
||||
LLAMA_ASSERT(written <= max_size);
|
||||
|
||||
return written;
|
||||
return data_ctx.get_size_written();
|
||||
}
|
||||
|
||||
// Sets the state reading from the specified source address
|
||||
|
|
@ -3894,15 +4042,9 @@ bool llama_save_session_file(struct llama_context * ctx, const char * path_sessi
|
|||
file.write_u32((uint32_t) n_token_count);
|
||||
file.write_raw(tokens, sizeof(llama_token) * n_token_count);
|
||||
|
||||
// save the context state
|
||||
{
|
||||
const size_t n_state_size_max = llama_get_state_size(ctx);
|
||||
|
||||
std::vector<uint8_t> state_data(n_state_size_max);
|
||||
const size_t n_state_size_cur = llama_copy_state_data(ctx, state_data.data());
|
||||
|
||||
file.write_raw(state_data.data(), n_state_size_cur);
|
||||
}
|
||||
// save the context state using stream saving
|
||||
llama_data_file_context data_ctx(&file);
|
||||
llama_copy_state_data_internal(ctx, &data_ctx);
|
||||
|
||||
return true;
|
||||
}
|
||||
|
|
|
|||
1
llama.h
1
llama.h
|
|
@ -108,6 +108,7 @@ extern "C" {
|
|||
|
||||
// Keep the booleans together to avoid misalignment during copy-by-value.
|
||||
bool low_vram; // if true, reduce VRAM usage at the cost of performance
|
||||
bool mul_mat_q; // if true, use experimental mul_mat_q kernels
|
||||
bool f16_kv; // use fp16 for KV cache
|
||||
bool logits_all; // the llama_eval() call computes all logits, not just the last one
|
||||
bool vocab_only; // only load the vocabulary, no weights
|
||||
|
|
|
|||
|
|
@ -10,5 +10,5 @@ cp -rpv ../ggml/src/ggml-metal.m ./ggml-metal.m
|
|||
cp -rpv ../ggml/src/ggml-metal.metal ./ggml-metal.metal
|
||||
cp -rpv ../ggml/include/ggml/ggml.h ./ggml.h
|
||||
|
||||
cp -rpv ../ggml/tests/test-opt.c ./tests/test-opt.c
|
||||
cp -rpv ../ggml/tests/test-grad0.c ./tests/test-grad0.c
|
||||
cp -rpv ../ggml/tests/test-opt.cpp ./tests/test-opt.cpp
|
||||
cp -rpv ../ggml/tests/test-grad0.cpp ./tests/test-grad0.cpp
|
||||
|
|
|
|||
|
|
@ -6,10 +6,10 @@ function(llama_add_test source)
|
|||
add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${ARGN})
|
||||
endfunction()
|
||||
|
||||
# llama_add_test(test-double-float.c) # SLOW
|
||||
# llama_add_test(test-double-float.cpp) # SLOW
|
||||
llama_add_test(test-quantize-fns.cpp)
|
||||
llama_add_test(test-quantize-perf.cpp)
|
||||
llama_add_test(test-sampling.cpp)
|
||||
llama_add_test(test-tokenizer-0.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab.bin)
|
||||
llama_add_test(test-grad0.c) # SLOW
|
||||
# llama_add_test(test-opt.c) # SLOW
|
||||
llama_add_test(test-grad0.cpp) # SLOW
|
||||
# llama_add_test(test-opt.cpp) # SLOW
|
||||
|
|
|
|||
|
|
@ -3,10 +3,11 @@
|
|||
// This is done by checking all finite (non-NaN, non-infinite) floats.
|
||||
|
||||
#undef NDEBUG
|
||||
#include <assert.h>
|
||||
#include <cassert>
|
||||
#include <immintrin.h>
|
||||
#include <math.h>
|
||||
#include <stdint.h>
|
||||
#include <cmath>
|
||||
#include <cstdint>
|
||||
#include <cstring>
|
||||
|
||||
#pragma GCC diagnostic push
|
||||
#pragma GCC diagnostic ignored "-Wdouble-promotion"
|
||||
|
|
@ -32,8 +33,9 @@ inline static float silu_float(float x) {
|
|||
int main(void) {
|
||||
uint32_t x = UINT32_MAX;
|
||||
do {
|
||||
float f = *(float *)&x;
|
||||
assert(!isfinite(f) || (round_orig(f) == round_float(f)));
|
||||
float f;
|
||||
memcpy(&f, &x, sizeof(x));
|
||||
assert(!std::isfinite(f) || (round_orig(f) == round_float(f)));
|
||||
} while (x--);
|
||||
|
||||
#ifdef __F16C__
|
||||
|
|
@ -1,10 +1,10 @@
|
|||
#define _CRT_SECURE_NO_DEPRECATE // Disables ridiculous "unsafe" warnigns on Windows
|
||||
#include "ggml.h"
|
||||
|
||||
#include <math.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <assert.h>
|
||||
#include <cmath>
|
||||
#include <cstdio>
|
||||
#include <cstdlib>
|
||||
#include <cassert>
|
||||
|
||||
#if defined(_MSC_VER)
|
||||
#pragma warning(disable: 4244 4267) // possible loss of data
|
||||
|
|
@ -47,16 +47,16 @@
|
|||
|
||||
#define GGML_PRINT(...) printf(__VA_ARGS__)
|
||||
|
||||
float frand(void) {
|
||||
static float frand(void) {
|
||||
return (float)rand()/(float)RAND_MAX;
|
||||
}
|
||||
|
||||
int irand(int n) {
|
||||
static int irand(int n) {
|
||||
if (n == 0) return 0;
|
||||
return rand()%n;
|
||||
}
|
||||
|
||||
void get_random_dims(int64_t * dims, int ndims) {
|
||||
static void get_random_dims(int64_t * dims, int ndims) {
|
||||
dims[0] = dims[1] = dims[2] = dims[3] = 1;
|
||||
|
||||
for (int i = 0; i < ndims; i++) {
|
||||
|
|
@ -64,7 +64,7 @@ void get_random_dims(int64_t * dims, int ndims) {
|
|||
}
|
||||
}
|
||||
|
||||
struct ggml_tensor * get_random_tensor_f32(
|
||||
static struct ggml_tensor * get_random_tensor_f32(
|
||||
struct ggml_context * ctx0,
|
||||
int ndims,
|
||||
int64_t ne[],
|
||||
|
|
@ -112,7 +112,7 @@ struct ggml_tensor * get_random_tensor_f32(
|
|||
return result;
|
||||
}
|
||||
|
||||
struct ggml_tensor * get_random_tensor_f16(
|
||||
static struct ggml_tensor * get_random_tensor_f16(
|
||||
struct ggml_context * ctx0,
|
||||
int ndims,
|
||||
int64_t ne[],
|
||||
|
|
@ -160,7 +160,7 @@ struct ggml_tensor * get_random_tensor_f16(
|
|||
return result;
|
||||
}
|
||||
|
||||
struct ggml_tensor * get_random_tensor_i32(
|
||||
static struct ggml_tensor * get_random_tensor_i32(
|
||||
struct ggml_context * ctx0,
|
||||
int ndims,
|
||||
int64_t ne[],
|
||||
|
|
@ -208,7 +208,7 @@ struct ggml_tensor * get_random_tensor_i32(
|
|||
return result;
|
||||
}
|
||||
|
||||
void print_elements(const char* label, const struct ggml_tensor * t) {
|
||||
static void print_elements(const char* label, const struct ggml_tensor * t) {
|
||||
if (!t) {
|
||||
printf("%s: %s = null\n", __func__, label);
|
||||
return;
|
||||
|
|
@ -228,7 +228,7 @@ void print_elements(const char* label, const struct ggml_tensor * t) {
|
|||
|
||||
}
|
||||
|
||||
bool check_gradient(
|
||||
static bool check_gradient(
|
||||
const char * op_name,
|
||||
struct ggml_context * ctx0,
|
||||
struct ggml_tensor * x[],
|
||||
|
|
@ -310,7 +310,7 @@ bool check_gradient(
|
|||
}
|
||||
|
||||
// TODO: clean-up this ..
|
||||
bool check_mat_mul(
|
||||
static bool check_mat_mul(
|
||||
const struct ggml_tensor * y,
|
||||
const struct ggml_tensor * x0,
|
||||
const struct ggml_tensor * x1) {
|
||||
|
|
@ -373,9 +373,9 @@ bool check_mat_mul(
|
|||
|
||||
int main(int argc, const char ** argv) {
|
||||
struct ggml_init_params params = {
|
||||
.mem_size = 128*1024*1024,
|
||||
.mem_buffer = NULL,
|
||||
.no_alloc = false,
|
||||
/* .mem_size = */ 128*1024*1024,
|
||||
/* .mem_buffer = */ NULL,
|
||||
/* .no_alloc = */ false,
|
||||
};
|
||||
|
||||
int64_t ne[4];
|
||||
|
|
@ -1,9 +1,9 @@
|
|||
#include "ggml.h"
|
||||
|
||||
#include <math.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <assert.h>
|
||||
#include <cmath>
|
||||
#include <cstdio>
|
||||
#include <cstdlib>
|
||||
#include <cassert>
|
||||
|
||||
#define MAX_NARGS 2
|
||||
|
||||
|
|
@ -119,10 +119,11 @@ void set_element(struct ggml_tensor * t, int idx, float value) {
|
|||
|
||||
int main(void) {
|
||||
struct ggml_init_params params = {
|
||||
.mem_size = 1024*1024*1024,
|
||||
.mem_buffer = NULL,
|
||||
.no_alloc = false,
|
||||
/* .mem_size = */ 1024*1024*1024,
|
||||
/* .mem_buffer = */ NULL,
|
||||
/* .no_alloc = */ false,
|
||||
};
|
||||
|
||||
struct ggml_context * ctx = ggml_init(params);
|
||||
|
||||
int64_t ne1[4] = {4, 128, 1, 1};
|
||||
Loading…
Add table
Add a link
Reference in a new issue