vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixed build

Browse source
This commit is contained in:
Concedo 2024-11-26 22:06:55 +08:00
parent 9708abf282
commit b9e99c69e8
3 changed files with 35 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

1
CMakeLists.txt
View file

@ -67,6 +67,7 @@ set(THREADS_PREFER_PTHREAD_FLAG ON)
find_package(Threads REQUIRED) find_package(Threads REQUIRED)
add_compile_definitions(LOG_DISABLE_LOGS) add_compile_definitions(LOG_DISABLE_LOGS)
add_compile_definitions(GGML_USE_CPU)
file(GLOB GGML_SOURCES_CUDA "ggml/src/ggml-cuda/*.cu") file(GLOB GGML_SOURCES_CUDA "ggml/src/ggml-cuda/*.cu")
list(APPEND GGML_SOURCES_CUDA "ggml/src/ggml-cuda/ggml-cuda.cu") list(APPEND GGML_SOURCES_CUDA "ggml/src/ggml-cuda/ggml-cuda.cu")

4
Makefile
View file

@ -48,8 +48,8 @@ ifdef KCPP_DEBUG
CFLAGS = -g -O0 CFLAGS = -g -O0
CXXFLAGS = -g -O0 CXXFLAGS = -g -O0
endif endif
CFLAGS += -I. -Iggml/include -Iggml/src -Iggml/src/ggml-cpu -Iinclude -Isrc -I./include -I./include/CL -I./otherarch -I./otherarch/tools -I./otherarch/sdcpp -I./otherarch/sdcpp/thirdparty -I./include/vulkan -O3 -fno-finite-math-only -std=c11 -fPIC -DLOG_DISABLE_LOGS -D_GNU_SOURCE CFLAGS += -I. -Iggml/include -Iggml/src -Iggml/src/ggml-cpu -Iinclude -Isrc -I./include -I./include/CL -I./otherarch -I./otherarch/tools -I./otherarch/sdcpp -I./otherarch/sdcpp/thirdparty -I./include/vulkan -O3 -fno-finite-math-only -std=c11 -fPIC -DLOG_DISABLE_LOGS -D_GNU_SOURCE -DGGML_USE_CPU
CXXFLAGS += -I. -Iggml/include -Iggml/src -Iggml/src/ggml-cpu -Iinclude -Isrc -I./common -I./include -I./include/CL -I./otherarch -I./otherarch/tools -I./otherarch/sdcpp -I./otherarch/sdcpp/thirdparty -I./include/vulkan -O3 -fno-finite-math-only -std=c++11 -fPIC -DLOG_DISABLE_LOGS -D_GNU_SOURCE CXXFLAGS += -I. -Iggml/include -Iggml/src -Iggml/src/ggml-cpu -Iinclude -Isrc -I./common -I./include -I./include/CL -I./otherarch -I./otherarch/tools -I./otherarch/sdcpp -I./otherarch/sdcpp/thirdparty -I./include/vulkan -O3 -fno-finite-math-only -std=c++11 -fPIC -DLOG_DISABLE_LOGS -D_GNU_SOURCE -DGGML_USE_CPU
ifndef KCPP_DEBUG ifndef KCPP_DEBUG
CFLAGS += -DNDEBUG -s CFLAGS += -DNDEBUG -s
CXXFLAGS += -DNDEBUG -s CXXFLAGS += -DNDEBUG -s

33
gpttype_adapter.cpp
View file

@ -496,6 +496,37 @@ void ContextRewind(std::vector<int> &embd, std::vector<int> &current_context_tok
} }
} }
const char * kcpp_print_system_info(void) {
ggml_cpu_init(); // some ARM features are detected at runtime
static std::string s;
s = "";
s += "AVX = " + std::to_string(ggml_cpu_has_avx()) + " | ";
s += "AVX_VNNI = " + std::to_string(ggml_cpu_has_avx_vnni()) + " | ";
s += "AVX2 = " + std::to_string(ggml_cpu_has_avx2()) + " | ";
s += "AVX512 = " + std::to_string(ggml_cpu_has_avx512()) + " | ";
s += "AVX512_VBMI = " + std::to_string(ggml_cpu_has_avx512_vbmi()) + " | ";
s += "AVX512_VNNI = " + std::to_string(ggml_cpu_has_avx512_vnni()) + " | ";
s += "AVX512_BF16 = " + std::to_string(ggml_cpu_has_avx512_bf16()) + " | ";
s += "AMX_INT8 = " + std::to_string(ggml_cpu_has_amx_int8()) + " | ";
s += "FMA = " + std::to_string(ggml_cpu_has_fma()) + " | ";
s += "NEON = " + std::to_string(ggml_cpu_has_neon()) + " | ";
s += "SVE = " + std::to_string(ggml_cpu_has_sve()) + " | ";
s += "ARM_FMA = " + std::to_string(ggml_cpu_has_arm_fma()) + " | ";
s += "F16C = " + std::to_string(ggml_cpu_has_f16c()) + " | ";
s += "FP16_VA = " + std::to_string(ggml_cpu_has_fp16_va()) + " | ";
s += "RISCV_VECT = " + std::to_string(ggml_cpu_has_riscv_v()) + " | ";
s += "WASM_SIMD = " + std::to_string(ggml_cpu_has_wasm_simd()) + " | ";
s += "SSE3 = " + std::to_string(ggml_cpu_has_sse3()) + " | ";
s += "SSSE3 = " + std::to_string(ggml_cpu_has_ssse3()) + " | ";
s += "VSX = " + std::to_string(ggml_cpu_has_vsx()) + " | ";
s += "MATMUL_INT8 = " + std::to_string(ggml_cpu_has_matmul_int8()) + " | ";
s += "LLAMAFILE = " + std::to_string(ggml_cpu_has_llamafile()) + " | ";
return s.c_str();
}
// KCPP SAMPLING FUNCTIONS // KCPP SAMPLING FUNCTIONS
void sample_softmax(llama_token_data_array * cur_p) { void sample_softmax(llama_token_data_array * cur_p) {
GGML_ASSERT(cur_p->size > 0); GGML_ASSERT(cur_p->size > 0);
@ -1811,7 +1842,7 @@ ModelLoadResult gpttype_load_model(const load_model_inputs inputs, FileFormat in
int cu_parseinfo_maindevice = inputs.cublas_info<=0?0:inputs.cublas_info; int cu_parseinfo_maindevice = inputs.cublas_info<=0?0:inputs.cublas_info;
printf("System Info: %s\n", llama_print_system_info()); printf("System Info: %s\n", kcpp_print_system_info());
#if defined(GGML_USE_CUDA) #if defined(GGML_USE_CUDA)
if(file_format!=FileFormat::GGUF_GENERIC) if(file_format!=FileFormat::GGUF_GENERIC)
{ {