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

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	CMakeLists.txt
#	Makefile
#	README.md
#	flake.lock
#	llama.cpp
This commit is contained in:
Concedo 2024-02-07 22:21:32 +08:00
commit ec2dbd99a3
21 changed files with 2614 additions and 1863 deletions
Download patch file Download diff file Expand all files Collapse all files

22
common/common.cpp
View file

@ -47,6 +47,10 @@
#define GGML_USE_CUBLAS_SYCL
#endif
#if (defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL)) || defined(GGML_USE_VULKAN)
#define GGML_USE_CUBLAS_SYCL_VULKAN
#endif
int32_t get_num_physical_cores() {
#ifdef __linux__
// enumerate the set of thread siblings, num entries is num cores
@ -400,6 +404,18 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
break;
}
sparams.penalty_present = std::stof(argv[i]);
} else if (arg == "--dynatemp-range") {
if (++i >= argc) {
invalid_param = true;
break;
}
sparams.dynatemp_range = std::stof(argv[i]);
} else if (arg == "--dynatemp-exp") {
if (++i >= argc) {
invalid_param = true;
break;
}
sparams.dynatemp_exponent = std::stof(argv[i]);
} else if (arg == "--mirostat") {
if (++i >= argc) {
invalid_param = true;
@ -649,8 +665,8 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
params.tensor_split[i] = 0.0f;
}
}
#ifndef GGML_USE_CUBLAS_SYCL
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS/SYCL. Setting a tensor split has no effect.\n");
#ifndef GGML_USE_CUBLAS_SYCL_VULKAN
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS/SYCL/Vulkan. Setting a tensor split has no effect.\n");
#endif // GGML_USE_CUBLAS_SYCL
} else if (arg == "--no-mmap") {
params.use_mmap = false;
@ -943,6 +959,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" --repeat-penalty N penalize repeat sequence of tokens (default: %.1f, 1.0 = disabled)\n", (double)sparams.penalty_repeat);
printf(" --presence-penalty N repeat alpha presence penalty (default: %.1f, 0.0 = disabled)\n", (double)sparams.penalty_present);
printf(" --frequency-penalty N repeat alpha frequency penalty (default: %.1f, 0.0 = disabled)\n", (double)sparams.penalty_freq);
printf(" --dynatemp-range N dynamic temperature range (default: %.1f, 0.0 = disabled)\n", (double)sparams.dynatemp_range);
printf(" --dynatemp-exp N dynamic temperature exponent (default: %.1f)\n", (double)sparams.dynatemp_exponent);
printf(" --mirostat N use Mirostat sampling.\n");
printf(" Top K, Nucleus, Tail Free and Locally Typical samplers are ignored if used.\n");
printf(" (default: %d, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)\n", sparams.mirostat);