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:
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	ci/README.md
#	ci/run.sh
#	flake.lock
#	ggml-metal.m
#	ggml-opencl.cpp
#	ggml-vulkan-shaders.hpp
#	ggml-vulkan.cpp
#	ggml-vulkan.h
#	ggml.c
#	ggml_vk_generate_shaders.py
#	llama.cpp
#	llama.h
#	pocs/vdot/vdot.cpp
#	tests/test-llama-grammar.cpp
#	tests/test-sampling.cpp
This commit is contained in:
Concedo 2024-01-29 23:12:09 +08:00
commit f73de33f74
37 changed files with 37432 additions and 21072 deletions
Download patch file Download diff file Expand all files Collapse all files

26
common/common.cpp
View file

@ -43,6 +43,10 @@
#pragma warning(disable: 4244 4267) // possible loss of data
#endif
#if (defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL))
#define GGML_USE_CUBLAS_SYCL
#endif
int32_t get_num_physical_cores() {
#ifdef __linux__
// enumerate the set of thread siblings, num entries is num cores
@ -600,9 +604,9 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
break;
}
params.main_gpu = std::stoi(argv[i]);
#ifndef GGML_USE_CUBLAS
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. Setting the main GPU has no effect.\n");
#endif // GGML_USE_CUBLAS
#ifndef GGML_USE_CUBLAS_SYCL
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS/SYCL. Setting the main GPU has no effect.\n");
#endif // GGML_USE_CUBLAS_SYCL
} else if (arg == "--split-mode" || arg == "-sm") {
if (++i >= argc) {
invalid_param = true;
@ -619,9 +623,10 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
invalid_param = true;
break;
}
#ifndef GGML_USE_CUBLAS
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. Setting the split mode has no effect.\n");
#endif // GGML_USE_CUBLAS
#ifndef GGML_USE_CUBLAS_SYCL
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS/SYCL. Setting the split mode has no effect.\n");
#endif // GGML_USE_CUBLAS_SYCL
} else if (arg == "--tensor-split" || arg == "-ts") {
if (++i >= argc) {
invalid_param = true;
@ -644,9 +649,9 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
params.tensor_split[i] = 0.0f;
}
}
#ifndef GGML_USE_CUBLAS
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. Setting a tensor split has no effect.\n");
#endif // GGML_USE_CUBLAS
#ifndef GGML_USE_CUBLAS_SYCL
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS/SYCL. Setting a tensor split has no effect.\n");
#endif // GGML_USE_CUBLAS_SYCL
} else if (arg == "--no-mmap") {
params.use_mmap = false;
} else if (arg == "--numa") {
@ -1008,7 +1013,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" fraction of the model to offload to each GPU, comma-separated list of proportions, e.g. 3,1\n");
printf(" -mg i, --main-gpu i the GPU to use for the model (with split-mode = none),\n");
printf(" or for intermediate results and KV (with split-mode = row) (default: %d)\n", params.main_gpu);
#endif
#endif // LLAMA_SUPPORTS_GPU_OFFLOAD
printf(" --verbose-prompt print a verbose prompt before generation (default: %s)\n", params.verbose_prompt ? "true" : "false");
printf(" --no-display-prompt don't print prompt at generation (default: %s)\n", !params.display_prompt ? "true" : "false");
printf(" -gan N, --grp-attn-n N\n");
@ -1515,7 +1520,6 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
fprintf(stream, "cpu_has_avx512: %s\n", ggml_cpu_has_avx512() ? "true" : "false");
fprintf(stream, "cpu_has_avx512_vbmi: %s\n", ggml_cpu_has_avx512_vbmi() ? "true" : "false");
fprintf(stream, "cpu_has_avx512_vnni: %s\n", ggml_cpu_has_avx512_vnni() ? "true" : "false");
fprintf(stream, "cpu_has_blas: %s\n", ggml_cpu_has_blas() ? "true" : "false");
fprintf(stream, "cpu_has_cublas: %s\n", ggml_cpu_has_cublas() ? "true" : "false");
fprintf(stream, "cpu_has_clblast: %s\n", ggml_cpu_has_clblast() ? "true" : "false");
fprintf(stream, "cpu_has_fma: %s\n", ggml_cpu_has_fma() ? "true" : "false");