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:
#	.devops/nix/package.nix
#	README.md
#	ggml-metal.m
#	llama.cpp
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-03-05 15:54:05 +08:00
commit ac43e0115c
28 changed files with 1225 additions and 309 deletions
Download patch file Download diff file Expand all files Collapse all files

9
common/common.cpp
View file

@ -514,12 +514,6 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
break;
}
params.n_sequences = std::stoi(argv[i]);
} else if (arg == "--p-accept" || arg == "-pa") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.p_accept = std::stof(argv[i]);
} else if (arg == "--p-split" || arg == "-ps") {
if (++i >= argc) {
invalid_param = true;
@ -1045,7 +1039,6 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" --chunks N max number of chunks to process (default: %d, -1 = all)\n", params.n_chunks);
printf(" -np N, --parallel N number of parallel sequences to decode (default: %d)\n", params.n_parallel);
printf(" -ns N, --sequences N number of sequences to decode (default: %d)\n", params.n_sequences);
printf(" -pa N, --p-accept N speculative decoding accept probability (default: %.1f)\n", (double)params.p_accept);
printf(" -ps N, --p-split N speculative decoding split probability (default: %.1f)\n", (double)params.p_split);
printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: disabled)\n");
printf(" --mmproj MMPROJ_FILE path to a multimodal projector file for LLaVA. see examples/llava/README.md\n");
@ -1300,7 +1293,7 @@ struct llama_context_params llama_context_params_from_gpt_params(const gpt_param
cparams.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;
cparams.seed = params.seed;
cparams.logits_all = params.logits_all;
cparams.embedding = params.embedding;
cparams.embeddings = params.embedding;
cparams.rope_scaling_type = params.rope_scaling_type;
cparams.rope_freq_base = params.rope_freq_base;
cparams.rope_freq_scale = params.rope_freq_scale;