vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-17 04:19:40 +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

5
common/common.h
View file

@ -37,7 +37,7 @@
int32_t get_num_physical_cores();
struct gpt_params {
uint32_t seed = -1; // RNG seed
uint32_t seed = LLAMA_DEFAULT_SEED; // RNG seed
int32_t n_threads = get_num_physical_cores();
int32_t n_threads_draft = -1;
@ -47,11 +47,10 @@ struct gpt_params {
int32_t n_ctx = 512; // context size
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_draft = 8; // number of tokens to draft during speculative decoding
int32_t n_draft = 5; // number of tokens to draft during speculative decoding
int32_t n_chunks = -1; // max number of chunks to process (-1 = unlimited)
int32_t n_parallel = 1; // number of parallel sequences to decode
int32_t n_sequences = 1; // number of sequences to decode
float p_accept = 0.5f; // speculative decoding accept probability
float p_split = 0.1f; // speculative decoding split probability
int32_t n_gpu_layers = -1; // number of layers to store in VRAM (-1 - use default)
int32_t n_gpu_layers_draft = -1; // number of layers to store in VRAM for the draft model (-1 - use default)