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 commit '6986c7835a' into concedo_experimental

Browse source 
# Conflicts:
#	README.md
This commit is contained in:
Concedo 2023-05-20 11:30:51 +08:00
commit 010b2753d9
11 changed files with 192 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama.cpp
View file

@ -829,10 +829,9 @@ static bool kv_cache_init(
struct llama_context_params llama_context_default_params() {
struct llama_context_params result = {
/*.n_ctx =*/ 512,
/*.n_parts =*/ -1,
/*.gpu_layers =*/ 0,
/*.seed =*/ -1,
/*.f16_kv =*/ false,
/*.f16_kv =*/ true,
/*.logits_all =*/ false,
/*.vocab_only =*/ false,
/*.use_mmap =*/ true,
@ -965,7 +964,7 @@ static void llama_model_load_internal(
size_t ctx_size;
size_t mmapped_size;
ml->calc_sizes(&ctx_size, &mmapped_size);
fprintf(stderr, "%s: ggml ctx size = %6.2f KB\n", __func__, ctx_size/1024.0);
fprintf(stderr, "%s: ggml ctx size = %6.2f MB\n", __func__, ctx_size/1024.0/1024.0);
// print memory requirements
{