vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-16 20:09:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	Makefile
#	README.md
This commit is contained in:
Concedo 2023-11-27 14:06:14 +08:00
commit 8acd7be734
20 changed files with 1274 additions and 136 deletions
Download patch file Download diff file Expand all files Collapse all files

11
common/common.h
View file

@ -130,6 +130,7 @@ struct gpt_params {
bool numa = false; // attempt optimizations that help on some NUMA systems
bool verbose_prompt = false; // print prompt tokens before generation
bool infill = false; // use infill mode
bool dump_kv_cache = false; // dump the KV cache contents for debugging purposes
// multimodal models (see examples/llava)
std::string mmproj = ""; // path to multimodal projector
@ -226,3 +227,13 @@ std::string get_sortable_timestamp();
void dump_non_result_info_yaml(
FILE * stream, const gpt_params & params, const llama_context * lctx,
const std::string & timestamp, const std::vector<int> & prompt_tokens, const char * model_desc);
//
// KV cache utils
//
// Dump the KV cache view with the number of sequences per cell.
void dump_kv_cache_view(const llama_kv_cache_view & view, int row_size = 80);
// Dump the KV cache view showing individual sequences in each cell (long output).
void dump_kv_cache_view_seqs(const llama_kv_cache_view & view, int row_size = 40);