extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-10 06:48:01 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-27 17:08:24 +03:00
parent 546928c33f
commit 26eb48cb08
18 changed files with 1968 additions and 1178 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/talk-llama/llama-memory.h
View File

@ -7,8 +7,8 @@ struct llama_memory_params {
ggml_type type_k;
ggml_type type_v;
// parameters for other types of memory
// ...
// use full-size SWA cache
bool swa_full;
};
// general concept of LLM memory
@ -22,9 +22,10 @@ public:
virtual bool seq_rm (llama_seq_id seq_id, llama_pos p0, llama_pos p1) = 0;
virtual void seq_cp (llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) = 0;
virtual void seq_keep(llama_seq_id seq_id) = 0;
virtual void seq_add (llama_seq_id seq_id, llama_pos p0, llama_pos p1, llama_pos delta) = 0;
virtual void seq_add (llama_seq_id seq_id, llama_pos p0, llama_pos p1, llama_pos shift) = 0;
virtual void seq_div (llama_seq_id seq_id, llama_pos p0, llama_pos p1, int d) = 0;
virtual llama_pos seq_pos_min(llama_seq_id seq_id) const = 0;
virtual llama_pos seq_pos_max(llama_seq_id seq_id) const = 0;
virtual bool get_can_edit() const = 0;