talk-llama : sync llama.cpp

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-13 13:20:19 +03:00
parent a14c89aefa
commit f890560575
25 changed files with 2847 additions and 1125 deletions

View File

@ -2,12 +2,22 @@
#include "llama.h"
struct llama_memory_params {
// kv cache
ggml_type type_k;
ggml_type type_v;
// parameters for other types of memory
// ...
};
// general concept of LLM memory
// the KV cache is a type of LLM memory, but there can be other types
class llama_memory_i {
public:
virtual ~llama_memory_i() = default;
virtual void clear() = 0;
virtual void defrag() = 0;
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;