mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-16 13:12:51 -04:00
de2ef53a4b
* kv-cache : rework kv_cell ggml-ci * kv-cells : use "shift" instead of "delta" consistently ggml-ci * llama : add llama_max_parallel_sequences() ggml-ci * kv-cells : update comments [no ci] * context : fail upon construction if sequences exceed max value ggml-ci * kv-cells : get_pos() -> pos_get() + comments ggml-ci * kv-cells : fix tracking of "used" cells ggml-ci
33 lines
1.1 KiB
C++
33 lines
1.1 KiB
C++
#pragma once
|
|
|
|
#include "llama.h"
|
|
|
|
struct llama_memory_params {
|
|
// kv cache
|
|
ggml_type type_k;
|
|
ggml_type type_v;
|
|
|
|
// use full-size SWA cache
|
|
bool swa_full;
|
|
};
|
|
|
|
// 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 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 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;
|
|
};
|