mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-09 18:40:20 -04:00
e0dbec0bc6
* llama : refactor llama_context, llama_kv_cache, llm_build_context ggml-ci * graph : don't mutate the KV cache during defrag ggml-ci * context : reduce virtuals + remove test function ggml-ci * context : move interface implementation to source file + factory ggml-ci * graph : move KV cache build functions to llama_context impl ggml-ci * graph : remove model reference from build_pooling ggml-ci * graph : remove llama_model reference ggml-ci * kv_cache : provide rope factors ggml-ci * graph : rework inputs to use only unique_ptr, remove attn input abstraction ggml-ci * context : remove llama_context_i abstraction ggml-ci * context : clean-up ggml-ci * graph : clean-up ggml-ci * llama : remove redundant keywords (struct, enum) ggml-ci * model : adapt gemma3 ggml-ci * graph : restore same attention ops as on master ggml-ci * llama : remove TODO + fix indent ggml-ci
22 lines
850 B
C++
22 lines
850 B
C++
#pragma once
|
|
|
|
#include "llama.h"
|
|
|
|
// 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 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;
|
|
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_div (llama_seq_id seq_id, llama_pos p0, llama_pos p1, int d) = 0;
|
|
|
|
virtual llama_pos seq_pos_max(llama_seq_id seq_id) = 0;
|
|
|
|
virtual bool get_can_edit() const = 0;
|
|
};
|