c642bc014c
* kv-cache : serparate recurrent vs non-recurrent impl (wip) ggml-ci * kv-cache : init -> contructor + add llama_memory_params ggml-ci * kv-cache : fix callback reference ggml-ci * context : llama_kv_cache -> llama_memory_i ggml-ci * context : move memory creation logic to model ggml-ci * llama : remove reference of memory during encode ggml-ci * kv-cache : hide padding details in the implementation ggml-ci * kv-cache : add ubatch_next() ggml-ci * context : simplify sbatch logic ggml-ci * kv-cache : hide defrag logic in the implementation ggml-ci * context : hide kv cache details in implementation ggml-ci * build : fix ggml-ci * cont : another fix ggml-ci * kv-cache : simplify interface (wip) ggml-ci * kv-cache : use separate KV cell structs for unified/recurrent ggml-ci * kv-cache : clean-up ggml-ci * model : better llama_model::create_model() signature ggml-ci * kv-cache : fix recurrent seq_rm() ggml-ci * kv-cache : replace `struct callbacks` with `llama_model &` ggml-ci * kv-cache : replace `struct graph_params` with `llama_context &` ggml-ci * kv-cache : fix offload check ggml-ci * context : avoid passing unique_ptr ggml-ci * kv-cache : avoid using the backends from the llama_context ref #13113 ggml-ci * kv-cache : more consistent debug logs [no ci] * kv-cache : do not pass the full llama_context for kv graphs ggml-ci * kv-cache : remove comment * kv-cache : ggml_rope_ext_inplace -> ggml_rope_ext ggml-ci * kv-cache : fix recurrent multi-user case ggml-ci * memory : remove comments [no ci]
31 lines
1,016 B
C++
31 lines
1,016 B
C++
#pragma once
|
|
|
|
#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 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) const = 0;
|
|
|
|
virtual bool get_can_edit() const = 0;
|
|
};
|