CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : support layer reuse (#15504)

Browse Source 
* kv-cache : support layer reuse

ggml-ci

* cont : update comments [no ci]
This commit is contained in:
Georgi Gerganov
2025-08-24 13:07:07 +03:00
committed by GitHub
parent c9a24fb932
commit b730706a49
12 changed files with 203 additions and 136 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
src/llama-memory-recurrent.h
View File

@@ -15,18 +15,14 @@
// see the implementation of llama_kv_cache_context_i for an example how to do it
class llama_memory_recurrent : public llama_memory_i {
public:
// this callback is used to filter out layers that should not be included in the cache
using layer_filter_cb = std::function<bool(int32_t il)>;
llama_memory_recurrent(
const llama_model & model,
layer_filter_cb && filter,
ggml_type type_r,
ggml_type type_s,
bool offload,
uint32_t mem_size,
uint32_t n_seq_max);
const llama_model & model,
ggml_type type_r,
ggml_type type_s,
bool offload,
uint32_t mem_size,
uint32_t n_seq_max,
const layer_filter_cb & filter);
~llama_memory_recurrent() = default;