CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : refactor the update/defrag mechanism (#13988)

Browse Source 
* kv-cache : refactor update mechanism

ggml-ci

* memory : improve status handling

* defrag : reset head + add comments

ggml-ci

* cont : minor fixes

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-04 18:58:20 +03:00
committed by GitHub
parent 2589ad3704
commit 3e63a58ef7
11 changed files with 340 additions and 191 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llama-kv-cache-recurrent.h
View File

@@ -52,9 +52,7 @@ public:
llama_memory_state_ptr init_full() override;
bool update(llama_context & lctx) override;
void defrag_sched(float thold) override;
llama_memory_state_ptr init_update(llama_context * lctx, bool optimize) override;
bool prepare(const std::vector<llama_ubatch> & ubatches);