tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 05:05:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : simplify + fix warning for recurrent models (#12756)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-04-04 21:48:10 +03:00
committed by GitHub
parent 1be76e4620
commit 3e1d29348b
4 changed files with 80 additions and 173 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-memory.h
View File

@ -15,7 +15,7 @@ public:
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 llama_pos seq_pos_max(llama_seq_id seq_id) const = 0;
virtual bool get_can_edit() const = 0;
};