CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-20 12:07:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

graph : reuse recurrent graphs

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-09 19:36:17 +03:00
parent ca00002f2d
commit 12a9751d46
2 changed files with 17 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-graph.h
View File

@@ -224,6 +224,8 @@ public:
void set_input(const llama_ubatch * ubatch) override;
bool can_reuse(const llm_graph_params & params) override;
ggml_tensor * s_copy; // I32 [n_rs]
// views of s_copy, computed once per graph