tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-28 21:23:55 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : auto-batch preparation (#13845)

Browse Source 
* llama : auto-batch

ggml-ci

* context : simplify if branching
This commit is contained in:
Georgi Gerganov
2025-05-31 12:55:57 +03:00
committed by GitHub
parent 51fa76f172
commit 3f55f781f1
5 changed files with 67 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-context.h
View File

@@ -50,8 +50,9 @@ struct llama_context {
llama_kv_cache * get_kv_self();
const llama_kv_cache * get_kv_self() const;
// return true of the KV cache was updated
// TODO: remove
void kv_self_update();
bool kv_self_update();
enum llama_pooling_type pooling_type() const;