ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-28 09:04:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Chnage KQ mask padding to 64 (#574)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-07-03 10:43:27 +02:00
committed by GitHub
parent c9148ba0b4
commit de7a4403b0
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml.h
View File

@@ -1957,7 +1957,7 @@ extern "C" {
int min_entries,
float thresh);
#define GGML_KQ_MASK_PAD 32
#define GGML_KQ_MASK_PAD 64
// q: [n_embd, n_batch, n_head, 1]
// k: [n_embd, n_kv, n_head_kv, 1]