Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-27 21:46:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

metal : fix mask bounds in flash attention block pre-pass (#29220)

Browse Source
This commit is contained in:
Foad Abo Dahood
2026-09-21 20:31:56 +03:00
committed by GitHub
parent c641dfa833
commit fb34fc262c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/kernels/fa.metal
+1 -1
View File
@@ -142,7 +142,7 @@ kernel void kernel_flash_attn_ext_blk(
const int32_t i1 = tgpig[1];
const int32_t i0 = tgpig[0];
char res = i0*C + C > args.ne30 ? 1 : 0;
char res = i0*C + C > args.ne30 || i1*Q + Q > args.ne31 ? 1 : 0;
device const half * mask_src = (device const half *) (mask + (i1*Q)*args.nb31 + i2*args.nb32 + i3*args.nb33) + i0*C + tiisg;