wmantly/llama.cpp-xrip
1
0 Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

Merge branch 'ggml-org:master' into master

Browse Source
This commit is contained in:
Ilya Maslennikov authored and GitHub committed 2026-09-21 22:31:16 +03:00
2 parents c3530049be fb34fc262c
commit ee422754be
1 file changed
+1 -1
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;