wmantly/llama.cpp-xrip
1
0 Fork 0
Code Issues Pull Requests Actions 34 Packages Projects Releases Wiki Activity

ggml-cuda: fattn do not check oob if k_VKQ_max = (k_VKQ_max - nbatch_fa) (#30572)

Browse Source
This commit is contained in:
thelittlefireman authored and GitHub committed 2026-10-18 10:59:06 +02:00
1 parent 547208dca2
commit 5aeac37a35
1 file changed
+1 -1
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/fattn-tile.cuh
+1 -1
View File
@@ -955,7 +955,7 @@ static __global__ void flash_attn_tile(
if (ncols2 == 1) {
// Branch with out-of-bounds checks.
int k_VKQ_0 = blockIdx.y*nbatch_fa;
while (k_VKQ_0 < k_VKQ_max - nbatch_fa) {
while (k_VKQ_0 <= k_VKQ_max - nbatch_fa) {
constexpr bool oob_check = false;
flash_attn_tile_iter<warp_size, nwarps, ncols1, ncols2, DKQ, DV, nbatch_fa, nbatch_K, use_logit_softcap, oob_check>
(Q_tmp, K_h2, V_h2, maskh, ne01, logit_softcap, slope, KQ, KV_tmp,