From 5aeac37a35b44fde4bdffaec9159f2fcb253b622 Mon Sep 17 00:00:00 2001
From: thelittlefireman <5165783+thelittlefireman@users.noreply.github.com>
Date: Sun, 18 Oct 2026 10:59:06 +0200
Subject: [PATCH] ggml-cuda: fattn do not check oob if k_VKQ_max = (k_VKQ_max -
 nbatch_fa) (#30572)

---
 ggml/src/ggml-cuda/fattn-tile.cuh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ggml/src/ggml-cuda/fattn-tile.cuh b/ggml/src/ggml-cuda/fattn-tile.cuh
index b5ea915e1..bd4a7710f 100644
--- a/ggml/src/ggml-cuda/fattn-tile.cuh
+++ b/ggml/src/ggml-cuda/fattn-tile.cuh
@@ -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,