ggml: CUDA: add head size 72 for flash-attn (#16962)

2025-11-03 14:29:11 +01:00
parent 070ff4d535
commit 622cd010ff
5 changed files with 44 additions and 5 deletions
@@ -0,0 +1,5 @@
+// This file has been autogenerated by generate_cu_files.py, do not edit manually.
+
+#include "../fattn-tile.cuh"
+
+DECL_FATTN_TILE_CASE(72, 72);