CUDA: faster tile FA, add oob checks, more HSs (#16492)

2025-10-11 20:54:32 +02:00
parent a3cb04744f
commit 11f0af5504
18 changed files with 1358 additions and 784 deletions
--- a/ggml/src/ggml-cuda/fattn-wmma-f16.cuh
+++ b/ggml/src/ggml-cuda/fattn-wmma-f16.cuh
@@ -1,3 +1,5 @@
+#pragma once
+
 #include "common.cuh"

 #if (!defined(GGML_USE_HIP) && __CUDA_ARCH__ >= GGML_CUDA_CC_VOLTA) || defined(GGML_USE_MUSA)