ggml : fix FA mask dim 2 and 3 (#14505)

* ggml : fix FA mask dim 2 and 3 ggml-ci * backends : unsupport batched FA in CUDA and Vulkan ggml-ci * vulkan : disable FA for mask->ne[2] != 1
2025-07-03 10:46:57 +03:00
parent d4cdd9c1c3
commit 9067487c44
9 changed files with 26 additions and 15 deletions
--- a/ggml/src/ggml-metal/ggml-metal-impl.h
+++ b/ggml/src/ggml-metal/ggml-metal-impl.h
@@ -230,8 +230,10 @@ typedef struct {
    uint64_t nb22;
    uint64_t nb23;
    int32_t  ne32;
+    int32_t  ne33;
    uint64_t nb31;
    uint64_t nb32;
+    uint64_t nb33;
    int32_t  ne1;
    int32_t  ne2;
    float    scale;