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
This commit is contained in:
@@ -5018,8 +5018,10 @@ static bool ggml_metal_encode_node(
|
||||
/*.nb22 =*/ nb22,
|
||||
/*.nb23 =*/ nb23,
|
||||
/*.ne32 =*/ ne32,
|
||||
/*.ne33 =*/ ne33,
|
||||
/*.nb31 =*/ nb31,
|
||||
/*.nb32 =*/ nb32,
|
||||
/*.nb33 =*/ nb33,
|
||||
/*.ne1 =*/ ne1,
|
||||
/*.ne2 =*/ ne2,
|
||||
/*.scale =*/ scale,
|
||||
|
||||
Reference in New Issue
Block a user