metal : FA support F32 K and V and head size = 32 (#16531)
* metal : FA support F32 K and V and head size = 32 * graph : remove obsolete comment [no ci]
This commit is contained in:
1 parent
e38b7c6e9e
commit
e60f241eac
4 files changed
+106
-52
No files matched your search
@@ -1323,7 +1323,6 @@ ggml_tensor * llm_graph_context::build_attn_mha(
|
||||
|
||||
ggml_tensor * cur;
|
||||
|
||||
// TODO: replace hardcoded padding with ggml-provided padding
|
||||
if (cparams.flash_attn && kq_b == nullptr) {
|
||||
GGML_ASSERT(kq_b == nullptr && "Flash attention does not support KQ bias yet");
|
||||
|
||||
|
||||
Reference in new issue
Block a user