[Perf][Diffusion] Run MammothModa2 DiT attention through the shared attention layer (#7094)
Signed-off-by: MrlixiangWE <mrdanaer@gmail.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
1 parent
13b85c5622
commit
220366db00
7 files changed
+582
-108
No files matched your search
@@ -233,6 +233,7 @@ def _fake_ltx_parallel_attention():
|
||||
|
||||
layer = object.__new__(ltx2_transformer._LTX2ParallelAttention)
|
||||
nn.Module.__init__(layer)
|
||||
layer.allow_fp32_fallback = False
|
||||
layer.attn_backend = Backend
|
||||
layer.attention = SimpleNamespace(forward=run("native"))
|
||||
layer.sdpa_fallback = SimpleNamespace(forward=run("sdpa"))
|
||||
|
||||
Reference in new issue
Block a user