StableDiffusion/WebUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add workaround for MPS layer_norm on PyTorch 2.0

Browse Source 
On PyTorch 2.0, with MPS layer_norm only accepts float32 inputs. This was fixed shortly after 2.0 was finalized so the workaround can be applied with an exact version match.
This commit is contained in:
brkirch 2023-03-24 03:04:47 -04:00
parent c5142e2fbe
commit 27fe3eb6a9
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
modules/mac_specific.py
View File

@ -54,4 +54,6 @@ if has_mps:
CondFunc('torch.cumsum', cumsum_fix_func, None)
CondFunc('torch.Tensor.cumsum', cumsum_fix_func, None)
CondFunc('torch.narrow', lambda orig_func, *args, **kwargs: orig_func(*args, **kwargs).clone(), None)
if version.parse(torch.__version__) == version.parse("2.0"):
# MPS workaround for https://github.com/pytorch/pytorch/issues/96113
CondFunc('torch.nn.functional.layer_norm', lambda orig_func, x, normalized_shape, weight, bias, eps, **kwargs: orig_func(x.float(), normalized_shape, weight.float() if weight is not None else None, bias.float() if bias is not None else bias, eps).to(x.dtype), lambda *args, **kwargs: len(args) == 6)