OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2024-12-29 19:05:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

torch.empty can create issues; use torch.zeros

Browse Source 
For MPS, using a tensor created with `torch.empty()` can cause `torch.baddbmm()` to include NaNs in the tensor it returns, even though `beta=0`. However, with a tensor of shape [1,1,1], there should be a negligible performance difference between `torch.empty()` and `torch.zeros()` anyway, so it's better to just use `torch.zeros()` for this and avoid unnecessarily creating issues.
This commit is contained in:
brkirch 2023-07-25 03:03:06 -04:00
parent 87dd685224
commit 2489252099
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
modules/sub_quadratic_attention.py
View File

@ -58,7 +58,7 @@ def _summarize_chunk(
scale: float,
) -> AttnChunk:
attn_weights = torch.baddbmm(
torch.empty(1, 1, 1, device=query.device, dtype=query.dtype),
torch.zeros(1, 1, 1, device=query.device, dtype=query.dtype),
query,
key.transpose(1,2),
alpha=scale,
@ -121,7 +121,7 @@ def _get_attention_scores_no_kv_chunking(
scale: float,
) -> Tensor:
attn_scores = torch.baddbmm(
torch.empty(1, 1, 1, device=query.device, dtype=query.dtype),
torch.zeros(1, 1, 1, device=query.device, dtype=query.dtype),
query,
key.transpose(1,2),
alpha=scale,