Torch2.0 scaled_dot_product_attention processor #2303
add sdpa processor
63b38841
don't use it by default
ae47101c
Merge branch 'main' of https://github.com/huggingface/diffusers into …
18cf0022
add some checks and style
92065dc8
typo
9656f01e
Merge branch 'main' into torch2.0
62850999
support torch sdpa in dreambooth example
00849d0d
Merge branch 'main' into torch2.0
0554cd6d
use torch attn proc by default when available
e25cecdd
Merge branch 'torch2.0' of https://github.com/huggingface/diffusers i…
904b389b
typo
23a40eb7
add attn mask
640f875a
fix naming
aaa83eca
being doc
e28f299a
doc
4d6458c6
patil-suraj
marked this pull request as ready for review 2 years ago
Apply suggestions from code review
0b7eac8e
polish
907869b6
torctree
8be0286e
Apply suggestions from code review
967fed25
better name
34c6cdb8
style
4a38b12e
add benchamrk table
a21bb888
Update docs/source/en/optimization/torch2.0.mdx
59630d2e
up
b5c65657
Merge branch 'torch2.0' of https://github.com/huggingface/diffusers i…
a1e87eee
fix example
c5a7bd51
check if processor is None
88efe896
pcuenca
approved these changes
on 2023-02-17
Apply suggestions from code review
238ee954
add fp32 benchmakr
3607326b
Apply suggestions from code review
e45029dc
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub