Skip to content

Commit d91dc57

Browse files
authored
Update mps.mdx (huggingface#2749)
Fix typos
1 parent fdcff56 commit d91dc57

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

docs/source/en/optimization/mps.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -51,7 +51,7 @@ image = pipe(prompt).images[0]
5151

5252
M1/M2 performance is very sensitive to memory pressure. The system will automatically swap if it needs to, but performance will degrade significantly when it does.
5353

54-
We recommend you use _attention slicing_ to reduce memory pressure during inference and prevent swapping, particularly if your computer has lass than 64 GB of system RAM, or if you generate images at non-standard resolutions larger than 512 × 512 pixels. Attention slicing performs the costly attention operation in multiple steps instead of all at once. It usually has a performance impact of ~20% in computers without universal memory, but we have observed _better performance_ in most Apple Silicon computers, unless you have 64 GB or more.
54+
We recommend you use _attention slicing_ to reduce memory pressure during inference and prevent swapping, particularly if your computer has less than 64 GB of system RAM, or if you generate images at non-standard resolutions larger than 512 × 512 pixels. Attention slicing performs the costly attention operation in multiple steps instead of all at once. It usually has a performance impact of ~20% in computers without universal memory, but we have observed _better performance_ in most Apple Silicon computers, unless you have 64 GB or more.
5555

5656
```python
5757
pipeline.enable_attention_slicing()

0 commit comments

Comments
 (0)