Skip to content

Commit d82669b

Browse files
pcuencaJimmy
authored and
Jimmy
committed
Small update to "Next steps" section (huggingface#3443)
Small update to "Next steps" section: - PyTorch 2 is recommended. - Updated improvement figures.
1 parent cdea032 commit d82669b

File tree

1 file changed

+3
-3
lines changed

1 file changed

+3
-3
lines changed

docs/source/en/stable_diffusion.mdx

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -266,6 +266,6 @@ image_grid(images)
266266

267267
In this tutorial, you learned how to optimize a [`DiffusionPipeline`] for computational and memory efficiency as well as improving the quality of generated outputs. If you're interested in making your pipeline even faster, take a look at the following resources:
268268

269-
- Enable [xFormers](./optimization/xformers) memory efficient attention mechanism for faster speed and reduced memory consumption.
270-
- Learn how in [PyTorch 2.0](./optimization/torch2.0), [`torch.compile`](https://pytorch.org/docs/stable/generated/torch.compile.html) can yield 2-9% faster inference speed.
271-
- Many optimization techniques for inference are also included in this memory and speed [guide](./optimization/fp16), such as memory offloading.
269+
- Learn how [PyTorch 2.0](./optimization/torch2.0) and [`torch.compile`](https://pytorch.org/docs/stable/generated/torch.compile.html) can yield 5 - 300% faster inference speed.
270+
- If you can't use PyTorch 2, we recommend you install [xFormers](./optimization/xformers). Its memory-efficient attention mechanism works great with PyTorch 1.13.1 for faster speed and reduced memory consumption.
271+
- Other optimization techniques, such as model offloading, are covered in [this guide](./optimization/fp16).

0 commit comments

Comments
 (0)