Skip to content

Update torch2.0.mdx #2748

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pcuenca merged 1 commit into from
Mar 20, 2023
Merged

Update torch2.0.mdx #2748

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions docs/source/en/optimization/torch2.0.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,7 @@ pip install --pre torch torchvision --index-url https://download.pytorch.org/whl
## Benchmark

We conducted a simple benchmark on different GPUs to compare vanilla attention, xFormers, `torch.nn.functional.scaled_dot_product_attention` and `torch.compile+torch.nn.functional.scaled_dot_product_attention`.
For the benchmark we used the the [stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) model with 50 steps. The `xFormers` benchmark is done using the `torch==1.13.1` version, while the accelerated transformers optimizations are tested using nightly versions of PyTorch 2.0. The tables below summarize the results we got.
For the benchmark we used the [stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) model with 50 steps. The `xFormers` benchmark is done using the `torch==1.13.1` version, while the accelerated transformers optimizations are tested using nightly versions of PyTorch 2.0. The tables below summarize the results we got.

The `Speed over xformers` columns denote the speed-up gained over `xFormers` using the `torch.compile+torch.nn.functional.scaled_dot_product_attention`.

Expand Down Expand Up @@ -202,7 +202,7 @@ Using `torch.compile` in addition to the accelerated transformers implementation



(1) Batch Size >= 32 requires enable_vae_slicing() because of https://github.com/pytorch/pytorch/issues/81665
This is required for PyTorch 1.13.1, and also for PyTorch 2.0 and batch size of 64
(1) Batch Size >= 32 requires enable_vae_slicing() because of https://github.com/pytorch/pytorch/issues/81665.
This is required for PyTorch 1.13.1, and also for PyTorch 2.0 and batch size of 64.

For more details about how this benchmark was run, please refer to [this PR](https://github.com/huggingface/diffusers/pull/2303).
For more details about how this benchmark was run, please refer to [this PR](https://github.com/huggingface/diffusers/pull/2303).