Buckets:
xFormers
We recommend xFormers for both inference and training. In our tests, the optimizations performed in the attention blocks allow for both faster speed and reduced memory consumption.
Install xFormers from pip:
pip install xformers
The xFormers
pippackage requires the latest version of PyTorch. If you need to use a previous version of PyTorch, then we recommend installing xFormers from the source.
After xFormers is installed, you can use it with set_attention_backend() as shown in the Attention backends guide.
According to this issue, xFormers
v0.0.16cannot be used for training (fine-tune or DreamBooth) in some GPUs. If you observe this problem, please install a development version as indicated in the issue comments.
Xet Storage Details
- Size:
- 1.1 kB
- Xet hash:
- 8d017bc1eed0d6cf6e102742c391412b14d8a558479f5037b618c4b5111a67da
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.