Welcome to xFormers's documentation!
=====================================

(This fork increases level of verbosity of the sidebar)

*xFormers* is a PyTorch based library which hosts flexible Transformers parts.
They are interoperable and optimized building blocks, which can be optionally be combined
to create some state of the art models.

.. toctree::
   :maxdepth: 2
   :caption: Index
   :hidden:

   what_is_xformers

|
|

.. toctree::
   :maxdepth: 2
   :caption: Components Documentation

   components/ops
   components/attentions
   components/feedforward
   components/position_embedding
   components/reversible
   components/mha

|
|

.. toctree::
   :maxdepth: 2
   :caption: Tutorials and examples

   tutorials/sparse_vit
   tutorials/blocksparse
   tutorials/aotautograd_nvfuser
   tutorials/extend_attentions
   tutorials/use_attention
   tutorials/pytorch_encoder
   tutorials/reversible
   tutorials/triton
   tutorials/hierarchical

|
|

.. toctree::
   :maxdepth: 2
   :caption: Some custom parts

   custom_parts/index

|
|