Skip to main content

Provide a library with fast transformer implementations.

Project description

Transformers are very successful models that achieve state of the art performance in many natural language tasks. However, it is very difficult to scale them to long sequences due to the quadratic scaling of self-attention.

This library was developed for our research on fast attention for transformers. You can find a list of our papers in the docs as well as related papers and papers that we have implemented.


The following code builds a transformer with softmax attention and one with linear attention and compares the time required by each to encode a sequence with 1000 elements.

import torch
from import TransformerEncoderBuilder

# Create the builder for our transformers
builder = TransformerEncoderBuilder.from_kwargs(

# Build a transformer with softmax attention
builder.attention_type = "full"
softmax_model = builder.get()

# Build a transformer with linear attention
builder.attention_type = "linear"
linear_model = builder.get()

# Construct the dummy input
X = torch.rand(10, 1000, 8*64)

# Prepare everythin for CUDA
X = X.cuda()

# Warmup the GPU
with torch.no_grad():

# Measure the execution time
softmax_start = torch.cuda.Event(enable_timing=True)
softmax_end = torch.cuda.Event(enable_timing=True)
linear_start = torch.cuda.Event(enable_timing=True)
linear_end = torch.cuda.Event(enable_timing=True)

with torch.no_grad():
    y = softmax_model(X)
    print("Softmax: ", softmax_start.elapsed_time(softmax_end), "ms")
    # Softmax: 144 ms (on a GTX1080Ti)

with torch.no_grad():
    y = linear_model(X)
    print("Linear: ", linear_start.elapsed_time(linear_end), "ms")
    # Linear: 68 ms (on a GTX1080Ti)

Dependencies & Installation

The fast transformers library has the following dependencies:

  • PyTorch
  • C++ toolchain
  • CUDA toolchain (if you want to compile for GPUs)

For most machines installation should be as simple as:

pip install --user pytorch-fast-transformers

Note: macOS users should ensure they have llvm and libomp installed. Using the homebrew package manager, this can be accomplished by running brew install llvm libomp.


There exists a dedicated documentation site but you are also encouraged to read the source code.



To read about the theory behind some attention implementations in this library we encourage you to follow our research.

  • Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention (2006.16236)
  • Fast Transformers with Clustered Attention (2007.04825)

If you found our research helpful or influential please consider citing

    author = {Katharopoulos, A. and Vyas, A. and Pappas, N. and Fleuret, F.},
    title = {Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention},
    booktitle = {Proceedings of the International Conference on Machine Learning (ICML)},
    year = {2020}

    author={Vyas, A. and Katharopoulos, A. and Fleuret, F.},
    title={Fast Transformers with Clustered Attention},
    booktitle = {Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)},

By others

  • Efficient Attention: Attention with Linear Complexities (1812.01243)
  • Linformer: Self-Attention with Linear Complexity (2006.04768)
  • Reformer: The Efficient Transformer (2001.04451)

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pytorch-fast-transformers-0.4.0.tar.gz (93.6 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page