Pytorch library for fast transformer implementations

Overview

Fast Transformers

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.

Quick-start

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 fast_transformers.builders import TransformerEncoderBuilder

# Create the builder for our transformers
builder = TransformerEncoderBuilder.from_kwargs(
    n_layers=8,
    n_heads=8,
    query_dimensions=64,
    value_dimensions=64,
    feed_forward_dimensions=1024
)

# 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()
softmax_model.cuda()
softmax_model.eval()
linear_model.cuda()
linear_model.eval()

# Warmup the GPU
with torch.no_grad():
    softmax_model(X)
    linear_model(X)
torch.cuda.synchronize()

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

with torch.no_grad():
    linear_start.record()
    y = linear_model(X)
    linear_end.record()
    torch.cuda.synchronize()
    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.

Documentation

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

Research

Ours

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

@inproceedings{katharopoulos_et_al_2020,
    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}
}

@article{vyas_et_al_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)},
    year={2020}
}

By others

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

Support, License and Copyright

This software is distributed with the MIT license which pretty much means that you can use it however you want and for whatever reason you want. All the information regarding support, copyright and the license can be found in the LICENSE file in the repository.

Owner
Idiap Research Institute
Idiap Research Institute
PINN(s): Physics-Informed Neural Network(s) for von Karman vortex street

PINN(s): Physics-Informed Neural Network(s) for von Karman vortex street This is

ShotaDEGUCHI 2 Apr 18, 2022
This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".

Mesa: A Memory-saving Training Framework for Transformers This is the official PyTorch implementation for Mesa: A Memory-saving Training Framework for

Zhuang AI Group 105 Dec 06, 2022
Official code for 'Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentationon Complex Urban Driving Scenes'

PEBAL This repo contains the Pytorch implementation of our paper: Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentationon Complex Urba

Yu Tian 115 Dec 29, 2022
Code for the SIGGRAPH 2021 paper "Consistent Depth of Moving Objects in Video".

Consistent Depth of Moving Objects in Video This repository contains training code for the SIGGRAPH 2021 paper "Consistent Depth of Moving Objects in

Google 203 Jan 05, 2023
Source code for NAACL 2021 paper "TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference"

TR-BERT Source code and dataset for "TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference". The code is based on huggaface's transformers.

THUNLP 37 Oct 30, 2022
The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations This is the authors' implementation of Unsupervised Adversarial Learning of

Dwango Media Village 140 Dec 07, 2022
Wordle-solver - Wordle answer generation program in python

🟨 Wordle Solver 🟩 Wordle answer generation program in python ✔️ Requirements U

Dahyun Kang 4 May 28, 2022
Second-Order Neural ODE Optimizer, NeurIPS 2021 spotlight

Second-order Neural ODE Optimizer (NeurIPS 2021 Spotlight) [arXiv] ✔️ faster convergence in wall-clock time | ✔️ O(1) memory cost | ✔️ better test-tim

Guan-Horng Liu 39 Oct 22, 2022
Pynomial - a lightweight python library for implementing the many confidence intervals for the risk parameter of a binomial model

Pynomial - a lightweight python library for implementing the many confidence intervals for the risk parameter of a binomial model

Demetri Pananos 9 Oct 04, 2022
Referring Video Object Segmentation

Awesome-Referring-Video-Object-Segmentation Welcome to starts ⭐ & comments 💹 & sharing 😀 !! - 2021.12.12: Recent papers (from 2021) - welcome to ad

Explorer 57 Dec 11, 2022
Lightweight library to build and train neural networks in Theano

Lasagne Lasagne is a lightweight library to build and train neural networks in Theano. Its main features are: Supports feed-forward networks such as C

Lasagne 3.8k Dec 29, 2022
A self-supervised learning framework for audio-visual speech

AV-HuBERT (Audio-Visual Hidden Unit BERT) Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction Robust Self-Supervised A

Meta Research 431 Jan 07, 2023
This repo contains the code for the paper "Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging" that has been accepted to NeurIPS 2021.

Dugh-NeurIPS-2021 This repo contains the code for the paper "Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroi

Ali Hashemi 5 Jul 12, 2022
Perspective: Julia for Biologists

Perspective: Julia for Biologists 1. Examples Speed: Example 1 - Single cell data and network inference Domain: Single cell data Methodology: Network

Elisabeth Roesch 55 Dec 02, 2022
SAT Project - The first project I had done at General Assembly, performed EDA, data cleaning and created data visualizations

Project 1: Standardized Test Analysis by Adam Klesc Overview This project covers: Basic statistics and probability Many Python programming concepts Pr

Adam Muhammad Klesc 1 Jan 03, 2022
Minimal deep learning library written from scratch in Python, using NumPy/CuPy.

SmallPebble Project status: experimental, unstable. SmallPebble is a minimal/toy automatic differentiation/deep learning library written from scratch

Sidney Radcliffe 92 Dec 30, 2022
A simple configurable bot for sending arXiv article alert by mail

arXiv-newsletter A simple configurable bot for sending arXiv article alert by mail. Prerequisites PyYAML=5.3.1 arxiv=1.4.0 Configuration All config

SXKDZ 21 Nov 09, 2022
DFM: A Performance Baseline for Deep Feature Matching

DFM: A Performance Baseline for Deep Feature Matching Python (Pytorch) and Matlab (MatConvNet) implementations of our paper DFM: A Performance Baselin

143 Jan 02, 2023
Experiments for Neural Flows paper

Neural Flows: Efficient Alternative to Neural ODEs [arxiv] TL;DR: We directly model the neural ODE solutions with neural flows, which is much faster a

54 Dec 07, 2022
This repo contains the source code and a benchmark for predicting user's utilities with Machine Learning techniques for Computational Persuasion

Machine Learning for Argument-Based Computational Persuasion This repo contains the source code and a benchmark for predicting user's utilities with M

Ivan Donadello 4 Nov 07, 2022