Attention for PyTorch with Linear Memory Footprint

Unofficially implements https://arxiv.org/abs/2112.05682 to get Linear Memory Cost on Attention (+ some sidekick speedup on the GPU when compared to reference implementation in JAX)

Usage:

git clone https://github.com/CHARM-Tx/linear_mem_attention_pytorch
cd linear_mem_attention_pytorch
python setup.py install

Usage:

High Level

from linear_mem_attention_torch.fast_attn import Attention

batch, length, features = 2, 2**8, 64
x, ctx = torch.randn(2, batch, length, features)
mask = torch.randn(batch, length) < 1.

attn = Attention(dim=features, heads = 8, dim_head = 64, bias=False)

# self-attn
v_self = attn(x, x, mask, query_chunk_size=1024, key_chunk_size=4096)

# cross-attn
v_cross = attn(x, ctx, mask, query_chunk_size=1024, key_chunk_size=4096)

Low level

from linear_mem_attention_torch import attention

batch, length, heads, features = 2, 2**8, 8, 64
mask = torch.randn(batch, length) < 1.
q, k, v = torch.randn(3, batch, length, heads, features)

v_ = attention(q, k, v, mask, query_chunk_size=1024, key_chunk_size=4096)

Benchmarks

See examples/example_benchamrk.ipynb for more information.

Citations:

@misc{rabe2021selfattention,
      title={Self-attention Does Not Need $O(n^2)$ Memory}, 
      author={Markus N. Rabe and Charles Staats},
      year={2021},
      eprint={2112.05682},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

Attention for PyTorch with Linear Memory Footprint

Related tags

Overview

Attention for PyTorch with Linear Memory Footprint

Usage:

Usage:

High Level

Low level

Benchmarks

Citations:

Owner

Automatic detection and classification of Covid severity degree in LUS (lung ultrasound) scans

SegNet including indices pooling for Semantic Segmentation with tensorflow and keras

基于PaddleOCR搭建的OCR server... 离线部署用

[NeurIPS 2021] “Improving Contrastive Learning on Imbalanced Data via Open-World Sampling”,

Run Keras models in the browser, with GPU support using WebGL

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021)

RoFormer_pytorch

Nest - A flexible tool for building and sharing deep learning modules

[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI

GuideDog is an AI/ML-based mobile app designed to assist the lives of the visually impaired, 100% voice-controlled

Dist2Dec: A Simplicial Neural Network for Homology Localization

[CVPR 2021] VirTex: Learning Visual Representations from Textual Annotations

Shitty gaze mouse controller

Libraries, tools and tasks created and used at DeepMind Robotics.

Uncertain natural language inference

ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton (AAAI'22)

Protect against subdomain takeover

Pretraining Representations For Data-Efficient Reinforcement Learning

Fast image augmentation library and an easy-to-use wrapper around other libraries