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

Disentangled Lifespan Face Synthesis

Code for the Convolutional Vision Transformer (ConViT)

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution (CVPR2021)

Python codes for Lite Audio-Visual Speech Enhancement.

A Deep Reinforcement Learning Framework for Stock Market Trading

Reinforcement learning library in JAX.

In this project, we develop a face recognize platform based on MTCNN object-detection netcwork and FaceNet self-supervised network.

Temporal Knowledge Graph Reasoning Triggered by Memories

Rotary Transformer

A PyTorch library and evaluation platform for end-to-end compression research

Code for DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning

Deep Q-learning for playing chrome dino game

NeurIPS 2021 paper 'Representation Learning on Spatial Networks' code

PixelPick This is an official implementation of the paper "All you need are a few pixels: semantic segmentation with PixelPick."

StyleGAN2-ada for practice

A transformer-based method for Healthcare Image Captioning in Vietnamese

Sign Language Transformers (CVPR'20)

The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".

An SMPC companion library for Syft

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)