Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"

Related tags

Deep Learningdeep-learningartificial-intelligencememory-efficientattention-mechanism
Overview

Memory Efficient Attention Pytorch

Implementation of a memory efficient multi-head attention as proposed in the paper, Self-attention Does Not Need O(n²) Memory. In addition, the module will take care of masking, causal masking, as well as cross attention.

Install

$ pip install memory-efficient-attention-pytorch

Usage

For autoregressive language model

import torch
from memory_efficient_attention_pytorch import Attention

attn = Attention(
    dim = 512,
    dim_head = 64,                # dimension per head
    heads = 8,                    # number of attention heads
    causal = True,                # autoregressive or not
    memory_efficient = True,      # whether to use memory efficient attention (can be turned off to test against normal attention)
    q_bucket_size = 1024,         # bucket size along queries dimension
    k_bucket_size = 2048          # bucket size along key / values dimension
).cuda()

x = torch.randn(1, 65536, 512).cuda()
out = attn(x) # (1, 65536, 512)

Cross attention

import torch
from memory_efficient_attention_pytorch import Attention

cross_attn = Attention(
    dim = 512,
    dim_head = 64,
    heads = 8,
    memory_efficient = True,
    q_bucket_size = 1024,
    k_bucket_size = 2048
).cuda()

x = torch.randn(1, 65536, 512).cuda()
context = torch.randn(1, 65536, 512).cuda()
mask = torch.ones(1, 65536).bool().cuda()

out = cross_attn(x, context = context, mask = mask) # (1, 65536, 512)
  • benchmark and see how much torch jit helps
  • look at Triton and Keops and see if either can be a fit

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}
}
@misc{liu2021swin,
    title   = {Swin Transformer V2: Scaling Up Capacity and Resolution},
    author  = {Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
    year    = {2021},
    eprint  = {2111.09883},
    archivePrefix = {arXiv},
    primaryClass = {cs.CV}
}
Comments
  • [feature request] Combining with flash attention?

    [feature request] Combining with flash attention?

    There is a new algorithm to optimize the qkv attention, https://github.com/HazyResearch/flash-attention https://arxiv.org/abs/2205.14135 It optimises the qkv attention part. Maybe you can look into integrating it with this.

    opened by Vbansal21 15
  • i did this, we could build on top

    i did this, we could build on top

    Hi there!

    It seems I did already some of the code... https://github.com/CHARM-Tx/linear_mem_attention_pytorch could we build on top of this? I talked to https://github.com/Chillee about an experimental functionality from functorch: https://github.com/pytorch/functorch that would allow for increased speed (mainly i want to match jax perofmance but its just difficult w/ pytorch imperative style).

    I would love to collaborate on this if you want!

    opened by hypnopump 5
  • Added dropout support to memory efficient variant

    Added dropout support to memory efficient variant

    Hey Phil,

    I have been using this repository for a project and I wanted to add dropout for completeness. I checked consistency with perceiver-ar impl.. I hope this is helpful.

    -Matt

    opened by usryokousha 2
  • Making this work with relative position bias from XTransformers

    Making this work with relative position bias from XTransformers

    Is there a way to make this work with RelativePositionBias. Currently this produces an attention bias of size $BHN^2$ where B is batch size, H is number of heads and N is input size. Can this be chunked and computed per chunk?

    opened by pfeatherstone 5
  • save_for_backward can only save variables, but argument 5 is of type bool

    save_for_backward can only save variables, but argument 5 is of type bool

    Hi,

    Thank you for your indescribable work. I was trying to test your method specifically for cross-attention but It seems I get the error " save_for_backward can only save variables, but argument 5 is of type bool". I am not sure what I am doing wrong. I tried your own examples too but get the same error.

    Can you please help me out?

    Code:

    import torch from memory_efficient_attention_pytorch import Attention

    cross_attn = Attention( dim = 512, dim_head = 64, heads = 8, memory_efficient = True, q_bucket_size = 1024, k_bucket_size = 2048 ).cuda() (# out = sm_mod(inp1)) did this to avoid being a header x = torch.randn(1, 65536, 512).cuda() context = torch.randn(1, 65536, 512).cuda() (# mask = torch.ones(1, 65536).bool().cuda()) did this to avoid being a heading out = cross_attn(x

    ERROR:

    File "/home/abali/.conda/envs/py38_ydp5/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/home/abali/.conda/envs/py38_ydp5/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/home/abali/.vscode-server/extensions/ms-python.python-2022.8.1/pythonFiles/lib/python/debugpy/main.py", line 45, in cli.main() File "/home/abali/.vscode-server/extensions/ms-python.python-2022.8.1/pythonFiles/lib/python/debugpy/../debugpy/server/cli.py", line 444, in main run() File "/home/abali/.vscode-server/extensions/ms-python.python-2022.8.1/pythonFiles/lib/python/debugpy/../debugpy/server/cli.py", line 285, in run_file runpy.run_path(target_as_str, run_name=compat.force_str("main")) File "/home/abali/.conda/envs/py38_ydp5/lib/python3.8/runpy.py", line 265, in run_path return _run_module_code(code, init_globals, run_name, File "/home/abali/.conda/envs/py38_ydp5/lib/python3.8/runpy.py", line 97, in _run_module_code _run_code(code, mod_globals, init_globals, File "/home/abali/.conda/envs/py38_ydp5/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/data/stars/user/abali/Phd_work/ISBI2023/X3D-Multigrid/CrossAttn_X3d_v2.py", line 872, in out = cross_attn(x, context = context, mask = mask) # (1, 65536, 512) print(out) File "/home/abali/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/abali/.conda/envs/py38_ydp5/lib/python3.8/site-packages/memory_efficient_attention_pytorch/memory_efficient_attention.py", line 215, in forward out = attn_fn(q, k, v, mask = mask, attn_bias = attn_bias, causal = self.causal, q_bucket_size = q_bucket_size, k_bucket_size = k_bucket_size) File "/home/abali/.conda/envs/py38_ydp5/lib/python3.8/site-packages/memory_efficient_attention_pytorch/memory_efficient_attention.py", line 127, in memory_efficient_attention exp_weight_chunk, weighted_value_chunk, weight_max_chunk = summarize_qkv_fn( File "/home/abali/.local/lib/python3.8/site-packages/torch/utils/checkpoint.py", line 163, in checkpoint return CheckpointFunction.apply(function, preserve, *args) TypeError: save_for_backward can only save variables, but argument 5 is of type bool

    opened by aliabid2243 1
  • Checkpointing is not compatible with .grad() or when an `inputs` parameter is passed to .backward()

    Checkpointing is not compatible with .grad() or when an `inputs` parameter is passed to .backward()

    https://github.com/lucidrains/memory-efficient-attention-pytorch/blob/35559a05572f9d4eb982a8e2e399b40a2d61b85c/memory_efficient_attention_pytorch/memory_efficient_attention.py#L95

    Should this be: summarize_qkv_fn = summarize_qkv_chunk if needs_backwards else checkpointed_summarize_qkv_chunk instead of: summarize_qkv_fn = checkpointed_summarize_qkv_chunk if needs_backwards else summarize_qkv_chunk

    opened by vrobot 0
Releases(0.1.1)
Owner
Phil Wang
Working with Attention. It's all we need
Phil Wang
GitHub Repository
Live Hand Tracking Using Python

Live-Hand-Tracking-Using-Python Project Description: In this project, we will be

Hassan Shahzad 2 Jan 06, 2022
Meta graph convolutional neural network-assisted resilient swarm communications

Resilient UAV Swarm Communications with Graph Convolutional Neural Network This repository contains the source codes of Resilient UAV Swarm Communicat

62 Dec 06, 2022
Gym environment for FLIPIT: The Game of "Stealthy Takeover"

gym-flipit Gym environment for FLIPIT: The Game of "Stealthy Takeover" invented by Marten van Dijk, Ari Juels, Alina Oprea, and Ronald L. Rivest. Desi

Lisa Oakley 2 Dec 15, 2021
PyTorch inference for "Progressive Growing of GANs" with CelebA snapshot

Progressive Growing of GANs inference in PyTorch with CelebA training snapshot Description This is an inference sample written in PyTorch of the origi

320 Nov 21, 2022
DeLag: Detecting Latency Degradation Patterns in Service-based Systems

DeLag: Detecting Latency Degradation Patterns in Service-based Systems Replication package of the work "DeLag: Detecting Latency Degradation Patterns

SEALABQualityGroup @ University of L'Aquila 2 Mar 24, 2022
Colossal-AI: A Unified Deep Learning System for Large-Scale Parallel Training

ColossalAI An integrated large-scale model training system with efficient parallelization techniques Installation PyPI pip install colossalai Install

HPC-AI Tech 7.1k Jan 03, 2023
Weakly Supervised Text-to-SQL Parsing through Question Decomposition

Weakly Supervised Text-to-SQL Parsing through Question Decomposition The official repository for the paper "Weakly Supervised Text-to-SQL Parsing thro

14 Dec 19, 2022
DPT: Deformable Patch-based Transformer for Visual Recognition (ACM MM2021)

DPT This repo is the official implementation of DPT: Deformable Patch-based Transformer for Visual Recognition (ACM MM2021). We provide code and model

CASIA-IVA-Lab 111 Dec 21, 2022
JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation

JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation This the repository for this paper. Find extensions of this w

Zhuoyuan Mao 14 Oct 26, 2022
Generative Models as a Data Source for Multiview Representation Learning

GenRep Project Page | Paper Generative Models as a Data Source for Multiview Representation Learning Ali Jahanian, Xavier Puig, Yonglong Tian, Phillip

Ali 81 Dec 03, 2022
A tool to estimate time varying instantaneous reproduction number during epidemics

EpiEstim A tool to estimate time varying instantaneous reproduction number during epidemics. It is described in the following paper: @article{Cori2013

MRC Centre for Global Infectious Disease Analysis 78 Dec 19, 2022
Predict stock movement with Machine Learning and Deep Learning algorithms

Project Overview Stock market movement prediction using LSTM Deep Neural Networks and machine learning algorithms Software and Library Requirements Th

Naz Delam 46 Sep 13, 2022
Streamlit App For Product Analysis - Streamlit App For Product Analysis

Streamlit_App_For_Product_Analysis Здравствуйте! Перед вами дашборд, позволяющий

Grigory Sirotkin 1 Jan 10, 2022
2021 National Underwater Robotics Vision Optics

2021-National-Underwater-Robotics-Vision-Optics 2021年全国水下机器人算法大赛-光学赛道-B榜精度第18名 (Kilian_Di的团队：A榜[email pro

Di Chang 9 Nov 04, 2022
GradAttack is a Python library for easy evaluation of privacy risks in public gradients in Federated Learning

GradAttack is a Python library for easy evaluation of privacy risks in public gradients in Federated Learning, as well as corresponding mitigation strategies.

129 Dec 30, 2022
MBPO (paper: When to trust your model: Model-based policy optimization) in offline RL settings

offline-MBPO This repository contains the code of a version of model-based RL algorithm MBPO, which is modified to perform in offline RL settings Pape

LxzGordon 1 Oct 24, 2021
[ICLR'21] FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

FedBN: Federated Learning on Non-IID Features via Local Batch Normalization This is the PyTorch implemention of our paper FedBN: Federated Learning on

<a href=[email protected]"> 156 Dec 15, 2022
git《USD-Seg:Learning Universal Shape Dictionary for Realtime Instance Segmentation》(2020) GitHub: [fig2]

USD-Seg This project is an implement of paper USD-Seg:Learning Universal Shape Dictionary for Realtime Instance Segmentation, based on FCOS detector f

Ruolin Ye 80 Nov 28, 2022
PerfFuzz: Automatically Generate Pathological Inputs for C/C++ programs

PerfFuzz Performance problems in software can arise unexpectedly when programs are provided with inputs that exhibit pathological behavior. But how ca

Caroline Lemieux 125 Nov 18, 2022
Code for Discriminative Sounding Objects Localization (NeurIPS 2020)

Discriminative Sounding Objects Localization Code for our NeurIPS 2020 paper Discriminative Sounding Objects Localization via Self-supervised Audiovis

51 Dec 11, 2022