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
Computational Pathology Toolbox developed by TIA Centre, University of Warwick.

TIA Toolbox Computational Pathology Toolbox developed at the TIA Centre Getting Started All Users This package is for those interested in digital path

Tissue Image Analytics (TIA) Centre 156 Jan 08, 2023
Code of the lileonardo team for the 2021 Emotion and Theme Recognition in Music task of MediaEval 2021

Emotion and Theme Recognition in Music The repository contains code for the submission of the lileonardo team to the 2021 Emotion and Theme Recognitio

Vincent Bour 8 Aug 02, 2022
chainladder - Property and Casualty Loss Reserving in Python

chainladder (python) chainladder - Property and Casualty Loss Reserving in Python This package gets inspiration from the popular R ChainLadder package

Casualty Actuarial Society 130 Dec 07, 2022
A python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization

Website, Tutorials, and Docs    Uncertainty Toolbox A python toolbox for predictive uncertainty quantification, calibration, metrics, and visualizatio

Uncertainty Toolbox 1.4k Dec 28, 2022
[CVPR 2022] CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation

CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation Prerequisite Please create and activate the following conda envrionment. To r

Qin Wang 87 Jan 08, 2023
UV matrix decompostion using movielens dataset

UV-matrix-decompostion-with-kfold UV matrix decompostion using movielens dataset upload the 'ratings.dat' file install the following python libraries

2 Oct 18, 2022
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models Code accompanying CVPR'20 paper of the same title. Paper lin

Alex Damian 7k Dec 30, 2022
Learning Domain Invariant Representations in Goal-conditioned Block MDPs

Learning Domain Invariant Representations in Goal-conditioned Block MDPs Beining Han, Chongyi Zheng, Harris Chan, Keiran Paster, Michael R. Zhang, Jim

Chongyi Zheng 3 Apr 12, 2022
Simulation code and tutorial for BBHnet training data

Simulation Dataset for BBHnet NOTE: OLD README, UPDATE IN PROGRESS We generate simulation dataset to train BBHnet, our deep learning framework for det

0 May 31, 2022
Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation

DynaBOA Code repositoty for the paper: Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation Shanyan Guan, Jingwei Xu, Michell

197 Jan 07, 2023
How to Learn a Domain Adaptive Event Simulator? ACM MM, 2021

LETGAN How to Learn a Domain Adaptive Event Simulator? ACM MM 2021 Running Environment: pytorch=1.4, 1 NVIDIA-1080TI. More details can be found in pap

CVTEAM 4 Sep 20, 2022
An end-to-end image translation model with weight-map for color constancy

CCUnet An end-to-end image translation model with weight-map for color constancy 1. Download the dataset (take Colorchecker_recommended dataset as an

Jianhui Qiu 1 Dec 21, 2021
the code of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021)

RMA-Net This repo is the implementation of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021). Paper

Wanquan Feng 205 Nov 09, 2022
Answering Open-Domain Questions of Varying Reasoning Steps from Text

This repository contains the authors' implementation of the Iterative Retriever, Reader, and Reranker (IRRR) model in the EMNLP 2021 paper "Answering Open-Domain Questions of Varying Reasoning Steps

26 Dec 22, 2022
Cooperative multi-agent reinforcement learning for high-dimensional nonequilibrium control

Cooperative multi-agent reinforcement learning for high-dimensional nonequilibrium control Official implementation of: Cooperative multi-agent reinfor

0 Nov 16, 2021
Pytorch implementation of

EfficientTTS Unofficial Pytorch implementation of "EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture"(arXiv). Disclaimer: Somebo

Liu Songxiang 109 Nov 16, 2022
A unified 3D Transformer Pipeline for visual synthesis

Overview This is the official repo for the paper: NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion. NÜWA is a unified multimodal p

Microsoft 2.6k Jan 06, 2023
Over9000 optimizer

Optimizers and tests Every result is avg of 20 runs. Dataset LR Schedule Imagenette size 128, 5 epoch Imagewoof size 128, 5 epoch Adam - baseline OneC

Mikhail Grankin 405 Nov 27, 2022
Official PyTorch implementation of PS-KD

Self-Knowledge Distillation with Progressive Refinement of Targets (PS-KD) Accepted at ICCV 2021, oral presentation Official PyTorch implementation of

61 Dec 28, 2022
An open source implementation of CLIP.

OpenCLIP Welcome to an open source implementation of OpenAI's CLIP (Contrastive Language-Image Pre-training). The goal of this repository is to enable

2.7k Dec 31, 2022