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
details on efforts to dump the Watermelon Games Paprium cart

Reminder, if you like these repos, fork them so they don't disappear https://github.com/ArcadeHustle/WatermelonPapriumDump/fork Big thanks to Fonzie f

Hustle Arcade 29 Dec 11, 2022
LRBoost is a scikit-learn compatible approach to performing linear residual based stacking/boosting.

LRBoost is a sckit-learn compatible package for linear residual boosting. LRBoost combines a linear estimator and a non-linear estimator to leverage t

Andrew Patton 5 Nov 23, 2022
A script that trains a model to recognize handwritten digits using the MNIST data set.

handwritten-digits-recognition A script that trains a model to recognize handwritten digits using the MNIST data set. Then it loads external files and

Hamza Sayih 1 Oct 30, 2021
Implementation of SSMF: Shifting Seasonal Matrix Factorization

SSMF Implementation of SSMF: Shifting Seasonal Matrix Factorization, Koki Kawabata, Siddharth Bhatia, Rui Liu, Mohit Wadhwa, Bryan Hooi. NeurIPS, 2021

Koki Kawabata 9 Jun 10, 2022
This repository contains the re-implementation of our paper deSpeckNet: Generalizing Deep Learning Based SAR Image Despeckling

deSpeckNet-TF-GEE This repository contains the re-implementation of our paper deSpeckNet: Generalizing Deep Learning Based SAR Image Despeckling publi

Adugna Mullissa 16 Sep 07, 2022
Official implementation for the paper "SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization".

SAPE Project page Paper Official implementation for the paper "SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization". Environment Cre

36 Dec 09, 2022
Unsupervised Image Generation with Infinite Generative Adversarial Networks

Unsupervised Image Generation with Infinite Generative Adversarial Networks Here is the implementation of MICGANs using DCGAN architecture on MNIST da

16 Dec 24, 2021
LUKE -- Language Understanding with Knowledge-based Embeddings

LUKE (Language Understanding with Knowledge-based Embeddings) is a new pre-trained contextualized representation of words and entities based on transf

Studio Ousia 587 Dec 30, 2022
A curated list of automated deep learning (including neural architecture search and hyper-parameter optimization) resources.

Awesome AutoDL A curated list of automated deep learning related resources. Inspired by awesome-deep-vision, awesome-adversarial-machine-learning, awe

D-X-Y 2k Dec 30, 2022
BBScan py3 - BBScan py3 With Python

BBScan_py3 This repository is forked from lijiejie/BBScan 1.5. I migrated the fo

baiyunfei 12 Dec 30, 2022
DilatedNet in Keras for image segmentation

Keras implementation of DilatedNet for semantic segmentation A native Keras implementation of semantic segmentation according to Multi-Scale Context A

303 Mar 15, 2022
Gesture-controlled Video Game. Just swing your finger and play the game without touching your PC

Gesture Controlled Video Game Detailed Blog : https://www.analyticsvidhya.com/blog/2021/06/gesture-controlled-video-game/ Introduction This project is

Devbrat Anuragi 35 Jan 06, 2023
State of the Art Neural Networks for Deep Learning

pyradox This python library helps you with implementing various state of the art neural networks in a totally customizable fashion using Tensorflow 2

Ritvik Rastogi 60 May 29, 2022
This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

Introduction This is an official implementation of CvT: Introducing Convolutions to Vision Transformers. We present a new architecture, named Convolut

Microsoft 408 Dec 30, 2022
[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.

OpenCOOD OpenCOOD is an Open COOperative Detection framework for autonomous driving. It is also the official implementation of the ICRA 2022 paper OPV

Runsheng Xu 322 Dec 23, 2022
Optimizing synthesizer parameters using gradient approximation

Optimizing synthesizer parameters using gradient approximation NASH 2021 Hackathon! These are some experiments I conducted during NASH 2021, the Neura

Jordie Shier 10 Feb 10, 2022
PyTorch implementation of SQN based on CloserLook3D's encoder

SQN_pytorch This repo is an implementation of Semantic Query Network (SQN) using CloserLook3D's encoder in Pytorch. For TensorFlow implementation, che

PointCloudYC 1 Oct 21, 2021
The official TensorFlow implementation of the paper Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition

Action Transformer A Self-Attention Model for Short-Time Human Action Recognition This repository contains the official TensorFlow implementation of t

PIC4SeRCentre 20 Jan 03, 2023
基于DouZero定制AI实战欢乐斗地主

DouZero_For_Happy_DouDiZhu: 将DouZero用于欢乐斗地主实战 本项目基于DouZero 环境配置请移步项目DouZero 模型默认为WP，更换模型请修改start.py中的模型路径 运行main.py即可 SL (baselines/sl/): 基于人类数据进行深度学习

1.5k Jan 08, 2023
CAUSE: Causality from AttribUtions on Sequence of Events

CAUSE: Causality from AttribUtions on Sequence of Events

Wei Zhang 21 Dec 01, 2022