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
Accelerating BERT Inference for Sequence Labeling via Early-Exit

Sequence-Labeling-Early-Exit Code for ACL 2021 paper: Accelerating BERT Inference for Sequence Labeling via Early-Exit Requirement: Please refer to re

李孝男 23 Oct 14, 2022
A command line simple note taking app

Why yet another note taking program? note was designed with a very specific target in mind: me, and my 2354 scraps of paper. It runs from the command

64 Nov 20, 2022
DIP-football - A football video analyse system based on Yolov5, alphapose, Qt6

足球视频分析系统 作者 陆徐东 [email protected] 方天宬

2 Jun 04, 2022
you can add any codes in any language by creating its respective folder (if already not available).

HACKTOBERFEST-2021-WEB-DEV Beginner-Hacktoberfest Need Your first pr for hacktoberfest 2k21 ? come on in About This is repository of Responsive Portfo

Suman Sharma 8 Oct 17, 2022
Underwater image enhancement

LANet Our work proposes an adaptive learning attention network (LANet) to solve the problem of color casts and low illumination in underwater images.

LiuShiBen 7 Sep 14, 2022
A embed able annotation tool for end to end cross document co-reference

CoRefi CoRefi is an emebedable web component and stand alone suite for exaughstive Within Document and Cross Document Coreference Anntoation. For a de

PythicCoder 39 Dec 12, 2022
Unofficial PyTorch code for BasicVSR

Dependencies and Installation The code is based on BasicSR, Please install the BasicSR framework first. Pytorch=1.51 Training cd ./code CUDA_VISIBLE_

Long 59 Dec 06, 2022
Resources complimenting the Machine Learning Course led in the Faculty of mathematics and informatics part of Sofia University.

Machine Learning and Data Mining, Summer 2021-2022 How to learn data science and machine learning? Programming. Learn Python. Basic Statistics. Take a

Simeon Hristov 8 Oct 04, 2022
Face2webtoon - Despite its importance, there are few previous works applying I2I translation to webtoon.

Despite its importance, there are few previous works applying I2I translation to webtoon. I collected dataset from naver webtoon 연애혁명 and tried to transfer human faces to webtoon domain.

이상윤 64 Oct 19, 2022
Download and preprocess popular sequential recommendation datasets

Sequential Recommendation Datasets This repository collects some commonly used sequential recommendation datasets in recent research papers and provid

125 Dec 06, 2022
This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation

SO-Pose This repository contains codes of ICCV2021 paper: SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation This paper is basically an

shangbuhuan 52 Nov 25, 2022
🤗 Push your spaCy pipelines to the Hugging Face Hub

spacy-huggingface-hub: Push your spaCy pipelines to the Hugging Face Hub This package provides a CLI command for uploading any trained spaCy pipeline

Explosion 30 Oct 09, 2022
Deep Learning pipeline for motor-imagery classification.

BCI-ToolBox 1. Introduction BCI-ToolBox is deep learning pipeline for motor-imagery classification. This repo contains five models: ShallowConvNet, De

DongHee 18 Oct 31, 2022
Keras code and weights files for popular deep learning models.

Trained image classification models for Keras THIS REPOSITORY IS DEPRECATED. USE THE MODULE keras.applications INSTEAD. Pull requests will not be revi

François Chollet 7.2k Dec 29, 2022
Source code for the Paper: CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints}

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints Installation Run pipenv install (at your own risk with --skip-lo

Autonomous Learning Group 65 Dec 27, 2022
A python comtrade load library accelerated by go

Comtrade-GRPC Code for python used is mainly from dparrini/python-comtrade. Just patch the code in BinaryDatReader.parse for parsing a little more eff

Bo 1 Dec 27, 2021
A symbolic-model-guided fuzzer for TLS

tlspuffin TLS Protocol Under FuzzINg A symbolic-model-guided fuzzer for TLS Master Thesis | Thesis Presentation | Documentation Disclaimer: The term "

69 Dec 20, 2022
Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)

An Image is Worth 16x16 Words, What is a Video Worth? paper Official PyTorch Implementation Gilad Sharir, Asaf Noy, Lihi Zelnik-Manor DAMO Academy, Al

213 Nov 12, 2022
Face recognition. Redefined.

FaceFinder Use a powerful CNN to identify faces in images! TABLE OF CONTENTS About The Project Built With Getting Started Prerequisites Installation U

BleepLogger 20 Jun 16, 2021
Retinal Vessel Segmentation with Pixel-wise Adaptive Filters (ISBI 2022)

Retinal Vessel Segmentation with Pixel-wise Adaptive Filters (ISBI 2022) Introdu

anonymous 14 Oct 27, 2022