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
A unofficial pytorch implementation of PAN(PSENet2): Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network Requirements pytorch 1.1+ torchvision 0.3+ pyclipper opencv3 gcc

zhoujun 400 Dec 26, 2022
SurfEmb (CVPR 2022) - SurfEmb: Dense and Continuous Correspondence Distributions

SurfEmb SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings Rasmus Laurvig Haugard, A

Rasmus Haugaard 56 Nov 19, 2022
Invertible conditional GANs for image editing

Invertible Conditional GANs This is the implementation of the IcGAN model proposed in our paper: Invertible Conditional GANs for image editing. Novemb

Guim 278 Dec 12, 2022
Official repository for Few-shot Image Generation via Cross-domain Correspondence (CVPR '21)

Few-shot Image Generation via Cross-domain Correspondence Utkarsh Ojha, Yijun Li, Jingwan Lu, Alexei A. Efros, Yong Jae Lee, Eli Shechtman, Richard Zh

Utkarsh Ojha 251 Dec 11, 2022
Awesome Artificial Intelligence, Machine Learning and Deep Learning as we learn it

Awesome Artificial Intelligence, Machine Learning and Deep Learning as we learn it. Study notes and a curated list of awesome resources of such topics.

mani 1.2k Jan 07, 2023
The InterScript dataset contains interactive user feedback on scripts generated by a T5-XXL model.

Interscript The Interscript dataset contains interactive user feedback on a T5-11B model generated scripts. Dataset data.json contains the data in an

AI2 8 Dec 01, 2022
Fast Differentiable Matrix Sqrt Root

Official Pytorch implementation of ICLR 22 paper Fast Differentiable Matrix Square Root

YueSong 42 Dec 30, 2022
nnFormer: Interleaved Transformer for Volumetric Segmentation Code for paper "nnFormer: Interleaved Transformer for Volumetric Segmentation "

nnFormer: Interleaved Transformer for Volumetric Segmentation Code for paper "nnFormer: Interleaved Transformer for Volumetric Segmentation ". Please

jsguo 610 Dec 28, 2022
A list of Machine Learning Art Colabs

ML Visual Art Colabs A list of cool Colabs on Machine Learning Imagemaking or other artistic purposes 3D Ken Burns Effect Ken Burns Effect by Manuel R

Derrick Schultz (he/him) 789 Dec 12, 2022
Latte: Cross-framework Python Package for Evaluation of Latent-based Generative Models

Cross-framework Python Package for Evaluation of Latent-based Generative Models Latte Latte (for LATent Tensor Evaluation) is a cross-framework Python

Karn Watcharasupat 30 Sep 08, 2022
Image-to-Image Translation with Conditional Adversarial Networks (Pix2pix) implementation in keras

pix2pix-keras Pix2pix implementation in keras. Original paper: Image-to-Image Translation with Conditional Adversarial Networks (pix2pix) Paper Author

William Falcon 141 Dec 30, 2022
This repository contains code accompanying the paper "An End-to-End Chinese Text Normalization Model based on Rule-Guided Flat-Lattice Transformer"

FlatTN This repository contains code accompanying the paper "An End-to-End Chinese Text Normalization Model based on Rule-Guided Flat-Lattice Transfor

THUHCSI 74 Nov 28, 2022
Pytorch Implementation of Adversarial Deep Network Embedding for Cross-Network Node Classification

Pytorch Implementation of Adversarial Deep Network Embedding for Cross-Network Node Classification (ACDNE) This is a pytorch implementation of the Adv

陈志豪 8 Oct 13, 2022
PSGAN running with ncnn⚡妆容迁移/仿妆⚡Imitation Makeup/Makeup Transfer⚡

PSGAN running with ncnn⚡妆容迁移/仿妆⚡Imitation Makeup/Makeup Transfer⚡

WuJinxuan 144 Dec 26, 2022
Code for the paper: Sketch Your Own GAN

Sketch Your Own GAN Project | Paper | Youtube | Slides Our method takes in one or a few hand-drawn sketches and customizes an off-the-shelf GAN to mat

677 Dec 28, 2022
This is a collection of all challenges in HKCERT CTF 2021

香港網絡保安新生代奪旗挑戰賽 2021 (HKCERT CTF 2021) This is a collection of all challenges (and writeups) in HKCERT CTF 2021 Challenges ID Chinese name Name Score S

10 Jan 27, 2022
This project contains an implemented version of Face Detection using OpenCV and Mediapipe. This is a code snippet and can be used in projects.

Live-Face-Detection Project Description: In this project, we will be using the live video feed from the camera to detect Faces. It will also detect so

Hassan Shahzad 3 Oct 02, 2021
This repository contains the implementation of the HealthGen model, a generative model to synthesize realistic EHR time series data with missingness

HealthGen: Conditional EHR Time Series Generation This repository contains the implementation of the HealthGen model, a generative model to synthesize

0 Jan 20, 2022
FEMDA: Robust classification with Flexible Discriminant Analysis in heterogeneous data

FEMDA: Robust classification with Flexible Discriminant Analysis in heterogeneous data. Flexible EM-Inspired Discriminant Analysis is a robust supervised classification algorithm that performs well i

0 Sep 06, 2022
Learning Continuous Signed Distance Functions for Shape Representation

DeepSDF This is an implementation of the CVPR '19 paper "DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation" by Park et a

Meta Research 1.1k Jan 01, 2023