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
using yolox+deepsort for object-tracker

YOLOX_deepsort_tracker yolox+deepsort实现目标跟踪 最新的yolox尝尝鲜~~（yolox正处在频繁更新阶段，因此直接链接yolox仓库作为子模块） Install Clone the repository recursively: git clone --rec

245 Dec 26, 2022
Hysterese plugin with two temperature offset areas

craftbeerpi4 plugin OffsetHysterese Temperatur-Steuerungs-Plugin mit zwei tempereaturbereich abhängigen Offsets. Installation sudo pip3 install https:

HappyHibo 1 Dec 21, 2021
Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback

Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback This is our Pytorch implementation for the paper: Yinwei Wei,

17 Jun 10, 2022
Hybrid Neural Fusion for Full-frame Video Stabilization

FuSta: Hybrid Neural Fusion for Full-frame Video Stabilization Project Page | Video | Paper | Google Colab Setup Setup environment for [Yu and Ramamoo

Yu-Lun Liu 430 Jan 04, 2023
A Framework for Encrypted Machine Learning in TensorFlow

TF Encrypted is a framework for encrypted machine learning in TensorFlow. It looks and feels like TensorFlow, taking advantage of the ease-of-use of t

TF Encrypted 0 Jul 06, 2022
A rough implementation of the paper "A Steering Algorithm for Redirected Walking Using Reinforcement Learning"

A rough implementation of the paper "A Steering Algorithm for Redirected Walking Using Reinforcement Learning"

Somnus ｀Chen 2 Jun 09, 2022
Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning. and others.

An Image Captioning codebase This is a codebase for image captioning research. It supports: Self critical training from Self-critical Sequence Trainin

Ruotian(RT) Luo 906 Jan 03, 2023
A cool little repl-based simulation written in Python

A cool little repl-based simulation written in Python planned to integrate machine-learning into itself to have AI battle to the death before your eye

Em 6 Sep 17, 2022
A Pytorch Implementation for Compact Bilinear Pooling.

CompactBilinearPooling-Pytorch A Pytorch Implementation for Compact Bilinear Pooling. Adapted from tensorflow_compact_bilinear_pooling Prerequisites I

169 Dec 23, 2022
A small library for creating and manipulating custom JAX Pytree classes

Treeo A small library for creating and manipulating custom JAX Pytree classes Light-weight: has no dependencies other than jax. Compatible: Treeo Tree

Cristian Garcia 58 Nov 23, 2022
mlpack: a scalable C++ machine learning library --

a fast, flexible machine learning library Home | Documentation | Doxygen | Community | Help | IRC Chat Download: current stable version (3.4.2) mlpack

mlpack 4.2k Jan 09, 2023
Machine learning algorithms for many-body quantum systems

NetKet NetKet is an open-source project delivering cutting-edge methods for the study of many-body quantum systems with artificial neural networks and

NetKet 413 Dec 31, 2022
A style-based Quantum Generative Adversarial Network

Style-qGAN A style based Quantum Generative Adversarial Network (style-qGAN) model for Monte Carlo event generation. Tutorial We have prepared a noteb

9 Nov 24, 2022
Unsupervised Image-to-Image Translation

UNIT: UNsupervised Image-to-image Translation Networks Imaginaire Repository We have a reimplementation of the UNIT method that is more performant. It

Ming-Yu Liu 劉洺堉 1.9k Dec 26, 2022
Explaining Deep Neural Networks - A comparison of different CAM methods based on an insect data set

Explaining Deep Neural Networks - A comparison of different CAM methods based on an insect data set This is the repository for the Deep Learning proje

Robert Krug 3 Feb 06, 2022
LeafSnap replicated using deep neural networks to test accuracy compared to traditional computer vision methods.

Deep-Leafsnap Convolutional Neural Networks have become largely popular in image tasks such as image classification recently largely due to to Krizhev

Sujith Vishwajith 48 Nov 27, 2022
HMLET (Hybrid-Method-of-Linear-and-non-linEar-collaborative-filTering-method)

Methods HMLET (Hybrid-Method-of-Linear-and-non-linEar-collaborative-filTering-method) Dynamically selecting the best propagation method for each node

Yong 7 Dec 18, 2022
Improving Deep Network Debuggability via Sparse Decision Layers

Improving Deep Network Debuggability via Sparse Decision Layers This repository contains the code for our paper: Leveraging Sparse Linear Layers for D

Madry Lab 35 Nov 14, 2022
Automatic differentiation with weighted finite-state transducers.

GTN: Automatic Differentiation with WFSTs Quickstart | Installation | Documentation What is GTN? GTN is a framework for automatic differentiation with

100 Dec 29, 2022
A simple python stock Predictor

Python Stock Predictor A simple python stock Predictor Demo Run Locally Clone the project git clone https://github.com/yashraj-n/stock-price-predict

Yashraj narke 5 Nov 29, 2021