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 knowledge-informed machine learning on the PRONOSTIA (FEMTO) and IMS bearing data sets. Predict remaining-useful-life (RUL).

Knowledge Informed Machine Learning using a Weibull-based Loss Function Exploring the concept of knowledge-informed machine learning with the use of a

Tim 43 Dec 14, 2022
CryptoFrog - My First Strategy for freqtrade

cryptofrog-strategies CryptoFrog - My First Strategy for freqtrade NB: (2021-04-20) You'll need the latest freqtrade develop branch otherwise you migh

Robert Davey 137 Jan 01, 2023
A cross-document event and entity coreference resolution system, trained and evaluated on the ECB+ corpus.

A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution. Introduction This repo contains experimental code derived from

2 May 09, 2022
Improving the robustness and performance of biomedical NLP models through adversarial training

RobustBioNLP Improving the robustness and performance of biomedical NLP models through adversarial training In this repository you can find suppliment

Milad Moradi 3 Sep 20, 2022
🌾 PASTIS 🌾 Panoptic Agricultural Satellite TIme Series

🌾 PASTIS 🌾 Panoptic Agricultural Satellite TIme Series (optical and radar) The PASTIS Dataset Dataset presentation PASTIS is a benchmark dataset for

86 Jan 04, 2023
JupyterNotebook - C/C++, Javascript, HTML, LaTex, Shell scripts in Jupyter Notebook Also run them on remote computer

JupyterNotebook Read, write and execute C, C++, Javascript, Shell scripts, HTML, LaTex in jupyter notebook, And also execute them on remote computer R

1 Jan 09, 2022
Using Self-Supervised Pretext Tasks for Active Learning - Official Pytorch Implementation

Using Self-Supervised Pretext Tasks for Active Learning - Official Pytorch Implementation Experiment Setting: CIFAR10 (downloaded and saved in ./DATA

John Seon Keun Yi 38 Dec 27, 2022
PyTorch code for the NAACL 2021 paper "Improving Generation and Evaluation of Visual Stories via Semantic Consistency"

Improving Generation and Evaluation of Visual Stories via Semantic Consistency PyTorch code for the NAACL 2021 paper "Improving Generation and Evaluat

Adyasha Maharana 28 Dec 08, 2022
PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis

PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis

Ubisoft 76 Dec 30, 2022
Hyperparameter tuning for humans

KerasTuner KerasTuner is an easy-to-use, scalable hyperparameter optimization framework that solves the pain points of hyperparameter search. Easily c

Keras 2.6k Dec 27, 2022
Bayesian Inference Tools in Python

BayesPy Bayesian Inference Tools in Python Our goal is, given the discrete outcomes of events, estimate the distribution of categories. Using gradient

Max Sklar 99 Dec 14, 2022
MERLOT: Multimodal Neural Script Knowledge Models

merlot MERLOT: Multimodal Neural Script Knowledge Models MERLOT is a model for learning what we are calling "neural script knowledge" -- representatio

Rowan Zellers 190 Dec 22, 2022
An implementation of the proximal policy optimization algorithm

PPO Pytorch C++ This is an implementation of the proximal policy optimization algorithm for the C++ API of Pytorch. It uses a simple TestEnvironment t

Martin Huber 59 Dec 09, 2022
DeepFashion2 is a comprehensive fashion dataset.

DeepFashion2 Dataset DeepFashion2 is a comprehensive fashion dataset. It contains 491K diverse images of 13 popular clothing categories from both comm

switchnorm 1.8k Jan 07, 2023
Augmented Traffic Control: A tool to simulate network conditions

Augmented Traffic Control Full documentation for the project is available at http://facebook.github.io/augmented-traffic-control/. Overview Augmented

Meta Archive 4.3k Jan 08, 2023
Deep Learning for Human Part Discovery in Images - Chainer implementation

Deep Learning for Human Part Discovery in Images - Chainer implementation NOTE: This is not official implementation. Original paper is Deep Learning f

Shintaro Shiba 63 Sep 25, 2022
LibMTL: A PyTorch Library for Multi-Task Learning

LibMTL LibMTL is an open-source library built on PyTorch for Multi-Task Learning (MTL). See the latest documentation for detailed introductions and AP

765 Jan 06, 2023
Code for "AutoMTL: A Programming Framework for Automated Multi-Task Learning"

AutoMTL: A Programming Framework for Automated Multi-Task Learning This is the website for our paper "AutoMTL: A Programming Framework for Automated M

Ivy Zhang 40 Dec 04, 2022
Code for KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs Check out the paper on arXiv: https://arxiv.org/abs/2103.13744 This repo cont

Christian Reiser 373 Dec 20, 2022
labelpix is a graphical image labeling interface for drawing bounding boxes

Welcome to labelpix 👋 labelpix is a graphical image labeling interface for drawing bounding boxes. 🏠 Homepage Install pip install -r requirements.tx

schissmantics 26 May 24, 2022