#Attention

Showing 60 of 96 repositories tagged #attention, ranked by stars

labmlai
labmlai
annotated_deep_learning_paper_implementations

๐Ÿง‘โ€๐Ÿซ 60+ Implementations/tutorials of deep learning papers with side-by-side notes ๐Ÿ“; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), ๐ŸŽฎ reinforcement learning (ppo, dqn), capsnet, distillation, ... ๐Ÿง 

Score
92
โ˜… 67.1k โ‘‚ 6.7k +11/day
Python
sgl-project
sgl-project
sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

Score
100
โ˜… 30.1k โ‘‚ 7.1k +17/day
Python
ddbourgin
ddbourgin
numpy-ml

Machine learning, in numpy

Score
62
โ˜… 16.3k โ‘‚ 3.8k โ€”
Python
kyegomez
kyegomez
OpenMythos

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Score
85
โ˜… 14.7k โ‘‚ 3.3k +400/day
Python
xmu-xiaoma666
xmu-xiaoma666
External-Attention-pytorch

๐Ÿ€ Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.โญโญโญ

Score
77
โ˜… 12.2k โ‘‚ 1.9k +2/day
Python
jadore801120
jadore801120
attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

Score
54
โ˜… 9.8k โ‘‚ 2.1k +5/day
Python
flashinfer-ai
flashinfer-ai
flashinfer

FlashInfer: Kernel Library for LLM Serving

Score
69
โ˜… 5.9k โ‘‚ 1.1k +6/day
Python
google-research
google-research
scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

Score
100
โ˜… 3.8k โ‘‚ 478 +4/day
Python
thu-ml
thu-ml
SageAttention

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Score
100
โ˜… 3.5k โ‘‚ 441 +12/day
Cuda
gordicaleksa
gordicaleksa
pytorch-GAT

My implementation of the original GAT paper (Veliฤkoviฤ‡ et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!

Score
100
โ˜… 2.7k โ‘‚ 355 +1/day
Jupyter Notebook
mesolitica
mesolitica
NLP-Models-Tensorflow

Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0

Score
90
โ˜… 1.8k โ‘‚ 712 +1/day
Jupyter Notebook
lucidrains
lucidrains
lambda-networks

Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

Score
82
โ˜… 1.5k โ‘‚ 155 โ€”
Python
szagoruyko
szagoruyko
attention-transfer

Improving Convolutional Networks via Attention Transfer (ICLR 2017)

Score
86
โ˜… 1.5k โ‘‚ 273 โ€”
Jupyter Notebook
lucidrains
lucidrains
transfusion-pytorch

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

Score
96
โ˜… 1.4k โ‘‚ 73 +1/day
Python
pprp
pprp
SimpleCVReproduction

Replication of simple CV Projects including attention, classification, detection, keypoint detection, etc.

Score
84
โ˜… 1.3k โ‘‚ 318 โ€”
Jupyter Notebook
The-AI-Summer
The-AI-Summer
self-attention-cv

Implementation of various self-attention mechanisms focused on computer vision. Ongoing repository.

Score
80
โ˜… 1.2k โ‘‚ 152 โ€”
Python
lucidrains
lucidrains
performer-pytorch

An implementation of Performer, a linear attention-based transformer, in Pytorch

Score
76
โ˜… 1.2k โ‘‚ 149 +1/day
Python
gordicaleksa
gordicaleksa
pytorch-original-transformer

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

Score
92
โ˜… 1.1k โ‘‚ 188 +2/day
Jupyter Notebook
thu-ml
thu-ml
SpargeAttn

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Score
85
โ˜… 1.0k โ‘‚ 95 +3/day
Cuda
MorvanZhou
MorvanZhou
NLP-Tutorials

Simple implementations of NLP models. Tutorials are written in Chinese on my website https://mofanpy.com

Score
46
โ˜… 950 โ‘‚ 315 โ€”
Python
jmaczan
jmaczan
tiny-vllm

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

Score
92
โ˜… 882 โ‘‚ 61 +51/day
C++
NVIDIA
NVIDIA
cudnn-frontend

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

Score
98
โ˜… 864 โ‘‚ 200 +2/day
Python
jeya-maria-jose
jeya-maria-jose
Medical-Transformer

Official Pytorch Code for "Medical Transformer: Gated Axial-Attention for Medical Image Segmentation" - MICCAI 2021

Score
75
โ˜… 862 โ‘‚ 177 โ€”
Python
lucidrains
lucidrains
native-sparse-attention-pytorch

Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper

Score
71
โ˜… 809 โ‘‚ 53 โ€”
Python
google-research
google-research
long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

Score
73
โ˜… 788 โ‘‚ 86 โ€”
Python
kyegomez
kyegomez
LongNet

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

Score
54
โ˜… 721 โ‘‚ 61 โ€”
Python
mlpotter
mlpotter
Transformer_Time_Series

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (NeurIPS 2019)

Score
83
โ˜… 602 โ‘‚ 103 +2/day
Jupyter Notebook
rayleizhu
rayleizhu
BiFormer

[CVPR 2023] Official code release of our paper "BiFormer: Vision Transformer with Bi-Level Routing Attention"

Score
57
โ˜… 581 โ‘‚ 41 โ€”
Python
chengchingwen
chengchingwen
Transformers.jl

Julia Implementation of Transformer models

Score
94
โ˜… 571 โ‘‚ 83 โ€”
Julia
zhvng
zhvng
open-musiclm

Implementation of MusicLM, a text to music model published by Google Research, with a few modifications.

Score
59
โ˜… 562 โ‘‚ 66 โ€”
Python
WenjieDu
WenjieDu
SAITS

The official PyTorch implementation of the paper "SAITS: Self-Attention-based Imputation for Time Series". A fast and state-of-the-art (SOTA) deep-learning neural network model for efficient time-series imputation (impute multivariate incomplete time series containing NaN missing data/values with machine learning). https://arxiv.org/abs/2202.08516

Score
78
โ˜… 507 โ‘‚ 70 โ€”
Python
kaushalshetty
kaushalshetty
Structured-Self-Attention

A Structured Self-attentive Sentence Embedding

Score
38
โ˜… 492 โ‘‚ 102 โ€”
Python
rentainhe
rentainhe
visualization

a collection of visualization function

Score
75
โ˜… 447 โ‘‚ 42 +1/day
Python
Tixierae
Tixierae
deep_learning_NLP

Keras, PyTorch, and NumPy Implementations of Deep Learning Architectures for NLP

Score
31
โ˜… 440 โ‘‚ 103 โ€”
Jupyter Notebook
ai-forever
ai-forever
ner-bert

BERT-NER (nert-bert) with google bert https://github.com/google-research.

Score
23
โ˜… 408 โ‘‚ 100 โ€”
Jupyter Notebook
kyegomez
kyegomez
ScreenAI

Implementation of the ScreenAI model from the paper: "A Vision-Language Model for UI and Infographics Understanding"

Score
92
โ˜… 385 โ‘‚ 38 โ€”
Python
jayeew
jayeew
Chinese-ChatBot

ไธญๆ–‡่Šๅคฉๆœบๅ™จไบบ๏ผŒๅŸบไบŽ10ไธ‡็ป„ๅฏน็™ฝ่ฎญ็ปƒ่€Œๆˆ๏ผŒ้‡‡็”จๆณจๆ„ๅŠ›ๆœบๅˆถ๏ผŒๅฏนไธ€่ˆฌ้—ฎ้ข˜้ƒฝไผš็”Ÿๆˆไธ€ไธชๆœ‰ๆ„ไน‰็š„็ญ”ๅคใ€‚ๅทฒไธŠไผ ๆจกๅž‹๏ผŒๅฏ็›ดๆŽฅ่ฟ่กŒใ€‚

Score
58
โ˜… 324 โ‘‚ 67 +1/day
Jupyter Notebook
aprbw
aprbw
traffic_prediction

Traffic prediction is the task of predicting future traffic measurements (e.g. volume, speed, etc.) in a road network (graph), using historical data (timeseries).

Score
55
โ˜… 319 โ‘‚ 48 โ€”
TeX
lucidrains
lucidrains
spear-tts-pytorch

Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in Pytorch

Score
47
โ˜… 278 โ‘‚ 20 โ€”
Python
kaiyuyue
kaiyuyue
cgnl-network.pytorch

PyTorch Implementation of Compact Generalized Non-local Network [NIPS'18]

Score
53
โ˜… 257 โ‘‚ 41 โ€”
Python
cbaziotis
cbaziotis
neat-vision

Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)

Score
42
โ˜… 251 โ‘‚ 24 โ€”
Vue
alokwhitewolf
alokwhitewolf
Guided-Attention-Inference-Network

Contains implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018). This repository aims to apply GAIN on fcn8 architecture used for segmentation.

Score
49
โ˜… 237 โ‘‚ 43 โ€”
Python
coderonion
coderonion
awesome-snn

๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅA collection of some awesome public SNN(Spiking Neural Network) projects.

Score
23
โ˜… 235 โ‘‚ 22 โ€”
jackaduma
jackaduma
SecBERT

pretrained BERT model for cyber security text, learned CyberSecurity Knowledge

Score
0
โ˜… 211 โ‘‚ 38 โ€”
Python
lucidrains
lucidrains
dreamer4

Implementation of Danijar's latest iteration for his Dreamer line of work

Score
88
โ˜… 204 โ‘‚ 18 +4/day
Python
cbaziotis
cbaziotis
datastories-semeval2017-task4

Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".

Score
51
โ˜… 199 โ‘‚ 64 โ€”
Python
lucidrains
lucidrains
llama-qrlhf

Implementation of the Llama architecture with RLHF + Q-learning

Score
41
โ˜… 170 โ‘‚ 8 โ€”
Python
lucidrains
lucidrains
h-transformer-1d

Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning

Score
43
โ˜… 167 โ‘‚ 23 โ€”
Python
lucidrains
lucidrains
genie2-pytorch

Implementation of a framework for Genie2 in Pytorch

Score
39
โ˜… 157 โ‘‚ 13 โ€”
Python
TobiasRoeddiger
TobiasRoeddiger
GazePointHeatMap

Easy to use Python command line based tool to generate a gaze point heatmap from a csv file. ๐Ÿ‘๏ธ

Score
33
โ˜… 150 โ‘‚ 45 โ€”
Python
ankit-ai
ankit-ai
BertQA-Attention-on-Steroids

BertQA - Attention on Steroids

Score
35
โ˜… 115 โ‘‚ 15 โ€”
Jupyter Notebook
walkinglabs
walkinglabs
modern-llm-notebook

A hands-on course for building modern LLMs from scratch in PyTorch, with 26 runnable Jupyter Notebooks covering tokenizers, attention, MoE, RLHF, inference, evaluation, and distillation.

Score
77
โ˜… 111 โ‘‚ 20 +7/day
Jupyter Notebook
SeanFDZ
SeanFDZ
macmind

Single-layer transformer in HyperTalk for the classic Macintosh

Score
69
โ˜… 105 โ‘‚ 5 +2/day
Python
IvoryTradesmanPort
IvoryTradesmanPort
Valorant-External-Assistant-2026

Monitor Valorant gameplay through an external overlay to track player stats and match data in real time.

Score
100
โ˜… 100 โ‘‚ 0 โ€”
FanChiMao
FanChiMao
CMFNet

Compound Multi-branch Feature Fusion for Real Image Restoration

Score
8
โ˜… 100 โ‘‚ 14 โ€”
Python
GuangxingHan
GuangxingHan
Meta-Faster-R-CNN

Code for AAAI 2022 Oral paper: 'Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment'

Score
0
โ˜… 99 โ‘‚ 12 โ€”
Python
jlamprou
jlamprou
Infini-Attention

Efficient Infinite Context Transformers with Infini-attention Pytorch Implementation + QwenMoE Implementation + Training Script + 1M context keypass retrieval

Score
15
โ˜… 98 โ‘‚ 7 +1/day
Python
AdityaSoni19031997
AdityaSoni19031997
Machine-Learning

My Attempt(s) In The World Of ML/DL....

Score
15
โ˜… 95 โ‘‚ 28 โ€”
Jupyter Notebook
zengqunzhao
zengqunzhao
MA-Net

[TIP'21] Learning Deep Global Multi-scale and Local Attention Features for Facial Expression Recognition in the Wild

Score
25
โ˜… 95 โ‘‚ 13 โ€”
Python
jeeliz
jeeliz
jeelizGlanceTracker

Real-time JavaScript/WebGL library to detect whether the user is looking at the screen. Lightweight, robust to varied lighting, perfect for auto play-pause or presence-aware web experiences ๐Ÿ‘€

Score
37
โ˜… 95 โ‘‚ 27 โ€”
JavaScript
Related Topics
#deep-learning#transformer#pytorch#artificial-intelligence#transformers#attention-mechanism#machine-learning#nlp#lstm#computer-vision#llm#python

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly