Fast Multi-dimensional Sparse Attention
☆722Feb 26, 2026Updated last week
Alternatives and similar repositories for NATTEN
Users that are interested in NATTEN are comparing it to the libraries listed below
Sorting:
- Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022☆1,175May 15, 2024Updated last year
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆954Feb 25, 2026Updated last week
- EDM2 and Autoguidance -- Official PyTorch implementation☆824Dec 9, 2024Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- [WIP] Better (FP8) attention for Hopper☆32Feb 24, 2025Updated last year
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,192Jan 17, 2026Updated last month
- New flexible and efficient image generation framework that sets new SOTA on FFHQ-256 with FID 2.05, 2022☆101Jun 26, 2025Updated 8 months ago
- ☆23Jun 18, 2024Updated last year
- Efficient vision foundation models for high-resolution generation and perception.☆3,249Sep 5, 2025Updated 6 months ago
- [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆1,560Mar 16, 2025Updated 11 months ago
- Helpful tools and examples for working with flex-attention☆1,140Feb 8, 2026Updated last month
- Lumina-T2X is a unified framework for Text to Any Modality Generation☆2,253Feb 16, 2025Updated last year
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆635Jul 1, 2024Updated last year
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆214Sep 27, 2025Updated 5 months ago
- Karras et al. (2022) diffusion models for PyTorch☆2,569Feb 12, 2026Updated 3 weeks ago
- Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"☆1,102Dec 22, 2025Updated 2 months ago
- Tile primitives for speedy kernels☆3,202Feb 24, 2026Updated last week
- VideoSys: An easy and efficient system for video generation☆2,016Aug 27, 2025Updated 6 months ago
- ☆79Dec 27, 2024Updated last year
- A unified inference and post-training framework for accelerated video generation.☆3,127Updated this week
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,474Updated this week
- ☆124May 28, 2024Updated last year
- Triton implement of bi-directional (non-causal) linear attention☆71Mar 1, 2026Updated last week
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆534Sep 8, 2025Updated 6 months ago
- PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis☆3,281Oct 31, 2024Updated last year
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆644Jan 15, 2026Updated last month
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,281Jun 8, 2025Updated 9 months ago
- Hackable and optimized Transformers building blocks, supporting a composable construction.☆10,356Feb 20, 2026Updated 2 weeks ago
- A suite of image and video neural tokenizers☆1,714Feb 11, 2025Updated last year
- ☆191Jan 14, 2025Updated last year
- Elucidating the Design Space of Diffusion-Based Generative Models (EDM)☆1,919Mar 16, 2024Updated last year
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,560Updated this week
- Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.☆857Jan 23, 2025Updated last year
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆130Oct 18, 2024Updated last year
- Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"☆8,393May 31, 2024Updated last year
- [CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models☆1,409Dec 16, 2025Updated 2 months ago
- [NeurIPS 2024] CV-VAE: A Compatible Video VAE for Latent Generative Video Models☆287Dec 4, 2024Updated last year
- SEED-Voken: A Series of Powerful Visual Tokenizers☆997Nov 25, 2025Updated 3 months ago
- Ring attention implementation with flash attention☆987Sep 10, 2025Updated 5 months ago