mit-han-lab / radial-attentionLinks
[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
☆563Updated last month
Alternatives and similar repositories for radial-attention
Users that are interested in radial-attention are comparing it to the libraries listed below
Sorting:
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆403Updated 5 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆597Updated last week
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆345Updated 4 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆255Updated 11 months ago
- TurboDiffusion: 100–200× Acceleration for Video Diffusion Models☆476Updated this week
- The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆243Updated last month
- Unofficial extension implementation of Self-Forcing to support I2V && 14B training.☆290Updated 2 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆149Updated 5 months ago
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆197Updated 9 months ago
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆257Updated 4 months ago
- Tiny AutoEncoder for Hunyuan Video (and other video models)☆250Updated this week
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆310Updated 2 months ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆826Updated this week
- Taming large-scale full-parameter few-step training with self-adversarial flows! 👏🏻☆255Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆710Updated 4 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆210Updated 2 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆161Updated last year
- [NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation☆647Updated 3 weeks ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆584Updated this week
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆388Updated 6 months ago
- Making Flux go brrr on GPUs.☆158Updated 5 months ago
- Code for Draft Attention☆98Updated 6 months ago
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆192Updated 8 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,099Updated 4 months ago
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆32Updated 7 months ago
- Light Video Generation Inference Framework☆1,133Updated last week
- ☆187Updated 11 months ago
- 🤗A PyTorch-native Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs: Z-Image, FLUX2, Qwen-Image, etc.☆761Updated this week
- Pusa: Thousands Timesteps Video Diffusion Model☆668Updated 3 months ago
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆212Updated 2 months ago