mit-han-lab / radial-attentionLinks
[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
☆575Updated 2 months ago
Alternatives and similar repositories for radial-attention
Users that are interested in radial-attention are comparing it to the libraries listed below
Sorting:
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆360Updated 5 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆621Updated last month
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆416Updated 6 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆258Updated last year
- Unofficial extension implementation of Self-Forcing to support I2V && 14B training.☆338Updated 4 months ago
- rCM: SOTA JVP-Based Diffusion Distillation & Few-Step Video Generation & Scaling Up sCM/MeanFlow☆514Updated this week
- The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆254Updated 2 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆150Updated 7 months ago
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆336Updated 3 months ago
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆269Updated 5 months ago
- Taming large-scale few-step training with self-adversarial flows! 👏🏻☆462Updated last week
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆206Updated 10 months ago
- Tiny AutoEncoder for Hunyuan Video (and other video models)☆286Updated last week
- [NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation☆705Updated 2 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆744Updated 5 months ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆916Updated 3 weeks ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆212Updated 4 months ago
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆390Updated 3 weeks ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆164Updated last year
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆213Updated 4 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,181Updated 5 months ago
- Making Flux go brrr on GPUs.☆159Updated 3 weeks ago
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆258Updated last week
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆195Updated 9 months ago
- 🤗 A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.☆929Updated this week
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆649Updated last year
- Pusa: Thousands Timesteps Video Diffusion Model☆672Updated 4 months ago
- Unofficial extension implementation of CausVid☆73Updated 9 months ago
- ☆357Updated this week
- Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"☆164Updated 3 weeks ago