mit-han-lab / radial-attentionLinks
[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
☆536Updated this week
Alternatives and similar repositories for radial-attention
Users that are interested in radial-attention are comparing it to the libraries listed below
Sorting:
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆553Updated last month
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆325Updated 2 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆385Updated 4 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆250Updated 10 months ago
- Light Video Generation Inference Framework☆714Updated this week
- The official code for "MagCache: Fast Video Generation with Magnitude-Aware Cache"☆220Updated last month
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆206Updated last month
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆269Updated last month
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆191Updated 7 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆144Updated 4 months ago
- Unofficial extension implementation of Self-Forcing to support I2V && 14B training.☆229Updated last month
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆252Updated 3 months ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆758Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆685Updated 2 months ago
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆381Updated 5 months ago
- Making Flux go brrr on GPUs.☆151Updated 3 months ago
- Tiny AutoEncoder for Hunyuan Video (and other video models)☆200Updated last month
- [NeurIPS 2025] Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".☆212Updated last month
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆160Updated last year
- ☆183Updated 9 months ago
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆32Updated 6 months ago
- A Unified Cache Acceleration Framework for 🤗Diffusers: Qwen-Image-Lightning, Qwen-Image, HunyuanImage, Wan, FLUX, etc.☆460Updated last week
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,016Updated 2 months ago
- Aiming to integrate most existing feature caching-based diffusion acceleration schemes into a unified framework.☆71Updated last week
- faster parallel inference of mochi-1 video generation model☆125Updated 8 months ago
- Code for Draft Attention☆92Updated 5 months ago
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆191Updated 6 months ago
- Enhance-A-Video: Better Generated Video for Free☆577Updated 7 months ago
- HART: Efficient Visual Generation with Hybrid Autoregressive Transformer☆640Updated last year
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆503Updated 10 months ago