thu-ml / SpargeAttnLinks
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
☆826Updated this week
Alternatives and similar repositories for SpargeAttn
Users that are interested in SpargeAttn are comparing it to the libraries listed below
Sorting:
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆584Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆710Updated 4 months ago
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆468Updated 2 weeks ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆597Updated last week
- 🤗A PyTorch-native Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs: Z-Image, FLUX2, Qwen-Image, etc.☆761Updated this week
- A sparse attention kernel supporting mix sparse patterns☆406Updated 10 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆563Updated last month
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆403Updated 5 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆713Updated last year
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆345Updated 4 months ago
- ☆187Updated 11 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆610Updated 2 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆140Updated 8 months ago
- 📚 Collection of awesome generation acceleration resources.☆371Updated 5 months ago
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆197Updated 9 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆2,826Updated last week
- ☆439Updated 4 months ago
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,474Updated this week
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆146Updated last month
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆942Updated 8 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆84Updated 4 months ago
- Aiming to integrate most existing feature caching-based diffusion acceleration schemes into a unified framework.☆82Updated last month
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆736Updated 2 weeks ago
- TurboDiffusion: 100–200× Acceleration for Video Diffusion Models☆476Updated this week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆256Updated 5 months ago
- High performance inference engine for diffusion models☆100Updated 3 months ago
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆32Updated 7 months ago
- Efficient triton implementation of Native Sparse Attention.☆254Updated 6 months ago
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆1,432Updated this week
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆149Updated 5 months ago