thu-ml / SpargeAttnLinks
SpargeAttention: A training-free sparse attention that can accelerate any model inference.
☆718Updated last month
Alternatives and similar repositories for SpargeAttn
Users that are interested in SpargeAttn are comparing it to the libraries listed below
Sorting:
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆403Updated last month
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆508Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆633Updated last month
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆430Updated 3 weeks ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆376Updated 2 months ago
- [NeurIPS 2025] Radial Attention: O(n\log n) Sparse Attention with Energy Decay for Long Video Generation☆507Updated this week
- A sparse attention kernel supporting mix sparse patterns☆296Updated 7 months ago
- A Unified Cache Acceleration Toolbox for 🤗Diffusers: FLUX.1, Qwen-Image-Edit, Qwen-Image, HunyuanImage-2.1, Wan 2.1/2.2, etc.☆317Updated this week
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆283Updated last month
- ☆175Updated 8 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆706Updated 9 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆562Updated last week
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆177Updated 6 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆119Updated 6 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆78Updated last month
- Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across…☆2,389Updated last month
- 📚 Collection of awesome generation acceleration resources.☆334Updated 2 months ago
- ☆423Updated last month
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆229Updated 2 months ago
- High performance inference engine for diffusion models☆91Updated 2 weeks ago
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,279Updated this week
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆453Updated last week
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆856Updated 6 months ago
- Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation☆16Updated 3 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆140Updated 2 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆1,087Updated 3 weeks ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆84Updated last week
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆31Updated 5 months ago
- Light Video Generation Inference Framework☆571Updated this week
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆239Updated last month