thu-ml / SpargeAttnLinks
SpargeAttention: A training-free sparse attention that can accelerate any model inference.
☆579Updated last week
Alternatives and similar repositories for SpargeAttn
Users that are interested in SpargeAttn are comparing it to the libraries listed below
Sorting:
- Model Compression Toolbox for Large Language Models and Diffusion Models☆481Updated 2 months ago
- Quantized Attention achieves speedup of 2-3x and 3-5x compared to FlashAttention and xformers, without lossing end-to-end metrics across …☆1,610Updated last week
- 📚A curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. 🎉🎉☆251Updated last week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆372Updated this week
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆292Updated this week
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆290Updated 3 weeks ago
- 📚 Collection of awesome generation acceleration resources.☆252Updated last month
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆684Updated 6 months ago
- From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆164Updated 2 weeks ago
- ☆167Updated 4 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆506Updated last week
- A sparse attention kernel supporting mix sparse patterns☆219Updated 3 months ago
- Accelerating Diffusion Transformers with Token-wise Feature Caching☆151Updated 2 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆95Updated 2 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆128Updated 3 months ago
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆1,978Updated last week
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆158Updated 3 weeks ago
- A parallelism VAE avoids OOM for high resolution image generation☆64Updated 4 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆147Updated 6 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆686Updated 2 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆294Updated 3 months ago
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models☆660Updated last month
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆203Updated 2 weeks ago
- Efficient triton implementation of Native Sparse Attention.☆155Updated last week
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆339Updated 3 weeks ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆203Updated 3 months ago
- Ring attention implementation with flash attention☆771Updated last week
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆222Updated 5 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆291Updated 6 months ago
- Scaling Diffusion Transformers with Mixture of Experts☆330Updated 8 months ago