thu-ml / SpargeAttnLinks
SpargeAttention: A training-free sparse attention that can accelerate any model inference.
☆645Updated 3 weeks ago
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☆530Updated 3 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆413Updated this week
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆319Updated this week
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆364Updated last month
- ☆170Updated 6 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆228Updated 3 weeks ago
- A sparse attention kernel supporting mix sparse patterns☆249Updated 5 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆695Updated 7 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆329Updated last week
- Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across…☆1,959Updated last week
- Radial Attention Official Implementation☆354Updated last week
- 📚 Collection of awesome generation acceleration resources.☆282Updated last week
- A parallelism VAE avoids OOM for high resolution image generation☆67Updated 5 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆528Updated last month
- Accelerating Diffusion Transformers with Token-wise Feature Caching☆162Updated 4 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆103Updated 3 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆133Updated 3 weeks ago
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,105Updated 2 weeks ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆191Updated last week
- To pioneer training long-context multi-modal transformer models☆42Updated last month
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆26Updated 2 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆720Updated 3 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆473Updated 5 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆152Updated 8 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆370Updated last week
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆215Updated last month
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆278Updated last week
- [ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.☆350Updated last year
- [CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for…☆102Updated this week
- 🤗CacheDiT: A Training-free and Easy-to-use Cache Acceleration Toolbox for Diffusion Transformers🔥☆99Updated this week