thu-ml / SpargeAttnLinks
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
☆738Updated 2 weeks ago
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☆530Updated this week
- Model Compression Toolbox for Large Language Models and Diffusion Models☆663Updated 2 months ago
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆419Updated last month
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆505Updated last week
- A Unified Cache Acceleration Framework for 🤗 Diffusers: Qwen-Image-Lightning, Qwen-Image, HunyuanImage, FLUX, Wan, etc.☆396Updated this week
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆302Updated 2 months ago
- ☆180Updated 9 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆384Updated 3 months ago
- A sparse attention kernel supporting mix sparse patterns☆315Updated 8 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆519Updated 3 weeks ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆706Updated 10 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆124Updated 6 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆573Updated 3 weeks ago
- ☆428Updated 2 months ago
- Aiming to integrate most existing feature caching-based diffusion acceleration schemes into a unified framework.☆60Updated 2 weeks ago
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆186Updated 7 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆81Updated 2 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆236Updated 3 months ago
- 📚 Collection of awesome generation acceleration resources.☆348Updated 3 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without lossing end-…☆2,505Updated last week
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆553Updated this week
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆65Updated this week
- VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo☆1,210Updated this week
- Efficient triton implementation of Native Sparse Attention.☆235Updated 4 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆895Updated 6 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆143Updated 3 months ago
- Combining Teacache with xDiT to Accelerate Visual Generation Models☆31Updated 5 months ago
- High performance inference engine for diffusion models☆94Updated last month
- Light Video Generation Inference Framework☆642Updated this week
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,324Updated this week