thu-ml / SpargeAttnLinks
SpargeAttention: A training-free sparse attention that can accelerate any model inference.
☆620Updated this 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☆501Updated 2 months ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆344Updated 2 weeks ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆385Updated this week
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Caching, Quantization, Parallelism, etc.☆283Updated this week
- Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across…☆1,766Updated last week
- A sparse attention kernel supporting mix sparse patterns☆238Updated 4 months ago
- ☆167Updated 5 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆304Updated last month
- 📚 Collection of awesome generation acceleration resources.☆270Updated 2 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆519Updated 3 weeks ago
- Accelerating Diffusion Transformers with Token-wise Feature Caching☆159Updated 3 months ago
- xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism☆2,044Updated this week
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆686Updated 6 months ago
- From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆179Updated last month
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆702Updated 3 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆130Updated 4 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆102Updated 3 months ago
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆166Updated this week
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆210Updated last week
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆202Updated 4 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆150Updated 7 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆233Updated 2 weeks ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆231Updated 5 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆64Updated 5 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆355Updated last month
- Ring attention implementation with flash attention☆789Updated last week
- Puzzles for learning Triton, play it with minimal environment configuration!☆367Updated 6 months ago
- Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models☆313Updated 4 months ago
- Scaling Diffusion Transformers with Mixture of Experts☆339Updated 9 months ago
- DeepSeek Native Sparse Attention pytorch implementation☆71Updated 3 months ago