SandAI-org / MagiAttentionLinks
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
☆489Updated last week
Alternatives and similar repositories for MagiAttention
Users that are interested in MagiAttention are comparing it to the libraries listed below
Sorting:
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆688Updated 2 weeks ago
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆412Updated 2 months ago
- ☆400Updated 2 weeks ago
- 🤗An Unified Cache Acceleration Toolbox for DiTs: Qwen-Image, Qwen-Image-Edit, FLUX.1, Wan2.1/2.2, etc.☆201Updated this week
- ☆173Updated 7 months ago
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆377Updated last week
- A sparse attention kernel supporting mix sparse patterns☆280Updated 6 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆703Updated 8 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆75Updated 3 weeks ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆550Updated last month
- Efficient triton implementation of Native Sparse Attention.☆208Updated 3 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆607Updated last week
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆927Updated this week
- Radial Attention Official Implementation☆485Updated 3 weeks ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆374Updated last week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆219Updated last month
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆822Updated 5 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆365Updated last month
- Patch convolution to avoid large GPU memory usage of Conv2D☆92Updated 7 months ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆81Updated 2 months ago
- Ring attention implementation with flash attention☆849Updated 3 weeks ago
- 🔥 A minimal training framework for scaling FLA models☆233Updated last week
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆156Updated 9 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆231Updated 2 weeks ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆266Updated 2 weeks ago
- Long-RL: Scaling RL to Long Sequences☆592Updated last week
- Code for Draft Attention☆90Updated 3 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆138Updated 2 months ago
- 📚 Collection of awesome generation acceleration resources.☆317Updated last month
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆115Updated 5 months ago