SandAI-org / MagiAttentionLinks
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
☆456Updated this 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.☆670Updated this week
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆393Updated 2 months ago
- ☆326Updated this week
- ☆171Updated 6 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆399Updated this week
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆699Updated 8 months ago
- A sparse attention kernel supporting mix sparse patterns☆262Updated 5 months ago
- A parallelism VAE avoids OOM for high resolution image generation☆68Updated 6 months ago
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉☆350Updated last week
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆537Updated 2 weeks ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆320Updated this week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆213Updated last month
- Efficient triton implementation of Native Sparse Attention.☆186Updated 2 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆566Updated 4 months ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆155Updated 9 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆778Updated 4 months ago
- Radial Attention Official Implementation☆453Updated 2 weeks ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆480Updated 5 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆92Updated 6 months ago
- Ring attention implementation with flash attention☆828Updated last week
- 📚 Collection of awesome generation acceleration resources.☆302Updated last month
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆350Updated last month
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆245Updated last month
- 🔥 A minimal training framework for scaling FLA models☆220Updated last month
- Code for Draft Attention☆89Updated 2 months ago
- 🤗A Training-free and Easy-to-use Cache Acceleration Toolbox for Diffusion Transformers.☆117Updated this week
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆108Updated 4 months ago
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆136Updated last month
- ☆232Updated 2 months ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆78Updated last month