SandAI-org / MagiAttentionLinks
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
☆385Updated this week
Alternatives and similar repositories for MagiAttention
Users that are interested in MagiAttention are comparing it to the libraries listed below
Sorting:
- [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity☆344Updated 2 weeks ago
- ☆167Updated 5 months ago
- SpargeAttention: A training-free sparse attention that can accelerate any model inference.☆620Updated last week
- A sparse attention kernel supporting mix sparse patterns☆238Updated 4 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆355Updated last month
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆150Updated 7 months ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆519Updated 3 weeks ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆304Updated last month
- 📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Caching, Quantization, Parallelism, etc.☆283Updated this week
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆130Updated 4 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆233Updated 2 weeks ago
- A parallelism VAE avoids OOM for high resolution image generation☆64Updated 5 months ago
- [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models☆686Updated 6 months ago
- Patch convolution to avoid large GPU memory usage of Conv2D☆88Updated 5 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆501Updated 2 months ago
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆166Updated this week
- 🔥 A minimal training framework for scaling FLA models☆178Updated 2 weeks ago
- From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆179Updated last month
- Efficient triton implementation of Native Sparse Attention.☆168Updated last month
- Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"☆302Updated 6 months ago
- 📚 Collection of awesome generation acceleration resources.☆270Updated 2 months ago
- ☆216Updated 2 weeks ago
- Ring attention implementation with flash attention☆789Updated last week
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆102Updated 3 months ago
- Scaling Diffusion Transformers with Mixture of Experts☆339Updated 9 months ago
- [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆231Updated 5 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆210Updated last week
- An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆783Updated last week
- ☆191Updated 2 months ago
- GenEval: An object-focused framework for evaluating text-to-image alignment☆310Updated 3 months ago