Alternatives and similar repositories for MagiAttention

Users that are interested in MagiAttention are comparing it to the libraries listed below

• thu-ml / SpargeAttn
  SpargeAttention: A training-free sparse attention that can accelerate any model inference.
  ☆709Updated last month
• vipshop / cache-dit
  A Unified Cache Acceleration Toolbox for 🤗Diffusers: FLUX.1, Qwen-Image-Edit, Qwen-Image, HunyuanImage-2.1, Wan 2.1/2.2, etc.
  ☆275Updated this week
• svg-project / Sparse-VideoGen
  [ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
  ☆424Updated 3 weeks ago
• mit-han-lab / Block-Sparse-Attention
  A sparse attention kernel supporting mix sparse patterns
  ☆294Updated 7 months ago
• xlite-dev / Awesome-DiT-Inference
  📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉
  ☆394Updated 3 weeks ago
• thu-nics / DiTFastAttn
  ☆173Updated 8 months ago
• stepfun-ai / Step3
  ☆423Updated last month
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆562Updated last week
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆215Updated 3 months ago
• NVlabs / Fast-dLLM
  Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
  ☆436Updated last week
• xdit-project / DistVAE
  A parallelism VAE avoids OOM for high resolution image generation
  ☆78Updated last month
• mit-han-lab / distrifuser
  [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
  ☆704Updated 9 months ago
• ByteDance-Seed / VeOmni
  VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework
  ☆1,050Updated 3 weeks ago
• mit-han-lab / x-attention
  [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆226Updated 2 months ago
• nunchaku-tech / deepcompressor
  Model Compression Toolbox for Large Language Models and Diffusion Models
  ☆628Updated last month
• fla-org / native-sparse-attention
  🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
  ☆847Updated 5 months ago
• Shenyi-Z / TaylorSeer
  [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
  ☆278Updated last month
• mit-han-lab / radial-attention
  Radial Attention Official Implementation
  ☆500Updated last week
• fla-org / flame
  🔥 A minimal training framework for scaling FLA models
  ☆239Updated this week
• zhuzilin / ring-flash-attention
  Ring attention implementation with flash attention
  ☆866Updated this week
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆239Updated last month
• thu-nics / ViDiT-Q
  [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  ☆118Updated 5 months ago
• microsoft / RAS
  An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…
  ☆139Updated 2 months ago
• sandyresearch / chipmunk
  🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …
  ☆82Updated last week
• shawnricecake / draft-attention
  Code for Draft Attention
  ☆91Updated 3 months ago
• chengzeyi / ParaAttention
  https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
  ☆373Updated 2 months ago
• xuyang-liu16 / Awesome-Generation-Acceleration
  📚 Collection of awesome generation acceleration resources.
  ☆334Updated 2 months ago
• Tele-AI / TeleTron
  To pioneer training long-context multi-modal transformer models
  ☆57Updated last month
• mit-han-lab / patch_conv
  Patch convolution to avoid large GPU memory usage of Conv2D
  ☆92Updated 7 months ago
• mit-han-lab / duo-attention
  [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
  ☆490Updated 7 months ago