Alternatives and similar repositories for MagiAttention

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

• mit-han-lab / Block-Sparse-Attention
  A sparse attention kernel supporting mix sparse patterns
  ☆430Updated last week
• thu-ml / SpargeAttn
  [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
  ☆897Updated 2 weeks ago
• thu-ml / SLA
  SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
  ☆243Updated 2 weeks ago
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆626Updated this week
• svg-project / Sparse-VideoGen
  [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention
  ☆616Updated last month
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆258Updated 7 months ago
• thu-nics / DiTFastAttn
  ☆189Updated last year
• stepfun-ai / Step3
  ☆444Updated 5 months ago
• xlite-dev / Awesome-DiT-Inference
  📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉
  ☆490Updated last month
• mit-han-lab / distrifuser
  [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
  ☆716Updated last year
• vipshop / cache-dit
  🤗A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.
  ☆891Updated this week
• xdit-project / DistVAE
  A parallelism VAE avoids OOM for high resolution image generation
  ☆84Updated 5 months ago
• zhijie-group / Discrete-Diffusion-Forcing
  Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference
  ☆234Updated 3 months ago
• zhuzilin / ring-flash-attention
  Ring attention implementation with flash attention
  ☆963Updated 4 months ago
• NVlabs / Fast-dLLM
  Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
  ☆773Updated last month
• mit-han-lab / flash-moba
  ☆216Updated last month
• fla-org / native-sparse-attention
  🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
  ☆952Updated 9 months ago
• nunchaku-ai / deepcompressor
  Model Compression Toolbox for Large Language Models and Diffusion Models
  ☆732Updated 5 months ago
• mit-han-lab / radial-attention
  [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
  ☆573Updated 2 months ago
• mit-han-lab / x-attention
  [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆263Updated 6 months ago
• Shenyi-Z / TaylorSeer
  [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
  ☆355Updated 5 months ago
• ByteDance-Seed / VeOmni
  VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
  ☆1,524Updated this week
• Dao-AILab / sonic-moe
  Accelerating MoE with IO and Tile-aware Optimizations
  ☆542Updated this week
• xuyang-liu16 / Awesome-Generation-Acceleration
  📚 Collection of awesome generation acceleration resources.
  ☆381Updated 6 months ago
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆257Updated 5 months ago
• fla-org / flame
  🔥 A minimal training framework for scaling FLA models
  ☆335Updated 2 months ago
• thu-nics / ViDiT-Q
  [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
  ☆146Updated 9 months ago
• chengzeyi / ParaAttention
  https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching
  ☆410Updated 6 months ago
• z-lab / dflash
  Block Diffusion for Ultra-Fast Speculative Decoding
  ☆313Updated last week
• microsoft / RAS
  An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…
  ☆149Updated 6 months ago