Alternatives and similar repositories for MagiAttention:

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

• thu-nics / DiTFastAttn
  ☆160Updated 3 months ago
• ByteDance-Seed / VeOmni
  VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework
  ☆297Updated 2 weeks ago
• mit-han-lab / x-attention
  XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆140Updated 3 weeks ago
• thu-ml / SpargeAttn
  SpargeAttention: A training-free sparse attention that can accelerate any model inference.
  ☆488Updated this week
• mit-han-lab / Block-Sparse-Attention
  A sparse attention kernel supporting mix sparse patterns
  ☆197Updated 2 months ago
• xdit-project / DistVAE
  A parallelism VAE avoids OOM for high resolution image generation
  ☆61Updated 3 months ago
• svg-project / Sparse-VideoGen
  Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
  ☆178Updated this week
• mit-han-lab / patch_conv
  Patch convolution to avoid large GPU memory usage of Conv2D
  ☆86Updated 3 months ago
• NVlabs / COAT
  [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
  ☆184Updated last week
• AdaCache-DiT / AdaCache
  Adaptive Caching for Faster Video Generation with Diffusion Transformers
  ☆145Updated 5 months ago
• xlite-dev / Awesome-Diffusion-Inference
  📖A curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. 🎉🎉
  ☆210Updated last month
• feifeibear / long-context-attention
  USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference
  ☆477Updated this week
• microsoft / RAS
  An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…
  ☆125Updated 2 months ago
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆139Updated 2 weeks ago
• ByteDance-Seed / ByteCheckpoint
  ByteCheckpoint: An Unified Checkpointing Library for LFMs
  ☆197Updated 3 weeks ago
• horseee / learning-to-cache
  [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
  ☆101Updated 9 months ago
• step-law / steplaw
  ☆179Updated last week
• TencentARC / mllm-npu
  mllm-npu: training multimodal large language models on Ascend NPUs
  ☆91Updated 7 months ago
• xuyang-liu16 / Awesome-Generation-Acceleration
  📚 Collection of awesome generation acceleration resources.
  ☆215Updated this week
• fla-org / flame
  🔥 A minimal training framework for scaling FLA models
  ☆107Updated last week
• NUS-HPC-AI-Lab / SpeeD
  SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
  ☆178Updated 2 months ago
• PipeFusion / PipeFusion
  A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters
  ☆44Updated 9 months ago
• xdit-project / DiTCacheAnalysis
  An auxiliary project analysis of the characteristics of KV in DiT Attention.
  ☆29Updated 4 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆270Updated 5 months ago
• mit-han-lab / duo-attention
  [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
  ☆453Updated 2 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆94Updated last week
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆90Updated 3 weeks ago
• zhuzilin / ring-flash-attention
  Ring attention implementation with flash attention
  ☆743Updated 2 weeks ago
• ByteDance-Seed / Triton-distributed
  Distributed Triton for Parallel Systems
  ☆451Updated 2 weeks ago
• mit-han-lab / vila-u
  [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
  ☆299Updated this week