thu-ml / SLALinks
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
☆44Updated this week
Alternatives and similar repositories for SLA
Users that are interested in SLA are comparing it to the libraries listed below
Sorting:
- ☆178Updated 8 months ago
- Code for Draft Attention☆90Updated 4 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆481Updated last week
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆143Updated 3 months ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆86Updated 3 weeks ago
- [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching☆180Updated 6 months ago
- [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers☆291Updated last month
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆49Updated last year
- A sparse attention kernel supporting mix sparse patterns☆307Updated 7 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆123Updated 6 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆517Updated 2 weeks ago
- Adaptive Caching for Faster Video Generation with Diffusion Transformers☆159Updated 11 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆114Updated last year
- Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆72Updated 2 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆234Updated 2 months ago
- (ToCa-v2) A New version of ToCa，with faster speed and better acceleration!☆38Updated 6 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆523Updated this week
- A parallelism VAE avoids OOM for high resolution image generation☆80Updated 2 months ago
- [NeurIPS'25] dKV-Cache: The Cache for Diffusion Language Models☆103Updated 4 months ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆40Updated 3 weeks ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆46Updated 3 months ago
- A Unified Cache Acceleration Framework for 🤗 Diffusers: Qwen-Image-Lightning, Qwen-Image, HunyuanImage, FLUX, Wan, etc.☆371Updated this week
- Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache☆40Updated this week
- The official implementation of "Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers" (arXiv …☆46Updated 3 months ago
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆43Updated 3 weeks ago
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆32Updated 10 months ago
- Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference☆151Updated last week
- Making Flux go brrr on GPUs.☆142Updated 2 months ago
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆183Updated this week
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆57Updated 2 months ago