thu-ml / SLALinks
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
☆113Updated this week
Alternatives and similar repositories for SLA
Users that are interested in SLA are comparing it to the libraries listed below
Sorting:
- A sparse attention kernel supporting mix sparse patterns☆322Updated 8 months ago
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆239Updated 3 months ago
- ☆182Updated 9 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆126Updated 7 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆58Updated 3 months ago
- 🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× …☆87Updated last month
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆32Updated 10 months ago
- Code for Draft Attention☆91Updated 5 months ago
- Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference☆171Updated last month
- FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation [Efficient ML Model]☆43Updated last month
- A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention☆200Updated last month
- [NeurIPS'25] dKV-Cache: The Cache for Diffusion Language Models☆110Updated 5 months ago
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆41Updated last month
- Fast and memory-efficient exact kmeans☆111Updated 3 weeks ago
- A parallelism VAE avoids OOM for high resolution image generation☆81Updated 2 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆147Updated last week
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆171Updated last month
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆116Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆119Updated 4 months ago
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆537Updated last week
- Efficient triton implementation of Native Sparse Attention.☆238Updated 5 months ago
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆517Updated 2 weeks ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆46Updated 3 months ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆29Updated 6 months ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆49Updated last year
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆158Updated last month
- Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆72Updated 3 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆581Updated 2 weeks ago
- ☆251Updated 4 months ago
- [NeurIPS 2025] ScaleKV: Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression☆49Updated 4 months ago