SingleZombie / LLSALinks
Official implementation of Log-linear Sparse Attention (LLSA).
☆54Updated last month
Alternatives and similar repositories for LLSA
Users that are interested in LLSA are comparing it to the libraries listed below
Sorting:
- Code for Draft Attention☆99Updated 8 months ago
- The official implementation of "Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers" (arXiv …☆50Updated 8 months ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆60Updated 7 months ago
- Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"☆165Updated last year
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆260Updated 2 weeks ago
- [ICLR 2026] Official implementation of DiCache: Let Diffusion Model Determine Its Own Cache☆54Updated last week
- A WebUI for Side-by-Side Comparison of Media (Images/Videos) Across Multiple Folders☆24Updated 11 months ago
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆52Updated last year
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆116Updated last year
- An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…☆150Updated 7 months ago
- ☆190Updated last year
- rCM: SOTA JVP-Based Diffusion Distillation & Few-Step Video Generation & Scaling Up sCM/MeanFlow☆524Updated last week
- flex-block-attn: an efficient block sparse attention computation library☆108Updated last month
- ☆132Updated 7 months ago
- 📚 A curated list of Awesome Efficient dLLMs Papers with Codes☆81Updated this week
- The official implementation of Distribution Backtracking Distillation for One-step Diffusion Models☆32Updated last year
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆624Updated last month
- Residual Context Diffusion (RCD): Repurposing discarded signals as structured priors for high-performance reasoning in dLLMs.☆45Updated this week
- A light-weight and high-efficient training framework for accelerating diffusion tasks.☆51Updated last year
- [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality…☆53Updated 10 months ago
- NVIDIA FastGen: Fast Generation from Diffusion Models☆508Updated last week
- Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆81Updated 6 months ago
- ☆221Updated 2 months ago
- ☆35Updated 9 months ago
- [Preprint] UCGM: Unified Continuous Generative Models☆179Updated 8 months ago
- DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space☆343Updated 4 months ago
- [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving☆269Updated 6 months ago
- UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, a…☆134Updated 10 months ago
- Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"☆173Updated this week
- [ICML 2025] Official Implementation of Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots☆29Updated 8 months ago