MG-Cache: Multi-Granularity Caching for Accelerating Diffusion Transformer Inference
cs.LG, cs.PF
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- HunyuanImage 3.0 Technical Report
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
- FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
- Progressive Distillation for Fast Sampling of Diffusion Models
- Denoising Diffusion Implicit Models
- Adaptive Hybrid Caching for Efficient Text-to-Video Diffusion Model Acceleration
- Wan: Open and Advanced Large-Scale Video Generative Models
- Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
- Real-Time Video Generation with Pyramid Attention Broadcast
- Accelerating Diffusion Transformers with Token-wise Feature Caching
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis