FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving
cs.DC, cs.LG
Submitted: 2026-07-13
Updated: 2026-10-27
Code: https://github.com/black-forest-labs/flux
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
- SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
- Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
- Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
- Stable Audio Open
- PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference
- xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
- Segment Anything
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
- AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
- DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
- TetriServe: Efficiently Serving Mixed DiT Workloads
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- Scalable Diffusion Models with Transformers
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
- High-Resolution Image Synthesis with Latent Diffusion Models
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
- Denoising Diffusion Implicit Models
- Score-Based Generative Modeling through Stochastic Differential Equations
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends