REVIEW 5 cited by
MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Diffusion-based text-to-image generation models trade latency for quality: small models are fast but generate lower-quality images, while large models produce better images but are slow. We present MoDM, a novel caching-based serving system for diffusion models that dynamically balances latency and quality through a mixture of diffusion models. Unlike prior approaches that rely on model-specific internal features, MoDM caches final images, allowing seamless retrieval and reuse across multiple diffusion model families. This design enables adaptive serving by dynamically balancing latency and image quality: using smaller models for cache-hit requests to reduce latency while reserving larger models for cache-miss requests to maintain quality. Small model image quality is preserved using retrieved cached images. We design a global monitor that optimally allocates GPU resources and balances inference workload, ensuring high throughput while meeting service-level objectives under varying request rates. Our evaluations show that MoDM significantly reduces average serving time by 2.5x while retaining image quality, making it a practical solution for scalable and resource-efficient model deployment.
Forward citations
Cited by 5 Pith papers
-
Cornfigurator: Automated Planning for Any-to-Any Multimodal Model Serving
Cornfigurator is the first automated deployment planner for generic any-to-any multimodal models that explores the full range of colocation-to-disaggregation strategies and delivers 1.12x to 6.32x higher goodput than ...
-
DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction
DSTAR reports 7.33x latency speedup and 41.89x energy savings over an A100 GPU on seven diffusion transformers by quantizing differential activations to as few as 2 bits and reusing block-wise sparse attention scores.
-
FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving
FlashDiff reduces diffusion serving latency by 30–97% and raises throughput 1.2–2.2× by adaptively skipping refinement of latent regions that no longer need it.
-
TetriServe: Efficiently Serving Mixed DiT Workloads
TetriServe's step-level, deadline-aware sequence parallelism improves SLO attainment for mixed-resolution diffusion transformer serving by up to 32% over fixed-SP systems.
-
FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving
FlashDiff cuts diffusion serving latency 30–97% and raises throughput 1.2–2.2× by selectively executing only active latent regions and rescheduling the reclaimed compute.
Discussion (0). Sign in to comment.