Pith. sign in

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

arxiv 2503.11972 v2 pith:2CRZJWMV submitted 2025-03-15 cs.DC

classification cs.DC
keywords modelsqualityimageimageslatencymodmservingwhile
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Cornfigurator: Automated Planning for Any-to-Any Multimodal Model Serving

    cs.LG 2025-12 conditional novelty 8.0 of 10

    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 ...

  2. DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction

    cs.AR 2026-07 conditional novelty 6.0 of 10

    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.

  3. FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving

    cs.DC 2026-07 conditional novelty 6.0 of 10

    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.

  4. TetriServe: Efficiently Serving Mixed DiT Workloads

    cs.LG 2025-10 conditional novelty 6.0 of 10

    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.

  5. FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving

    cs.DC 2026-07 conditional novelty 5.0 of 10

    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.

Pith tools