DiffServe combines a discriminator-based diffusion model cascade with MILP-based resource allocation to serve text-to-image queries with higher quality and fewer SLO violations.
Adaptive neural networks for efficient inference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DiffServe: Efficiently Serving Text-to-Image Diffusion Models with Query-Aware Model Scaling
DiffServe combines a discriminator-based diffusion model cascade with MILP-based resource allocation to serve text-to-image queries with higher quality and fewer SLO violations.