DDiT cuts text-to-video serving latency by up to 1.44x via DiT-VAE phase decoupling and step-level, starvation-aware GPU reassignment.
Pixart- 饾憼饾憱饾憯饾憵饾憥: Weak-to-strong training of diffusion transformer for 4k text- to-image generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving
DDiT cuts text-to-video serving latency by up to 1.44x via DiT-VAE phase decoupling and step-level, starvation-aware GPU reassignment.