ChunkFlow achieves up to 1.28x step-time speedup and up to 49% lower peak GPU memory for DiT inference by using a first-order model to guide communication-aware chunked prefetching.
Gonzalez, Matei Zaharia, and Ion Stoica
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
ChunkFlow: Communication-Aware Chunked Prefetching for Layerwise Offloading in Distributed Diffusion Transformer Inference
ChunkFlow achieves up to 1.28x step-time speedup and up to 49% lower peak GPU memory for DiT inference by using a first-order model to guide communication-aware chunked prefetching.