Hybrid DPU-GPU CNN inference with GNN-predicted layer splits achieves up to 3.37x lower latency than single-device baselines on tested networks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DPU or GPU for Accelerating Neural Networks Inference -- Why not both? Split CNN Inference
Hybrid DPU-GPU CNN inference with GNN-predicted layer splits achieves up to 3.37x lower latency than single-device baselines on tested networks.