A split fine-tuning scheme for wireless networks splits an LLM between devices and an edge server, compresses exchanged activations, and jointly optimizes compression, layer split, and bandwidth, cutting simulated fine-tuning delay by up to 80.2% and communication by 93.6%.
DeViT: Decomposing vision transformers for collaborative inference in edge devices,
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
unclear 1representative citing papers
citing papers explorer
-
Split Fine-Tuning for Large Language Models in Wireless Networks
A split fine-tuning scheme for wireless networks splits an LLM between devices and an edge server, compresses exchanged activations, and jointly optimizes compression, layer split, and bandwidth, cutting simulated fine-tuning delay by up to 80.2% and communication by 93.6%.