ConceptSplit Inference / split inference
Split Inference
An inference paradigm in edge AI that partitions a neural network by layers into multiple sub-models deployed on different nodes (device, edge, cloud). Intermediate tensors are transmitted over the network to address computing-power and memory constraints on the device side.
Timeline (last 90 days)
Oct 14
The research proposes Inference on Demand (IoD), attempting to turn split inference from a private implementation at the application layer into a service that can be recognized and scheduled by the network on the 5G user plane.
Unverified50%