← The AI Systems Map
L2 · ChipsStandard / protocol

ONNX

Open model-exchange format for interop

ONNX is the open intermediate format for exchanging trained models between frameworks and runtimes (ONNX Runtime, edge deployments), important for portability and edge/embedded inference. It is a neutrality layer that lets models move off any single training framework or vendor runtime.

Steward

LF AI & Data

Use

cross-runtime model exchange

How it fits the stack

ONNX with what it depends on (above) and what it feeds (below). The figure renders as a crawlable diagram and upgrades to an interactive 3D graph as it scrolls into view.

used byONNXChipsOn-device / edgeinference (NPUs, GGUF)
ONNXFeeds ↓

ONNX in the AI stack. ONNX with its immediate upstream dependencies (top) and downstream dependents (bottom) in the AI value chain. Hover a node in 3D, or read the full relationships below.

Graph data (text) — 2 entities, 1 relationships
  • On-device / edge inference (NPUs, GGUF)used byONNX