TECHNOLOGY PROFILE · TECH-0180
ONNX Runtime
Cross-platform execution engine for ONNX and supported model formats.
Reference link only — not reviewed this edition. This profile preserves the prepared catalog’s original descriptions. Advantages depend on the workload; comparisons are editorial, not benchmark results.
Where it has an edge
Execution providers let one exported model target multiple supported accelerators without shipping its training framework.
Best-fit problems
Portable application inference and optimized conventional neural models.
Tradeoffs & cautions
Export fidelity and operator coverage need correctness tests.
What to test before choosing
Replay representative concurrency and context lengths; measure p50/p95 latency, throughput, memory and error rate.
Runtime & hardware
Usually server CPU/GPU
Access & licensing
Open-source core; deployment costs separate
Execution
Local / self-hosted
Lifecycle
Not independently audited
Comparison basis
Editorial problem-fit judgement; no head-to-head benchmark performed
Connected concepts
Alternatives to investigate
OpenVINO · TensorRT · ExecuTorch