ONNX Runtime

Cross-platform, high performance ML inferencing and training accelerator

C-
Score: 50/100
Type
Execution
hybrid
Interface
sdk

About

ONNX Runtime is a cross-platform inference and training machine-learning accelerator. It supports models in ONNX format with execution providers for CUDA, DirectML, CoreML, and more. Used for optimized LLM inference in production scenarios.

Performance

500ms
Cold Start
300MB
Base Memory
100ms
Startup Overhead

Last Verified

Date: Jan 18, 2026
Method: manual test

Manually verified

Languages

PythonC++C#Java

Details

Isolation
process
Maturity
production
License
MIT

Links