ONNX Runtime: Cross-platform inference engine

Fields

id

sources/src5-onnxruntime-github

URL

https://github.com/microsoft/onnxruntime

Publisher

Microsoft

Kind

repo

Published

2019-01-01

Accessed

2026-10-04

notes

ONNX Runtime provides cross-platform inference for ONNX models. Supports CPU, GPU (CUDA, ROCm, DirectML), mobile. Key for model deployment. Used by vLLM, llama.cpp for ONNX model execution. Supports quantization, optimization, multi-threading.

Notes

ONNX Runtime provides cross-platform inference for ONNX models. Supports CPU, GPU (CUDA, ROCm, DirectML), mobile. Key for model deployment. Used by vLLM, llama.cpp for ONNX model execution. Supports quantization, optimization, multi-threading.

Cross-references

This record references no other records.