ONNX Runtime

Microsoft’s high-performance, cross-platform inference engine for ONNX and GenAI models.

Visit Website

Introduction

Overview

ONNX Runtime accelerates >20 frameworks via graph optimizers and hardware EPs (CUDA, DNNL, DirectML, ROCm, CoreML).

Key Capabilities

Training & inference APIs (Python/C#/C++)
ORT-GenAI with flash-attn kernels
Mobile AOT & WebAssembly targets

Back

Information

Websiteonnxruntime.ai
AuthorsMicrosoft
Published date2018/12/04

More Items

Ray

2017

RISELab (UC Berkeley), Anyscale Inc.

Ray is an open-source distributed compute engine that lets you scale Python and AI workloads—from data processing to model training and serving—without deep distributed-systems expertise.

ai-development ai-framework ai-train ai-serving

OpenVINO

2018

Intel

OpenVINO is an open-source toolkit from Intel that streamlines the optimization and deployment of AI inference models across a wide range of Intel® hardware.

ai-development ai-inference ai-serving

NVIDIA Dynamo

2025

NVIDIA

NVIDIA Dynamo is an open-source, high-throughput, low-latency inference framework that scales generative-AI and reasoning models across large, multi-node GPU clusters.

ai-development ai-inference ai-serving nvidia