2026年4月21日·1 分钟阅读

ONNX Runtime — Cross-Platform ML Model Inference Engine

ONNX Runtime is a high-performance inference engine for machine learning models in the ONNX format. Developed by Microsoft, it accelerates model serving across CPU, GPU, and specialized hardware with a unified API for Python, C++, C#, Java, and JavaScript.

Anonymous
Anonymous · Community
Agent 就绪

Agent 可直接安装

这个资产可安装；Agent 先选择当前运行时、检查安装计划，再运行匹配命令。

Native · 98/100策略：允许
Agent 入口
任意 MCP/CLI Agent
类型
Skill
安装
Single
信任
信任等级：Community
入口
ONNX Runtime Inference
直接安装命令
npx -y tokrepo@latest install 0e90de1c-3d9d-11f1-9bc6-00163e2b0d79 --target codex

先 dry-run 确认安装计划，再运行此命令。

ONNX Runtime is a high-performance inference engine for machine learning models in the ONNX format. Developed by Microsoft, it accelerates model serving across CPU, GPU, and specialized hardware with a unified API for Python, C++, C#, Java, and JavaScript.

讨论

登录后参与讨论。
还没有评论，来写第一条吧。

相关资产

NVIDIA Triton Inference Server — Multi-Framework Model Serving at Scale

Triton Inference Server is NVIDIA's production model serving platform. It deploys models from any framework (PyTorch, TensorFlow, ONNX, TensorRT, Python) with dynamic batching, multi-model ensembles, and hardware-optimized inference.

Skills
NVIDIA

ONNX Runtime — Cross-Platform ML Inference Accelerator

ONNX Runtime is Microsoft's high-performance inference engine for machine learning models in the ONNX format. It supports CPU, GPU, and specialized hardware accelerators across Linux, Windows, macOS, iOS, Android, and the web browser.

Skills
Script Depot

ONNX Runtime — Cross-Platform ML Inference Accelerator

A high-performance inference engine for ONNX models that runs on CPU, GPU, and specialized hardware across cloud, edge, and mobile.

Skills
AI Open Source

ONNX Runtime — Cross-Platform ML Inference and Training Accelerator

High-performance inference engine for ONNX models across CPUs, GPUs, and edge devices with broad framework support.

Scripts
Script Depot
◈首页🔍搜索👤我的