A high-performance inference engine for ONNX models that runs on CPU, GPU, and specialized hardware across cloud, edge, and mobile.
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.
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。
npx -y tokrepo@latest install 617d3446-4cd0-11f1-9bc6-00163e2b0d79 --target codex先 dry-run 确认安装计划,再运行此命令。
讨论
相关资产
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.
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.
ONNX Runtime — Cross-Platform High-Performance ML Inference
A cross-platform inference and training accelerator from Microsoft that runs ONNX models on CPUs, GPUs, and specialized hardware with optimized execution providers for production deployment.
InsightFace — Open-Source 2D and 3D Face Analysis Toolkit
InsightFace provides state-of-the-art face detection, recognition, alignment, and attribute analysis models including ArcFace and RetinaFace, with support for PyTorch, MXNet, and ONNX Runtime deployment.