II.
Tool overview
Reference · livetool:onnx-runtime
ONNX Runtime overview
Cross-platform, high-performance ML inference engine for ONNX models. Runs on CPU, CUDA, DirectML, CoreML, ROCm, and other execution providers; supports quantization and graph optimisations. Used for deploying models trained in PyTorch, TensorFlow, or scikit-learn after export to the open ONNX interchange format.
Attributes
displayName
ONNX Runtime
homepageUrl
kind
other
description
Cross-platform, high-performance ML inference engine for ONNX models.
Runs on CPU, CUDA, DirectML, CoreML, ROCm, and other execution providers;
supports quantization and graph optimisations. Used for deploying models
trained in PyTorch, TensorFlow, or scikit-learn after export to the open
ONNX interchange format.
Outgoing edges
alternative_to3
- tool:vllm·ToolvLLM
- tool:tensorrt·ToolTensorRT
- tool:triton-inference·ToolTriton Inference Server
belongs_to_language1
- language:cpp·LanguageC++
tool_used_by2
- skill-area:model-serving·SkillAreaModel Serving
- skill-area:model-optimisation·SkillAreaModel Optimisation
used_for2
- skill-area:model-serving·SkillAreaModel Serving
- skill-area:ai-evaluation·SkillAreaAI Evaluation
Incoming edges
alternative_to3
- tool:vllm·ToolvLLM
- tool:tensorrt·ToolTensorRT
- tool:triton-inference·ToolTriton Inference Server
uses_tool1
- specialization:ml-inference-serving·SpecializationML Inference Serving