ONNX

1. ONNX concepts

   Graphs, nodes, initializers, operators, opsets, and the ONNX model format.

2. Python API and building models

   Constructing, loading, and saving ONNX models with the helper API.

3. Operators

   The standard operator set and versioned operator definitions.

4. Model checker

   Validating models against the specification.

5. Shape inference

   Propagating tensor shapes and types through a graph.

6. Version converter

   Converting models between opset versions.

7. Functions and custom domains

   Converting from training frameworks and reusing subgraphs as functions.

8. Reference implementation

   Evaluating models in pure Python for testing.

9. ONNX Runtime

   Executing ONNX models with execution providers and optimization.

Each section links to the official page. Titles and summaries by Extra Credit; the docs belong to their authors.

• LlamaIndex
• LLM engineering
• MCP
• Mistral AI
• MLflow
• Ollama
• OpenAI
• OpenCV
• PyTorch
• Ray
• Replicate
• scikit-learn