Introduction to ONNX Runtime

preview_player
Показать описание
This video provides a brief introduction to the ONNXRuntime-GenAI project and its ecosystem, assuming basic familiarity with LLM inference. It answers key questions, including:
- What is ONNX, and what does an ONNX model look like?
- How does ONNXRuntime execute an ONNX model?
- What is ONNXRuntime-GenAI, and how does it connect with ONNX and ONNXRuntime?
By the end, you'll be prepared for the accompanying notebook to install the library and run your first model inference.

Рекомендации по теме
Комментарии
Автор

ooh hadn't heard of ONNXRuntime-GenAI yet. will it support also diffusion models or focused on LLM?

pharmapsychotic