Open Bug 1932408 Opened 10 days ago Updated 10 days ago

Inference Engine: Memory Efficent model initialization

Categories

(Core :: Machine Learning, enhancement)

Product:
Core
Component:
Machine Learning
Type:
enhancement

Tracking

()

People

(Reporter: atossou, Assigned: atossou)

References

Details

(Whiteboard: [genai])

Currently we send an arraybuffer for the model to onnx.

Onnx support sending a File. So let's send a file for memory efficiency.

You need to log in before you can comment on or make changes to this bug.