This repository was archived by the owner on Jul 1, 2025. It is now read-only.
This repository was archived by the owner on Jul 1, 2025. It is now read-only.
Support directly loading a quantized model. #1727
Description
Currently, the only way to run a quantized model is to do the profiling and reload it. We would like to support to directly load a quantized model. Since there is no quantized ONNX op support yet, we will start with Caffe2 loader. More details will be updated here later.
Metadata
Metadata
Assignees
Labels
No labels