int8 quantization support

Open qiangxinglin opened this issue 1 year ago • 1 comments

Firstly, thanks to all of you for the bravo project!

Currently, the model seems like does not support int8 quantization. Any plan on it?

May 30 '24 07:05 qiangxinglin

Thanks for your interest! Does https://github.com/openvinotoolkit/openvino_notebooks/blob/0ba3c0211bcd49aa860369feddffdf7273a73c64/notebooks/yolov10-optimization/yolov10-optimization.ipynb help?

May 30 '24 07:05 jameslahm

Thanks for your interest! Does https://github.com/openvinotoolkit/openvino_notebooks/blob/0ba3c0211bcd49aa860369feddffdf7273a73c64/notebooks/yolov10-optimization/yolov10-optimization.ipynb help?

Hi, this is post-training quantization (ptq). Is there any source for quantization-aware training (qat)?

Jun 11 '24 18:06 yoloyash