Hi there!
I was playing around with the quantization & there’s a run-time issue I’m facing while running it locally, while it works on google colab.
Here’s an error statement: Didn’t find engine for operation quantized::linear_prepack NoQEngine
I checked the torch version which is 2.2.1 in my case (local machine), while it’s 2.2.1+cu121 in the Google colab case.
I’d appreciate a help.
Thanks!
