RuntimeError: Didn't find engine for operation quantized::conv_prepack NoQEngine #29327
There are two libraries we're currently using for quantized operations: fbgemm and qnnpack. Fbgemm today doesn't support window build: pytorch/FBGEMM#150 . Would be nice if someone gave it a try.
For qnnpack - we disable it by default on non-mobile builds:
Afaik, the performance is not that great for qnnpack on x86 cpus and there were some other stability issues. @supriyar - do you know if it's better to reenable it?
As a temp workaround - try setting