How to get best performace with optimization with torch_blade

[JackWeiw]

My script compare Torch with Disc

However according to profiling , Disc boost litle compare to Torch, even in some dynamic range worse than torch,.
Is there some i missing to get optimal performance of Disc?

[JackWeiw]

I updated my script like examples in Disc torch inference do, another problem occured

your kindly help is much appriciated!!! @Yancey1989 @eedalong

[JackWeiw]

I passed the half precission model to blade_disc, however, the saved optimized model by blade_disc is fp32, how come?