Hello,
I was wondering if GTX 1650 can be used to run inference in FP16 with Tensorrt, since it seems to be a Turing architecture.
It would help me if someone could confirm this fact or not.
Thanks for your help :)
Hello,
I was wondering if GTX 1650 can be used to run inference in FP16 with Tensorrt, since it seems to be a Turing architecture.
It would help me if someone could confirm this fact or not.
Thanks for your help :)
Please reference Support Matrix :: NVIDIA Deep Learning TensorRT Documentation
and GTX1650 has SM capability 6.1.