[fx2trt] improve to_dtype (#48)
Summary:
X-link: https://github.com/pytorch/fx2trt/pull/48
Currently, to_dtype can only support
1) to(dtype)
This diff makes this op more capable of handling more cases:
2) to(torch.device) #gpu
3) to(torch.device, dtype) #gpu
(Note: this ignores all push blocking failures!)
Test Plan: buck test mode/dev-nosan deeplearning/trt/fx2trt_oss/test/converters:test_to_dtype
Reviewed By: 842974287
Differential Revision: D35331003
fbshipit-source-id: 4dee2b3c7899805fa4f3c91d0a16207241396647
(cherry picked from commit 18e6c0c060b17eeca38827d015f0d9fae290fc4e)
