[FEA]: Add __int128_t method for cuda::std::abs()

### Is this a duplicate?

- [X] I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cccl/issues) for this request and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md)

### Area

libcu++

### Is your feature request related to a problem? Please describe.

In template code, I need to take the absolute value of a signed integer, but I cannot use cuda::std::abs() as one of the integer types I need to use is __int128_t. Since cuda::std::abs() doesn't support __int128_t, I have to roll my own version instead.

### Describe the solution you'd like

I would like there to be an overload for cuda::std::abs() that takes an __int128_t as an input.

### Describe alternatives you've considered

_No response_

### Additional context

_No response_