[BUG]: cuda.parallel: radix_sort unit tests failing on T-4 runners

### Is this a duplicate?

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

### Type of Bug

Silent Failure

### Component

cuda.parallel (Python)

### Describe the bug

Noticed a couple of radix_sort tests failing when I switched to using T-4 runners: https://github.com/NVIDIA/cccl/actions/runs/15158015134/job/42617959618?pr=4721

### How to Reproduce

-

### Expected behavior

-

### Reproduction link

_No response_

### Operating System

_No response_

### nvidia-smi output

_No response_

### NVCC version

_No response_