accept CudaStream as parameter for CudaKernel (#12985)
**Description**: accept CudaStream as parameter for CudaKernel.
**Motivation and Context**
- Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here.
Co-authored-by: Lei Cao <leca@microsoft.com@orttrainingdev9.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
