[Feature] pipeline.get_logits() support tensor on gpu as input rather than list input
Open
- Dominant language
- Python
- Stars
- 8.1k
- Forks
- 748
- Avg merge
- 6d 2h
- Merged PRs (30d)
- 54
Description
### Motivation
Now the get_logits() function of pipeline only support list input from cpu, could you support tensor input on gpu?
### Related resources
_No response_
### Additional context
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.