Cyrus Leung

> I think we do not want to add output type as a parameter in `_run_engine(self, output_type: Type[_O], *...)`. If the type checking issue happen we can resolve it in...

> I think we should keep prompts/prompt_tokens_ids input for backward compatibility? These arguments are still being maintained. I just decorated the relevant methods so we can deprecate them simply by...

Pretty sure the CI will pass now.

@njhill I have responded to your comments.

Are you still encountering this issue in the latest version?

Can you try installing the latest vLLM version (`0.5.0.post1`)?

@njhill any update on this? As mentioned in #4194, we would like to work on #4200 in the near future so it would be great if we could get this...

I have merged #4328 into this PR in advance, so you might see additional diffs. These diffs should disappear once #4328 is merged into `main`.

@njhill any update?

@njhill I have updated this PR based on your #6227. PTAL.