Checklist Before Starting

• Search for similar PR(s).
• Thanks to:
  • close Refactor/merge sgl rollouts and bump to 0.4.6.post4 #1558 due to mix of prs
  • close [Bug Fix] Use global rank instead of local rank in AsyncSGLangRollout broadcast when TP > 1 #1449 due to partial fix sgl new version issue
  • close chore(deps): bump sglang[all] from 0.4.4.post4 to 0.4.6 #1300 which is part of current pr
• This pr is co-authored with @ocss884

What does this PR do?

Add one-line overview of what this PR aims to achieve or accomplish.

• bump sglang to 0.4.6.post4
• unified sglang and sglang_async generate_sequences api behavior, e.g. image support
• fix warning for cuda barrier at start of fsdp_workers

Checklist Before Submitting

• Read the Contribute Guide.
• Apply pre-commit checks.
• Add [BREAKING] to the PR title if it breaks any API.
• Update the documentation about your changes in the docs.
• Add CI test(s) if necessary.