Motivation

Support updating the model weights without relaunching the server.
#634

Modification

• Support post a "/update_weights" request in server.py
• Add update_weights methods in tokenizer_manager, tp_worker and model_runner
• Add unit test in test_update_weights.py

Checklist

• Before submitting a PR for review, make sure it has passed verification in your local development environment at least.
• Ensure pre-commit pre-commit run --all-files or other linting tools are used to fix potential lint issues.
• Confirm that modifications are covered by complete unit tests. If not, please add more unit tests for correctness.
• Modify documentation as needed, such as docstrings or example tutorials.