feat: separately wakeup vllm to reduce peak memory in refitting

[zpqiu]

During experiments, I encountered OOM (Out of Memory) issues when waking up VLLM. Additionally, I noticed that in the latest VLLM version 0.8.3, they updated the wakeup API by adding a 'tags' parameter.

What does this PR do ?

Add a one line overview of what this PR aims to accomplish.

As shown in the figure below, we can first load only the weights, then update the parameters, and finally load the KV cache to reduce peak memory usage during the refit_policy_generation phase. This logic has also been implemented in veRL.

Issues

List issues that this PR closes (syntax):

• feat: Upgrade to vllm v1 runtime #170 upgrade vllm

Usage

• You can potentially add a usage example below

# Add a code snippet demonstrating how to use this 

Before your PR is "Ready for review"

Pre checks:

• [x ] Make sure you read and followed Contributor guidelines
• Did you write any new necessary tests?
• Did you run the unit tests and functional tests locally? Visit our Testing Guide for how to run tests
• Did you add or update any necessary documentation? Visit our Document Development Guide for how to write, build and test the docs.

Additional Information

• ...

[parthchadha]

@zpqiu thanks for the suggestion! We have included these changes in #176.